Copy disabled (too large)
Download .txt
Showing preview only (105,914K chars total). Download the full file to get everything.
Repository: microsoft/TinyTroupe
Branch: main
Commit: 8378a1138f83
Files: 1516
Total size: 313.6 MB
Directory structure:
gitextract_rb6ph2t1/
├── .gitattributes
├── .github/
│ ├── copilot-instructions.md
│ ├── project-copilot-instructions.md
│ ├── prompts/
│ │ ├── improve.prompt.md
│ │ ├── open-ended_ideas.prompt.md
│ │ └── write_tests.prompt.md
│ └── workflows/
│ ├── bandit.yml
│ └── codeql.yml
├── .gitignore
├── CODE_OF_CONDUCT.md
├── LICENSE
├── MANIFEST.in
├── README.md
├── RESPONSIBLE_AI_FAQ.md
├── SECURITY.md
├── SUPPORT.md
├── build_and_install_package_from_repo.bat
├── build_package.bat
├── config.ini
├── data/
│ ├── empirical/
│ │ ├── 07.17.2025 - Market Research - AI-enabled story telling device or app - Raw Data.csv
│ │ └── 07.19.2025 - Market Research - Bottled Gazpacho - Raw Data.csv
│ ├── extractions/
│ │ ├── appartment_rent_ad.extraction.json
│ │ ├── appartment_rent_ad_1.extraction.json
│ │ ├── synthetic_data_generation.out.csv
│ │ └── wordprocessor/
│ │ └── Document/
│ │ ├── Lisa Carter - Resume.Lisa Carter.docx
│ │ ├── Lisa Carter - Resume.Lisa Carter.json
│ │ ├── Lisa Carter - Resume.Lisa Carter.md
│ │ ├── Resume of Lisa Carter.Lisa Carter.docx
│ │ ├── Resume of Lisa Carter.Lisa Carter.json
│ │ ├── Resume of Lisa Carter.Lisa Carter.md
│ │ ├── Resume of Lisa.Lisa.docx
│ │ ├── Resume of Lisa.Lisa.json
│ │ ├── Resume of Lisa.Lisa.md
│ │ └── Resume.Lisa.docx
│ ├── facts/
│ │ └── business-facts.synthetic.txt
│ └── grounding_examples/
│ ├── grounding_examples_1/
│ │ ├── don_quijote_project_gutenberg.txt
│ │ └── marus_aurelius_meditations_by_project_gutenberg.txt
│ └── grounding_microsoft/
│ ├── 2023_Microsoft_Annual_Report.docx
│ └── 2024_Annual_Report.docx
├── docs/
│ ├── api/
│ │ └── tinytroupe/
│ │ ├── agent/
│ │ │ ├── action_generator.html
│ │ │ ├── grounding.html
│ │ │ ├── index.html
│ │ │ ├── memory.html
│ │ │ ├── mental_faculty.html
│ │ │ └── tiny_person.html
│ │ ├── clients/
│ │ │ ├── azure_client.html
│ │ │ ├── index.html
│ │ │ ├── ollama_client.html
│ │ │ └── openai_client.html
│ │ ├── control.html
│ │ ├── enrichment/
│ │ │ ├── index.html
│ │ │ ├── tiny_enricher.html
│ │ │ └── tiny_styler.html
│ │ ├── environment/
│ │ │ ├── index.html
│ │ │ ├── tiny_social_network.html
│ │ │ └── tiny_world.html
│ │ ├── examples/
│ │ │ ├── agents.html
│ │ │ ├── index.html
│ │ │ └── loaders.html
│ │ ├── experimentation/
│ │ │ ├── in_place_experiment_runner.html
│ │ │ ├── index.html
│ │ │ ├── proposition.html
│ │ │ ├── randomization.html
│ │ │ └── statistical_tests.html
│ │ ├── extraction/
│ │ │ ├── artifact_exporter.html
│ │ │ ├── index.html
│ │ │ ├── normalizer.html
│ │ │ ├── results_extractor.html
│ │ │ ├── results_reducer.html
│ │ │ └── results_reporter.html
│ │ ├── factory/
│ │ │ ├── index.html
│ │ │ ├── tiny_factory.html
│ │ │ └── tiny_person_factory.html
│ │ ├── index.html
│ │ ├── profiling.html
│ │ ├── steering/
│ │ │ ├── index.html
│ │ │ ├── intervention.html
│ │ │ └── tiny_story.html
│ │ ├── tools/
│ │ │ ├── index.html
│ │ │ ├── tiny_calendar.html
│ │ │ ├── tiny_tool.html
│ │ │ └── tiny_word_processor.html
│ │ ├── ui/
│ │ │ ├── index.html
│ │ │ └── jupyter_widgets.html
│ │ ├── utils/
│ │ │ ├── behavior.html
│ │ │ ├── concurrency.html
│ │ │ ├── config.html
│ │ │ ├── index.html
│ │ │ ├── json.html
│ │ │ ├── llm.html
│ │ │ ├── misc.html
│ │ │ ├── parallel.html
│ │ │ ├── rendering.html
│ │ │ ├── semantics.html
│ │ │ └── validation.html
│ │ └── validation/
│ │ ├── index.html
│ │ ├── propositions.html
│ │ ├── simulation_validator.html
│ │ ├── tiny_person_validator.html
│ │ └── validation_chamber.html
│ ├── guides/
│ │ └── ollama.md
│ └── index.html
├── examples/
│ ├── AI-enabled Children Story Telling Market Research 2.ipynb
│ ├── AI-enabled Children Story Telling Market Research.ipynb
│ ├── Advertisement for TV.ipynb
│ ├── Bottled Gazpacho Market Research 2.archival.ipynb
│ ├── Bottled Gazpacho Market Research 3.archival.ipynb
│ ├── Bottled Gazpacho Market Research 4.archival.ipynb
│ ├── Bottled Gazpacho Market Research 4b.archival.ipynb
│ ├── Bottled Gazpacho Market Research 5 (with behavior correction).ipynb
│ ├── Bottled Gazpacho Market Research 5.ipynb
│ ├── Bottled Gazpacho Market Research 5b.ipynb
│ ├── Bottled Gazpacho Market Research 5c.ipynb
│ ├── Bottled Gazpacho Market Research.archival.ipynb
│ ├── Create Ad for Apartment.ipynb
│ ├── Creating and Validating Agents.ipynb
│ ├── Interview with Customer.ipynb
│ ├── Investment Firm.ipynb
│ ├── Online Advertisement for Travel.ipynb
│ ├── Political Compass (customizing agents with fragments).ipynb
│ ├── Product Brainstorming (with behavior correction).ipynb
│ ├── Product Brainstorming.ipynb
│ ├── Simple Chat.ipynb
│ ├── Story telling (long narratives).ipynb
│ ├── Synthetic Data Generation 1.ipynb
│ ├── Synthetic Data Generation 2 (tool usage).ipynb
│ ├── Synthetic Data Generation.ipynb
│ ├── Travel Product Market Research.ipynb
│ ├── Word Processor Tool Usage.ipynb
│ ├── agents/
│ │ ├── Friedrich_Wolf.agent.json
│ │ ├── Lila.agent.json
│ │ ├── Lisa.agent.json
│ │ ├── Marcos.agent.json
│ │ ├── Oscar.agent.json
│ │ ├── Paulo_Salem.agent.json
│ │ └── Sophie_Lefevre.agent.json
│ ├── archive/
│ │ ├── AI-enabled Children Story Telling Market Research.ipynb
│ │ ├── Bottled Gazpacho Market Research 2.archival.ipynb
│ │ ├── Bottled Gazpacho Market Research 3.archival.ipynb
│ │ ├── Bottled Gazpacho Market Research 4.archival.ipynb
│ │ ├── Bottled Gazpacho Market Research 4b.archival.ipynb
│ │ ├── Bottled Gazpacho Market Research 5b.ipynb
│ │ ├── Bottled Gazpacho Market Research 5c.ipynb
│ │ └── Bottled Gazpacho Market Research.archival.ipynb
│ ├── config.ini
│ ├── extractions/
│ │ └── synthetic_data_example_3/
│ │ └── Document/
│ │ ├── MultiLever Rapid Response Report- Stabilizing Demand under High Inflation.Lisa Carter.docx
│ │ ├── MultiLever Rapid Response Report- Stabilizing Demand under High Inflation.Lisa Carter.json
│ │ ├── MultiLever Rapid Response Report- Stabilizing Demand under High Inflation.Lisa Carter.md
│ │ ├── MultiLever — Initial Rapid Diagnostic & Recommendations (Client Brief).Lisa Carter.docx
│ │ ├── MultiLever — Initial Rapid Diagnostic & Recommendations (Client Brief).Lisa Carter.json
│ │ ├── MultiLever — Initial Rapid Diagnostic & Recommendations (Client Brief).Lisa Carter.md
│ │ ├── MultiLever — Rapid Diagnostic & Recommendations.Lisa Carter.docx
│ │ ├── MultiLever — Rapid Diagnostic & Recommendations.Lisa Carter.json
│ │ ├── MultiLever — Rapid Diagnostic & Recommendations.Lisa Carter.md
│ │ ├── Port Aurora u0007 Rapid Flood Resilience Plan u0007 Initial Report and Recommended Next Steps.Lisa Carter.docx
│ │ ├── Port Aurora u0007 Rapid Flood Resilience Plan u0007 Initial Report and Recommended Next Steps.Lisa Carter.json
│ │ ├── Port Aurora u0007 Rapid Flood Resilience Plan u0007 Initial Report and Recommended Next Steps.Lisa Carter.md
│ │ ├── Rapid Delivery Plan- Phase 1 FEMA-compliant Procurement and Upgrade Path.Lisa Carter.docx
│ │ ├── Rapid Delivery Plan- Phase 1 FEMA-compliant Procurement and Upgrade Path.Lisa Carter.json
│ │ └── Rapid Delivery Plan- Phase 1 FEMA-compliant Procurement and Upgrade Path.Lisa Carter.md
│ ├── fragments/
│ │ ├── aggressive_debater.fragment.json
│ │ ├── authoritarian.agent.fragment.json
│ │ ├── genuine.agent.fragment.json
│ │ ├── leftwing.agent.fragment.json
│ │ ├── libertarian.agent.fragment.json
│ │ ├── loving_parent.agent.fragment.json
│ │ ├── picky_customer.agent.fragment.json
│ │ ├── rightwing.agent.fragment.json
│ │ └── travel_enthusiast.agent.fragment.json
│ ├── information/
│ │ └── populations/
│ │ ├── brazil.json
│ │ ├── spain.json
│ │ └── usa.json
│ ├── ollama/
│ │ ├── Simple Chat.ipynb
│ │ └── config.ini
│ └── scratch/
│ ├── Advertisement for TV.ipynb
│ ├── Simulation Experiment Empirical Validation Example.ipynb
│ ├── config.ini
│ └── tool_usage.ipynb
├── generate_api_documentation.bat
├── install_package_from_repo.bat
├── publications/
│ ├── README.md
│ ├── paper_artifacts_june-2025/
│ │ ├── Brainstorming and Focus Group Quantitative Experimentation 1 - treatment run.ipynb
│ │ ├── Brainstorming and Focus Group Quantitative Experimentation 1.ipynb
│ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.1 - treatment run.ipynb
│ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.1.ipynb
│ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.2 - treatment run.ipynb
│ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.2.ipynb
│ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.3 - treatment run.ipynb
│ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.3.ipynb
│ │ ├── Debating Quantitative Experimentation 1 - treatment run.ipynb
│ │ ├── Debating Quantitative Experimentation 1.ipynb
│ │ ├── Food Products Ideas Brainstorming.ipynb
│ │ ├── Market Research Quantitative Experimentation 1.ipynb
│ │ ├── Market Research Quantitative Experimentation 2.ipynb
│ │ ├── Opinion Poll Quantitative Experimentation.ipynb
│ │ ├── Political Compass (customizing agents with fragments).ipynb
│ │ ├── Populations creation.ipynb
│ │ ├── Spicy Food Market Research.ipynb
│ │ ├── Synthetic Data Generation.ipynb
│ │ ├── Travel Product Market Research (with behavior correction).ipynb
│ │ ├── Travel Product Market Research.ipynb
│ │ ├── brainstorming_and_focus_group_quantitative_experimentation_1c.json
│ │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.1c.json
│ │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.2b.json
│ │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.3.json
│ │ ├── common_utils.py
│ │ ├── config.ini
│ │ ├── debating_quantitative_experimentation_1c.json
│ │ ├── extractions/
│ │ │ ├── synthetic_data_example_1/
│ │ │ │ └── Document/
│ │ │ │ ├── Report for AquaPure Solutions- Strategies for Modernizing Water Purification Systems.Lisa Carter.docx
│ │ │ │ ├── Report for AquaPure Solutions- Strategies for Modernizing Water Purification Systems.Lisa Carter.json
│ │ │ │ ├── Report for AquaPure Solutions- Strategies for Modernizing Water Purification Systems.Lisa Carter.md
│ │ │ │ ├── Report for BioSphere Innovations- Feasibility Study for Waste-to-Energy Solution.Lisa Carter.docx
│ │ │ │ ├── Report for BioSphere Innovations- Feasibility Study for Waste-to-Energy Solution.Lisa Carter.json
│ │ │ │ ├── Report for BioSphere Innovations- Feasibility Study for Waste-to-Energy Solution.Lisa Carter.md
│ │ │ │ ├── Report for BrightPath Industries- Strategies for Enhancing Supply Chain Resilience.Lisa Carter.docx
│ │ │ │ ├── Report for BrightPath Industries- Strategies for Enhancing Supply Chain Resilience.Lisa Carter.json
│ │ │ │ ├── Report for BrightPath Industries- Strategies for Enhancing Supply Chain Resilience.Lisa Carter.md
│ │ │ │ ├── Report for CleanFuture Corp- Strategies for Reshaping Public Image and Sustainability Practices.Lisa Carter.docx
│ │ │ │ ├── Report for CleanFuture Corp- Strategies for Reshaping Public Image and Sustainability Practices.Lisa Carter.json
│ │ │ │ ├── Report for CleanFuture Corp- Strategies for Reshaping Public Image and Sustainability Practices.Lisa Carter.md
│ │ │ │ ├── Report for EcoFuture Enterprises- Strategies for Sourcing Sustainable Materials.Lisa Carter.docx
│ │ │ │ ├── Report for EcoFuture Enterprises- Strategies for Sourcing Sustainable Materials.Lisa Carter.json
│ │ │ │ ├── Report for EcoFuture Enterprises- Strategies for Sourcing Sustainable Materials.Lisa Carter.md
│ │ │ │ ├── Report for EcoTech Solutions- Strategies for Enhancing Product Appeal and Market Presence.Lisa Carter.docx
│ │ │ │ ├── Report for EcoTech Solutions- Strategies for Enhancing Product Appeal and Market Presence.Lisa Carter.json
│ │ │ │ ├── Report for EcoTech Solutions- Strategies for Enhancing Product Appeal and Market Presence.Lisa Carter.md
│ │ │ │ ├── Report for GreenWave Innovations- Strategies for Reducing Waste and Enhancing Sustainability.Lisa Carter.docx
│ │ │ │ ├── Report for GreenWave Innovations- Strategies for Reducing Waste and Enhancing Sustainability.Lisa Carter.json
│ │ │ │ ├── Report for GreenWave Innovations- Strategies for Reducing Waste and Enhancing Sustainability.Lisa Carter.md
│ │ │ │ ├── Report for MultiLever- Strategies for Addressing Inflation and Enhancing Consumer Demand.Lisa Carter.docx
│ │ │ │ ├── Report for MultiLever- Strategies for Addressing Inflation and Enhancing Consumer Demand.Lisa Carter.json
│ │ │ │ ├── Report for MultiLever- Strategies for Addressing Inflation and Enhancing Consumer Demand.Lisa Carter.md
│ │ │ │ ├── Report for SolarWave Technologies- Strategies for Securing Funding for Solar Panel Project.Lisa Carter.docx
│ │ │ │ ├── Report for SolarWave Technologies- Strategies for Securing Funding for Solar Panel Project.Lisa Carter.json
│ │ │ │ ├── Report for SolarWave Technologies- Strategies for Securing Funding for Solar Panel Project.Lisa Carter.md
│ │ │ │ ├── Report for TerraBuild- Strategies for Reducing Carbon Footprint and Improving Public Image.Lisa Carter.docx
│ │ │ │ ├── Report for TerraBuild- Strategies for Reducing Carbon Footprint and Improving Public Image.Lisa Carter.json
│ │ │ │ ├── Report for TerraBuild- Strategies for Reducing Carbon Footprint and Improving Public Image.Lisa Carter.md
│ │ │ │ ├── Report for UrbanGreen- Strategies for Sustainable Urban Development Projects.Lisa Carter.docx
│ │ │ │ ├── Report for UrbanGreen- Strategies for Sustainable Urban Development Projects.Lisa Carter.json
│ │ │ │ └── Report for UrbanGreen- Strategies for Sustainable Urban Development Projects.Lisa Carter.md
│ │ │ └── synthetic_data_example_2/
│ │ │ └── Document/
│ │ │ ├── Report for AquaPure- Sustainable Funding Model and Operational Efficiency Improvement.Lisa Carter.docx
│ │ │ ├── Report for AquaPure- Sustainable Funding Model and Operational Efficiency Improvement.Lisa Carter.json
│ │ │ ├── Report for AquaPure- Sustainable Funding Model and Operational Efficiency Improvement.Lisa Carter.md
│ │ │ ├── Report for EcoTech Innovations- Strategies for Improving Visibility and Consumer Engagement.Lisa Carter.docx
│ │ │ ├── Report for EcoTech Innovations- Strategies for Improving Visibility and Consumer Engagement.Lisa Carter.json
│ │ │ ├── Report for EcoTech Innovations- Strategies for Improving Visibility and Consumer Engagement.Lisa Carter.md
│ │ │ ├── Report for FinTech Nexus- Strategies for Competitive Advantage and Compliance Navigation.Lisa Carter.docx
│ │ │ ├── Report for FinTech Nexus- Strategies for Competitive Advantage and Compliance Navigation.Lisa Carter.json
│ │ │ ├── Report for FinTech Nexus- Strategies for Competitive Advantage and Compliance Navigation.Lisa Carter.md
│ │ │ ├── Report for GreenWave Logistics- Sustainable Logistics Model Development.Lisa Carter.docx
│ │ │ ├── Report for GreenWave Logistics- Sustainable Logistics Model Development.Lisa Carter.json
│ │ │ ├── Report for GreenWave Logistics- Sustainable Logistics Model Development.Lisa Carter.md
│ │ │ ├── Report for MedTech Solutions- Strategies for Regulatory Compliance and Market Penetration.Lisa Carter.docx
│ │ │ ├── Report for MedTech Solutions- Strategies for Regulatory Compliance and Market Penetration.Lisa Carter.json
│ │ │ ├── Report for MedTech Solutions- Strategies for Regulatory Compliance and Market Penetration.Lisa Carter.md
│ │ │ ├── Report for MultiLever- Strategies to Address Inflation and Decreased Consumer Demand.Lisa Carter.docx
│ │ │ ├── Report for MultiLever- Strategies to Address Inflation and Decreased Consumer Demand.Lisa Carter.json
│ │ │ ├── Report for MultiLever- Strategies to Address Inflation and Decreased Consumer Demand.Lisa Carter.md
│ │ │ ├── Report for SafeHaven- Strategies for Streamlining Claims Processing and Improving Communication.Lisa Carter.docx
│ │ │ ├── Report for SafeHaven- Strategies for Streamlining Claims Processing and Improving Communication.Lisa Carter.json
│ │ │ ├── Report for SafeHaven- Strategies for Streamlining Claims Processing and Improving Communication.Lisa Carter.md
│ │ │ ├── Report for StellarTech- Streamlining Operations and Navigating Regulatory Compliance.Lisa Carter.docx
│ │ │ ├── Report for StellarTech- Streamlining Operations and Navigating Regulatory Compliance.Lisa Carter.json
│ │ │ ├── Report for StellarTech- Streamlining Operations and Navigating Regulatory Compliance.Lisa Carter.md
│ │ │ ├── Report for TechSphere- Crisis Management and Cybersecurity Enhancement Strategies.Lisa Carter.docx
│ │ │ ├── Report for TechSphere- Crisis Management and Cybersecurity Enhancement Strategies.Lisa Carter.json
│ │ │ ├── Report for TechSphere- Crisis Management and Cybersecurity Enhancement Strategies.Lisa Carter.md
│ │ │ ├── Report for UrbanGrow- Strategies for Addressing Climate Change and Supply Chain Disruptions.Lisa Carter.docx
│ │ │ ├── Report for UrbanGrow- Strategies for Addressing Climate Change and Supply Chain Disruptions.Lisa Carter.json
│ │ │ ├── Report for UrbanGrow- Strategies for Addressing Climate Change and Supply Chain Disruptions.Lisa Carter.md
│ │ │ ├── Report for UrbanHealth- Comprehensive Outreach Strategy and Funding Proposal.Lisa Carter.docx
│ │ │ ├── Report for UrbanHealth- Comprehensive Outreach Strategy and Funding Proposal.Lisa Carter.json
│ │ │ └── Report for UrbanHealth- Comprehensive Outreach Strategy and Funding Proposal.Lisa Carter.md
│ │ ├── food_products_brainstorming_2.json
│ │ ├── fragments/
│ │ │ ├── aggressive_debater.fragment.json
│ │ │ ├── authoritarian.agent.fragment.json
│ │ │ ├── difficult_person.agent.fragment.json
│ │ │ ├── leftwing.agent.fragment.json
│ │ │ ├── libertarian.agent.fragment.json
│ │ │ ├── loving_parent.agent.fragment.json
│ │ │ ├── picky_customer.agent.fragment copy.json
│ │ │ ├── picky_customer.agent.fragment.json
│ │ │ └── rightwing.agent.fragment.json
│ │ ├── information/
│ │ │ └── populations/
│ │ │ ├── brazil.json
│ │ │ ├── china.json
│ │ │ ├── india.json
│ │ │ ├── mexico.json
│ │ │ ├── norway.json
│ │ │ ├── scandinavia.json
│ │ │ └── usa.json
│ │ ├── market_research_quantitative_experimentation_1.json
│ │ ├── market_research_quantitative_experimentation_2.json
│ │ ├── market_research_utils.py
│ │ ├── opinion_poll_quantitative_experimentation_1.json
│ │ ├── population/
│ │ │ ├── difficult_people/
│ │ │ │ ├── Benjamin Carter.agent.json
│ │ │ │ ├── Benjamin Hall.agent.json
│ │ │ │ ├── Chloe Turner.agent.json
│ │ │ │ ├── Clara Johnson.agent.json
│ │ │ │ ├── Clara White.agent.json
│ │ │ │ ├── Ella Johnson.agent.json
│ │ │ │ ├── Gabriel White.agent.json
│ │ │ │ ├── Gavin Lewis.agent.json
│ │ │ │ ├── Henry White.agent.json
│ │ │ │ ├── Isaac Anderson.agent.json
│ │ │ │ ├── Isaac Brooks.agent.json
│ │ │ │ ├── Isaac Turner.agent.json
│ │ │ │ ├── Jasmine Brooks.agent.json
│ │ │ │ ├── Katherine Hall.agent.json
│ │ │ │ ├── Liam Foster.agent.json
│ │ │ │ ├── Nora Adams.agent.json
│ │ │ │ ├── Nora Mitchell.agent.json
│ │ │ │ ├── Sophie Johnson.agent.json
│ │ │ │ ├── Victoria Hall.agent.json
│ │ │ │ └── Zoe Mitchell.agent.json
│ │ │ ├── global_general/
│ │ │ │ ├── Amelia Scott.agent.json
│ │ │ │ ├── Ava Patel.agent.json
│ │ │ │ ├── Benjamin Taylor.agent.json
│ │ │ │ ├── Charlotte Nguyen.agent.json
│ │ │ │ ├── Daniel Clark.agent.json
│ │ │ │ ├── Daniel Evans.agent.json
│ │ │ │ ├── Ella Lewis.agent.json
│ │ │ │ ├── Emily Foster.agent.json
│ │ │ │ ├── Emma Thompson.agent.json
│ │ │ │ ├── Ethan Singh.agent.json
│ │ │ │ ├── Grace Harris.agent.json
│ │ │ │ ├── Isabella Martinez.agent.json
│ │ │ │ ├── James Rodriguez.agent.json
│ │ │ │ ├── Liam Chen.agent.json
│ │ │ │ ├── Lily Carter.agent.json
│ │ │ │ ├── Lucas Wilson.agent.json
│ │ │ │ ├── Mason Brown.agent.json
│ │ │ │ ├── Matthew Young.agent.json
│ │ │ │ ├── Noah Kim.agent.json
│ │ │ │ └── Samuel Turner.agent.json
│ │ │ ├── mexico_general/
│ │ │ │ ├── Ana Maria Herrera.agent.json
│ │ │ │ ├── Ana Maria Salazar.agent.json
│ │ │ │ ├── Camila Rojas.agent.json
│ │ │ │ ├── Camila Salazar.agent.json
│ │ │ │ ├── Camila Torres.agent.json
│ │ │ │ ├── Carlos Herrera.agent.json
│ │ │ │ ├── Carlos Mendoza.agent.json
│ │ │ │ ├── Diego Mendoza.agent.json
│ │ │ │ ├── Diego Morales.agent.json
│ │ │ │ ├── Diego Salazar.agent.json
│ │ │ │ ├── Fernando Ramirez.agent.json
│ │ │ │ ├── Isabel Gonzalez.agent.json
│ │ │ │ ├── Isabel Rojas.agent.json
│ │ │ │ ├── Isabella Rojas.agent.json
│ │ │ │ ├── Lucia Morales.agent.json
│ │ │ │ ├── Santiago Jimenez.agent.json
│ │ │ │ ├── Santiago Rojas.agent.json
│ │ │ │ ├── Valeria Jimenez.agent.json
│ │ │ │ ├── Valeria Morales.agent.json
│ │ │ │ └── Valeria Torres.agent.json
│ │ │ ├── misc/
│ │ │ │ ├── Daniel Harris (Market Researcher).agent.json
│ │ │ │ └── Oscar.agent.json
│ │ │ ├── norway_general/
│ │ │ │ ├── Astrid Johansen.agent.json
│ │ │ │ ├── Astrid Nilsen.agent.json
│ │ │ │ ├── Astrid Sørensen.agent.json
│ │ │ │ ├── Emil Bergstrom.agent.json
│ │ │ │ ├── Emil Knudsen.agent.json
│ │ │ │ ├── Freja Eriksen.agent.json
│ │ │ │ ├── Freja Johansen.agent.json
│ │ │ │ ├── Henrik Berg.agent.json
│ │ │ │ ├── Henrik Eriksen.agent.json
│ │ │ │ ├── Ingrid Knudsen.agent.json
│ │ │ │ ├── Ingrid Lund.agent.json
│ │ │ │ ├── Ingrid Madsen.agent.json
│ │ │ │ ├── Ingrid Sørensen.agent.json
│ │ │ │ ├── Kari Madsen.agent.json
│ │ │ │ ├── Lars Nilsen.agent.json
│ │ │ │ ├── Magnus Knudsen.agent.json
│ │ │ │ ├── Magnus Sørensen.agent.json
│ │ │ │ ├── Oskar Berg.agent.json
│ │ │ │ ├── Sofie Lundgren.agent.json
│ │ │ │ └── Sofie Sørensen.agent.json
│ │ │ ├── political_compass/
│ │ │ │ ├── Aiden Lewis.agent.json
│ │ │ │ ├── Benjamin Carter.agent.json
│ │ │ │ ├── Chloe Mitchell.agent.json
│ │ │ │ ├── Chloe White.agent.json
│ │ │ │ ├── Ethan Brooks.agent.json
│ │ │ │ ├── Ethan Rivera.agent.json
│ │ │ │ ├── Ethan Young.agent.json
│ │ │ │ ├── Evelyn Carter.agent.json
│ │ │ │ ├── Grace Adams.agent.json
│ │ │ │ ├── Henry Johnson.agent.json
│ │ │ │ ├── Isabella Martinez.agent.json
│ │ │ │ ├── Jessica Martinez.agent.json
│ │ │ │ ├── Natalie Brown.agent.json
│ │ │ │ ├── Noah Anderson.agent.json
│ │ │ │ ├── Noah Davis.agent.json
│ │ │ │ ├── Olivia Foster.agent.json
│ │ │ │ ├── Olivia Harris.agent.json
│ │ │ │ ├── Samuel Reed.agent.json
│ │ │ │ ├── Sophia Lewis.agent.json
│ │ │ │ └── Sophia Turner.agent.json
│ │ │ ├── usa_couples/
│ │ │ │ ├── Aiden Garcia.agent.json
│ │ │ │ ├── Aiden Lee.agent.json
│ │ │ │ ├── Aiden Martinez.agent.json
│ │ │ │ ├── Aiden Thompson.agent.json
│ │ │ │ ├── Chloe Adams.agent.json
│ │ │ │ ├── Chloe Garcia.agent.json
│ │ │ │ ├── Chloe Kim.agent.json
│ │ │ │ ├── David Kim.agent.json
│ │ │ │ ├── David Nguyen.agent.json
│ │ │ │ ├── David Patel.agent.json
│ │ │ │ ├── David Wilson.agent.json
│ │ │ │ ├── Ella Adams.agent.json
│ │ │ │ ├── Ella Brown.agent.json
│ │ │ │ ├── Ella Garcia.agent.json
│ │ │ │ ├── Ella Johnson.agent.json
│ │ │ │ ├── Ella Rodriguez.agent.json
│ │ │ │ ├── Emily Chen.agent.json
│ │ │ │ ├── Emily Rodriguez.agent.json
│ │ │ │ ├── Grace Adams.agent.json
│ │ │ │ ├── Grace Johnson.agent.json
│ │ │ │ ├── Grace Nguyen.agent.json
│ │ │ │ ├── Grace Patel.agent.json
│ │ │ │ ├── Isabella Garcia.agent.json
│ │ │ │ ├── Isabella Lee.agent.json
│ │ │ │ ├── Isabella White.agent.json
│ │ │ │ ├── James Brown.agent.json
│ │ │ │ ├── James Nguyen.agent.json
│ │ │ │ ├── James Patel.agent.json
│ │ │ │ ├── James Thompson.agent.json
│ │ │ │ ├── Lucas Kim.agent.json
│ │ │ │ ├── Mia Carter.agent.json
│ │ │ │ ├── Mia Garcia.agent.json
│ │ │ │ ├── Mia Rodriguez.agent.json
│ │ │ │ ├── Oliver Garcia.agent.json
│ │ │ │ ├── Oliver Kim.agent.json
│ │ │ │ ├── Oliver Thompson.agent.json
│ │ │ │ ├── Sofia Johnson.agent.json
│ │ │ │ ├── Sofia Kim.agent.json
│ │ │ │ ├── Sofia Lee.agent.json
│ │ │ │ └── Sofia Martinez.agent.json
│ │ │ ├── usa_couples_2/
│ │ │ │ ├── Ava Carter-Moore.agent.json
│ │ │ │ ├── Chloe Lee-Williams.agent.json
│ │ │ │ ├── Chloe Nguyen-Smith.agent.json
│ │ │ │ ├── Elena Carter-Jones.agent.json
│ │ │ │ ├── Elena Martinez-Garcia.agent.json
│ │ │ │ ├── Elena Martinez-Jones.agent.json
│ │ │ │ ├── Elena Rodriguez.agent.json
│ │ │ │ ├── Elijah Carter-Jones.agent.json
│ │ │ │ ├── Gabriel Lee-Roberts.agent.json
│ │ │ │ ├── Gabriel Lee-Smith.agent.json
│ │ │ │ ├── Gabriel Lee-Williams.agent.json
│ │ │ │ ├── Gabriel Martinez-Smith.agent.json
│ │ │ │ ├── Isabella Carter-Jones.agent.json
│ │ │ │ ├── Isabella Carter.agent.json
│ │ │ │ ├── Isabella Kimball-Wong.agent.json
│ │ │ │ ├── Isaiah Carter.agent.json
│ │ │ │ ├── Isaiah Johnson-Smith.agent.json
│ │ │ │ ├── Isaiah Patel-Garcia.agent.json
│ │ │ │ ├── Jasper Lee-Roberts.agent.json
│ │ │ │ ├── Jasper Nguyen-Williams.agent.json
│ │ │ │ ├── Jasper Nguyen.agent.json
│ │ │ │ ├── Liam Patel-Smith.agent.json
│ │ │ │ ├── Liam Torres-Brown.agent.json
│ │ │ │ ├── Liam Torres-Garcia.agent.json
│ │ │ │ ├── Liam Torres-Moore.agent.json
│ │ │ │ ├── Liam Torres-Smith.agent.json
│ │ │ │ ├── Nina Hayes-Roberts.agent.json
│ │ │ │ ├── Nina Johnson-Rivera.agent.json
│ │ │ │ ├── Nina Robinson-Smith.agent.json
│ │ │ │ ├── Nina Torres-Smith.agent.json
│ │ │ │ ├── Oliver Hayes-Kim.agent.json
│ │ │ │ ├── Oliver Hayes-Smith.agent.json
│ │ │ │ ├── Oliver Martinez-Jones.agent.json
│ │ │ │ ├── Samuel Lee-Patel.agent.json
│ │ │ │ ├── Sofia Adams-Williams.agent.json
│ │ │ │ ├── Sofia Johnson-Brown.agent.json
│ │ │ │ ├── Sofia Patel-Jones.agent.json
│ │ │ │ ├── Sofia Patel-Roberts.agent.json
│ │ │ │ ├── Sofia Patel-Williams.agent.json
│ │ │ │ ├── Victoria Adams-Garcia.agent.json
│ │ │ │ ├── Victoria Adams-Kim.agent.json
│ │ │ │ ├── Victoria Nguyen.agent.json
│ │ │ │ ├── Zara Johnson-Kim.agent.json
│ │ │ │ └── Zara Johnson-Smith.agent.json
│ │ │ ├── usa_families/
│ │ │ │ ├── Aiden Brown.agent.json
│ │ │ │ ├── Aiden Johnson.agent.json
│ │ │ │ ├── Aiden Smith.agent.json
│ │ │ │ ├── Benjamin Clark.agent.json
│ │ │ │ ├── Benjamin Lee.agent.json
│ │ │ │ ├── Benjamin Lewis.agent.json
│ │ │ │ ├── Benjamin Scott.agent.json
│ │ │ │ ├── Chloe Davis.agent.json
│ │ │ │ ├── Chloe Harris.agent.json
│ │ │ │ ├── Chloe Taylor.agent.json
│ │ │ │ ├── Chloe White.agent.json
│ │ │ │ ├── Chloe Wilson.agent.json
│ │ │ │ ├── Ella Thompson.agent.json
│ │ │ │ ├── Ella Wilson.agent.json
│ │ │ │ ├── Emily Davis.agent.json
│ │ │ │ ├── Emily Smith.agent.json
│ │ │ │ ├── Emily Taylor.agent.json
│ │ │ │ ├── Emily Wilson.agent.json
│ │ │ │ ├── Ethan Smith.agent.json
│ │ │ │ ├── Ethan Taylor.agent.json
│ │ │ │ ├── Ethan Wilson.agent.json
│ │ │ │ ├── Grace Martinez.agent.json
│ │ │ │ ├── Grace Taylor.agent.json
│ │ │ │ ├── Grace Wilson.agent.json
│ │ │ │ ├── Jackson Lee.agent.json
│ │ │ │ ├── Jackson White.agent.json
│ │ │ │ ├── James Anderson.agent.json
│ │ │ │ ├── James Taylor.agent.json
│ │ │ │ ├── Lucas Anderson.agent.json
│ │ │ │ ├── Lucas Brown.agent.json
│ │ │ │ ├── Lucas Davis.agent.json
│ │ │ │ ├── Lucas Martinez.agent.json
│ │ │ │ ├── Lucas Taylor.agent.json
│ │ │ │ ├── Lucas White.agent.json
│ │ │ │ ├── Mia Anderson.agent.json
│ │ │ │ ├── Mia Johnson.agent.json
│ │ │ │ ├── Mia Thompson.agent.json
│ │ │ │ ├── Oliver Davis.agent.json
│ │ │ │ ├── Oliver Johnson.agent.json
│ │ │ │ ├── Oliver Smith.agent.json
│ │ │ │ ├── Sofia Anderson.agent.json
│ │ │ │ ├── Sofia Brown.agent.json
│ │ │ │ ├── Sofia Clark.agent.json
│ │ │ │ ├── Sofia Davis.agent.json
│ │ │ │ └── Sofia White.agent.json
│ │ │ ├── usa_families_2/
│ │ │ │ ├── Avery Martinez.agent.json
│ │ │ │ ├── Chloe White.agent.json
│ │ │ │ ├── Dante Brooks.agent.json
│ │ │ │ ├── Dante Hayes.agent.json
│ │ │ │ ├── Dante Kim.agent.json
│ │ │ │ ├── Elena Garcia.agent.json
│ │ │ │ ├── Elena Martinez-Williams.agent.json
│ │ │ │ ├── Elena Martinez.agent.json
│ │ │ │ ├── Elijah Carter-Williams.agent.json
│ │ │ │ ├── Elijah Johnson.agent.json
│ │ │ │ ├── Ethan Brooks.agent.json
│ │ │ │ ├── Ethan Carter.agent.json
│ │ │ │ ├── Ethan Ramirez.agent.json
│ │ │ │ ├── Gabriel Lee-Moore.agent.json
│ │ │ │ ├── Gabriel Martinez.agent.json
│ │ │ │ ├── Gabriel Torres-Moore.agent.json
│ │ │ │ ├── Gabriel Torres.agent.json
│ │ │ │ ├── Isabella Martinez-Garcia.agent.json
│ │ │ │ ├── Isabella Martinez.agent.json
│ │ │ │ ├── Isaiah Ramirez.agent.json
│ │ │ │ ├── Jasper Martinez.agent.json
│ │ │ │ ├── Julian Hayes-Smith.agent.json
│ │ │ │ ├── Liam Carter-Smith.agent.json
│ │ │ │ ├── Liam Carter.agent.json
│ │ │ │ ├── Liam Harris.agent.json
│ │ │ │ ├── Liam Rivera-Sanchez.agent.json
│ │ │ │ ├── Liam Rivera.agent.json
│ │ │ │ ├── Lucas Thompson.agent.json
│ │ │ │ ├── Mason Brown.agent.json
│ │ │ │ ├── Mason Carter.agent.json
│ │ │ │ ├── Maya Johnson-Smith.agent.json
│ │ │ │ ├── Nina Foster.agent.json
│ │ │ │ ├── Nina Patel.agent.json
│ │ │ │ ├── Nina Robinson.agent.json
│ │ │ │ ├── Nina Torres-Garcia.agent.json
│ │ │ │ ├── Nina Torres.agent.json
│ │ │ │ ├── Rafael Adams.agent.json
│ │ │ │ ├── Rafael Torres.agent.json
│ │ │ │ ├── Samuel White-Blackwell.agent.json
│ │ │ │ ├── Sofia Adams.agent.json
│ │ │ │ ├── Sofia Bennett.agent.json
│ │ │ │ ├── Sofia Johnson.agent.json
│ │ │ │ ├── Sophia Brown.agent.json
│ │ │ │ ├── Talia Brooks.agent.json
│ │ │ │ ├── Talia Hayes.agent.json
│ │ │ │ ├── Talia Robinson.agent.json
│ │ │ │ ├── Victoria Adams-Brown.agent.json
│ │ │ │ ├── Victoria Torres.agent.json
│ │ │ │ ├── Zara Patel.agent.json
│ │ │ │ ├── Zara Thompson-Jones.agent.json
│ │ │ │ └── Zara Thompson.agent.json
│ │ │ ├── usa_general/
│ │ │ │ ├── Aiden Brooks.agent.json
│ │ │ │ ├── Ashley Wilson.agent.json
│ │ │ │ ├── Charlotte Cooper.agent.json
│ │ │ │ ├── Christopher Lee.agent.json
│ │ │ │ ├── David Anderson.agent.json
│ │ │ │ ├── Ethan Foster.agent.json
│ │ │ │ ├── Ethan Scott.agent.json
│ │ │ │ ├── Henry Murphy.agent.json
│ │ │ │ ├── Isabella Young.agent.json
│ │ │ │ ├── Jackson Ward.agent.json
│ │ │ │ ├── James Carter.agent.json
│ │ │ │ ├── Jessica Martinez.agent.json
│ │ │ │ ├── Lucas Carter.agent.json
│ │ │ │ ├── Lucas Hall.agent.json
│ │ │ │ ├── Matthew Robinson.agent.json
│ │ │ │ ├── Michael Thompson.agent.json
│ │ │ │ ├── Olivia Bennett.agent.json
│ │ │ │ ├── Olivia Harris.agent.json
│ │ │ │ ├── Sarah Brown.agent.json
│ │ │ │ └── Zoe Rivera.agent.json
│ │ │ ├── usa_picky/
│ │ │ │ ├── Amelia Lewis.agent.json
│ │ │ │ ├── Benjamin Young.agent.json
│ │ │ │ ├── Charlotte Clark.agent.json
│ │ │ │ ├── Chloe Anderson.agent.json
│ │ │ │ ├── Ella Martin.agent.json
│ │ │ │ ├── Emily Johnson.agent.json
│ │ │ │ ├── Ethan Wilson.agent.json
│ │ │ │ ├── Grace Allen.agent.json
│ │ │ │ ├── Grace White.agent.json
│ │ │ │ ├── Henry Walker.agent.json
│ │ │ │ ├── James Williams.agent.json
│ │ │ │ ├── Lucas Thompson.agent.json
│ │ │ │ ├── Lucas Young.agent.json
│ │ │ │ ├── Mason Taylor.agent.json
│ │ │ │ ├── Noah Rodriguez.agent.json
│ │ │ │ ├── Oliver Harris.agent.json
│ │ │ │ ├── Olivia Jones.agent.json
│ │ │ │ ├── Scarlett Hall.agent.json
│ │ │ │ ├── Victoria King.agent.json
│ │ │ │ └── Zoe King.agent.json
│ │ │ ├── usa_singles/
│ │ │ │ ├── Aiden Foster.agent.json
│ │ │ │ ├── Ashley Brown.agent.json
│ │ │ │ ├── Ava Cooper.agent.json
│ │ │ │ ├── Ava Patel.agent.json
│ │ │ │ ├── Ava Scott.agent.json
│ │ │ │ ├── Chloe Nguyen.agent.json
│ │ │ │ ├── Chloe Ramirez.agent.json
│ │ │ │ ├── Chloe Reed.agent.json
│ │ │ │ ├── Christopher Garcia.agent.json
│ │ │ │ ├── Daniel Anderson.agent.json
│ │ │ │ ├── David Lee.agent.json
│ │ │ │ ├── Ella Murphy.agent.json
│ │ │ │ ├── Emily Johnson.agent.json
│ │ │ │ ├── Ethan Brooks.agent.json
│ │ │ │ ├── Ethan Clark.agent.json
│ │ │ │ ├── Ethan Ramirez.agent.json
│ │ │ │ ├── Isabella Brooks.agent.json
│ │ │ │ ├── Isabella Foster.agent.json
│ │ │ │ ├── Isabella Green.agent.json
│ │ │ │ ├── Isabella Patel.agent.json
│ │ │ │ ├── Isabella Turner.agent.json
│ │ │ │ ├── Jackson Green.agent.json
│ │ │ │ ├── James Wilson.agent.json
│ │ │ │ ├── Jessica Martinez.agent.json
│ │ │ │ ├── Laura White.agent.json
│ │ │ │ ├── Liam Carter.agent.json
│ │ │ │ ├── Liam Foster.agent.json
│ │ │ │ ├── Liam Patel.agent.json
│ │ │ │ ├── Liam Young.agent.json
│ │ │ │ ├── Lucas Harris.agent.json
│ │ │ │ ├── Lucas Wright.agent.json
│ │ │ │ ├── Mason Lee.agent.json
│ │ │ │ ├── Mason Reed.agent.json
│ │ │ │ ├── Mason Rivera.agent.json
│ │ │ │ ├── Michael Thompson.agent.json
│ │ │ │ ├── Noah Brooks.agent.json
│ │ │ │ ├── Noah Carter.agent.json
│ │ │ │ ├── Noah King.agent.json
│ │ │ │ ├── Olivia Harris.agent.json
│ │ │ │ ├── Sarah Robinson.agent.json
│ │ │ │ ├── Sophia Lewis.agent.json
│ │ │ │ ├── Sophia Turner.agent.json
│ │ │ │ ├── Zoe Cooper.agent.json
│ │ │ │ ├── Zoe Thompson.agent.json
│ │ │ │ └── Zoe Turner.agent.json
│ │ │ └── usa_singles_2/
│ │ │ ├── Amelia Foster.agent.json
│ │ │ ├── Amelia Torres.agent.json
│ │ │ ├── Ava Martinez.agent.json
│ │ │ ├── Charlotte Evans.agent.json
│ │ │ ├── Charlotte Nguyen.agent.json
│ │ │ ├── Chloe Bennett.agent.json
│ │ │ ├── Chloe Martinez.agent.json
│ │ │ ├── Chloe Nguyen.agent.json
│ │ │ ├── Chloe Ramirez.agent.json
│ │ │ ├── Daniel Foster.agent.json
│ │ │ ├── David Lee.agent.json
│ │ │ ├── Emily Chen.agent.json
│ │ │ ├── Ethan Kim.agent.json
│ │ │ ├── Evelyn Brooks-Johnson.agent.json
│ │ │ ├── Evelyn Brooks.agent.json
│ │ │ ├── Evelyn Martinez.agent.json
│ │ │ ├── Gabriel Scott.agent.json
│ │ │ ├── Grace Mitchell.agent.json
│ │ │ ├── Grace Nguyen.agent.json
│ │ │ ├── Henry Adams.agent.json
│ │ │ ├── Henry Mitchell.agent.json
│ │ │ ├── Isaac Johnson.agent.json
│ │ │ ├── Isabella Garcia.agent.json
│ │ │ ├── Isabella Wright.agent.json
│ │ │ ├── Isaiah Patel.agent.json
│ │ │ ├── Jackson Wright.agent.json
│ │ │ ├── James Anderson.agent.json
│ │ │ ├── Jaxon Rivera.agent.json
│ │ │ ├── Julian Grant.agent.json
│ │ │ ├── Julian Hayes.agent.json
│ │ │ ├── Liam Johnson.agent.json
│ │ │ ├── Lily Carter.agent.json
│ │ │ ├── Lily Foster.agent.json
│ │ │ ├── Lily Nguyen.agent.json
│ │ │ ├── Lucas Ramirez.agent.json
│ │ │ ├── Luna Hayes.agent.json
│ │ │ ├── Madison Reed.agent.json
│ │ │ ├── Madison Torres.agent.json
│ │ │ ├── Mason Reed.agent.json
│ │ │ ├── Mia Robinson.agent.json
│ │ │ ├── Michael Thompson.agent.json
│ │ │ ├── Natalie Torres.agent.json
│ │ │ ├── Nathaniel Scott.agent.json
│ │ │ ├── Noah Lewis.agent.json
│ │ │ ├── Nora Kim.agent.json
│ │ │ ├── Oliver Brooks.agent.json
│ │ │ ├── Olivia Garcia.agent.json
│ │ │ ├── Olivia Turner.agent.json
│ │ │ ├── Olivia Walker.agent.json
│ │ │ ├── Samantha Lee.agent.json
│ │ │ ├── Samantha Reed.agent.json
│ │ │ ├── Scarlett Nguyen.agent.json
│ │ │ ├── Sofia Martinez.agent.json
│ │ │ ├── Sophia Carter.agent.json
│ │ │ └── Sophia Patel.agent.json
│ │ └── spicy_product_market_research.json
│ └── paper_artifacts_october-2025/
│ ├── Brainstorming and Focus Group Quantitative Experimentation 1 (Treatment run).ipynb
│ ├── Brainstorming and Focus Group Quantitative Experimentation 1.ipynb
│ ├── Brainstorming and Focus Group Quantitative Experimentation 2.1 (Treatment run).ipynb
│ ├── Brainstorming and Focus Group Quantitative Experimentation 2.1.ipynb
│ ├── Brainstorming and Focus Group Quantitative Experimentation 2.2 (Treatment run).ipynb
│ ├── Brainstorming and Focus Group Quantitative Experimentation 2.2.ipynb
│ ├── Brainstorming and Focus Group Quantitative Experimentation 2.3 (Treatment run).ipynb
│ ├── Brainstorming and Focus Group Quantitative Experimentation 2.3.ipynb
│ ├── Food Products Ideas Brainstorming.ipynb
│ ├── Paper Charts and Plots.ipynb
│ ├── Political Compass (customizing agents with fragments).ipynb
│ ├── Populations creation.ipynb
│ ├── Synthetic Data Generation.ipynb
│ ├── Travel Product Market Research (with behavior correction).ipynb
│ ├── Travel Product Market Research 2.ipynb
│ ├── Travel Product Market Research 2b (with behavior correction).ipynb
│ ├── Travel Product Market Research 2b.ipynb
│ ├── Travel Product Market Research 2c (with behavior correction).ipynb
│ ├── Travel Product Market Research.ipynb
│ ├── action_correction_example.txt
│ ├── brainstorming_and_focus_group_quantitative_experimentation_1.json
│ ├── brainstorming_and_focus_group_quantitative_experimentation_1b.json
│ ├── brainstorming_and_focus_group_quantitative_experimentation_2.1c.json
│ ├── brainstorming_and_focus_group_quantitative_experimentation_2.1d.json
│ ├── brainstorming_and_focus_group_quantitative_experimentation_2.1e.json
│ ├── brainstorming_and_focus_group_quantitative_experimentation_2.1f.json
│ ├── brainstorming_and_focus_group_quantitative_experimentation_2.2b.json
│ ├── brainstorming_and_focus_group_quantitative_experimentation_2.3.json
│ ├── common_utils.py
│ ├── config.ini
│ ├── debating_quantitative_experimentation_1c.json
│ ├── extractions/
│ │ └── synthetic_data_example_3/
│ │ └── Document/
│ │ ├── Asteria Conservatory — Emergency Response Report & 10‑Day Action Plan.Lisa Carter.docx
│ │ ├── Asteria Conservatory — Emergency Response Report & 10‑Day Action Plan.Lisa Carter.json
│ │ ├── Asteria Conservatory — Emergency Response Report & 10‑Day Action Plan.Lisa Carter.md
│ │ ├── BlueHarbor – Rapid Scoping Report- Microgrid Options, Immediate Asks & 6-week Plan.Lisa Carter.docx
│ │ ├── BlueHarbor – Rapid Scoping Report- Microgrid Options, Immediate Asks & 6-week Plan.Lisa Carter.json
│ │ ├── BlueHarbor – Rapid Scoping Report- Microgrid Options, Immediate Asks & 6-week Plan.Lisa Carter.md
│ │ ├── GreenRiver Rapid-Response Report — 48h Needs Assessment & Pilot Plan (Draft).Lisa Carter.docx
│ │ ├── GreenRiver Rapid-Response Report — 48h Needs Assessment & Pilot Plan (Draft).Lisa Carter.json
│ │ ├── GreenRiver Rapid-Response Report — 48h Needs Assessment & Pilot Plan (Draft).Lisa Carter.md
│ │ ├── Halcyon Air — Initial Recovery & Regulator-Lender Outreach Report (Draft).Lisa Carter.docx
│ │ ├── Halcyon Air — Initial Recovery & Regulator-Lender Outreach Report (Draft).Lisa Carter.json
│ │ ├── Halcyon Air — Initial Recovery & Regulator-Lender Outreach Report (Draft).Lisa Carter.md
│ │ ├── Highland Coffee Cooperative — Recovery & Traceability Plan (Draft).Lisa Carter.docx
│ │ ├── Highland Coffee Cooperative — Recovery & Traceability Plan (Draft).Lisa Carter.json
│ │ ├── Highland Coffee Cooperative — Recovery & Traceability Plan (Draft).Lisa Carter.md
│ │ ├── IronCliff Emergency Stabilisation & Community Protection Plan — Draft Short Report.Lisa Carter.docx
│ │ ├── IronCliff Emergency Stabilisation & Community Protection Plan — Draft Short Report.Lisa Carter.json
│ │ ├── IronCliff Emergency Stabilisation & Community Protection Plan — Draft Short Report.Lisa Carter.md
│ │ ├── MultiLever Rapid Diagnostic & Action Plan.Lisa Carter.docx
│ │ ├── MultiLever Rapid Diagnostic & Action Plan.Lisa Carter.json
│ │ ├── MultiLever Rapid Diagnostic & Action Plan.Lisa Carter.md
│ │ ├── MultiLever — Rapid Diagnostic & Action Plan (Inflation & Demand Shock).Lisa Carter.docx
│ │ ├── MultiLever — Rapid Diagnostic & Action Plan (Inflation & Demand Shock).Lisa Carter.json
│ │ ├── MultiLever — Rapid Diagnostic & Action Plan (Inflation & Demand Shock).Lisa Carter.md
│ │ ├── MultiLever — Rapid Diagnostic & Action Plan for Demand Shortfall.Lisa Carter, Wild Advice Partners.docx
│ │ ├── MultiLever — Rapid Diagnostic & Action Plan for Demand Shortfall.Lisa Carter, Wild Advice Partners.json
│ │ ├── MultiLever — Rapid Diagnostic & Action Plan for Demand Shortfall.Lisa Carter, Wild Advice Partners.md
│ │ ├── MultiLever- Rapid Diagnostic & Action Plan for Demand Recovery.Lisa Carter.docx
│ │ ├── MultiLever- Rapid Diagnostic & Action Plan for Demand Recovery.Lisa Carter.json
│ │ ├── MultiLever- Rapid Diagnostic & Action Plan for Demand Recovery.Lisa Carter.md
│ │ ├── ZephyrPay — AML Remediation & Model Audit- 3-week plan.Lisa Carter.docx
│ │ ├── ZephyrPay — AML Remediation & Model Audit- 3-week plan.Lisa Carter.json
│ │ └── ZephyrPay — AML Remediation & Model Audit- 3-week plan.Lisa Carter.md
│ ├── food_products_brainstorming_2.json
│ ├── fragments/
│ │ ├── aggressive_debater.fragment.json
│ │ ├── authoritarian.agent.fragment.json
│ │ ├── difficult_person.agent.fragment.json
│ │ ├── leftwing.agent.fragment.json
│ │ ├── libertarian.agent.fragment.json
│ │ ├── loving_parent.agent.fragment.json
│ │ ├── picky_customer.agent.fragment copy.json
│ │ ├── picky_customer.agent.fragment.json
│ │ └── rightwing.agent.fragment.json
│ ├── information/
│ │ └── populations/
│ │ ├── brazil.json
│ │ ├── china.json
│ │ ├── india.json
│ │ ├── mexico.json
│ │ ├── norway.json
│ │ ├── scandinavia.json
│ │ └── usa.json
│ ├── market_research_utils.py
│ ├── population/
│ │ ├── company_2/
│ │ │ ├── Alan Merrick.agent.json
│ │ │ ├── Anthony Russo.agent.json
│ │ │ ├── Anya Calder-Mori.agent.json
│ │ │ ├── Barbara Jean Pratt.agent.json
│ │ │ ├── Colin Arthur Matthews.agent.json
│ │ │ ├── Colin Murray.agent.json
│ │ │ ├── Connor Walsh.agent.json
│ │ │ ├── Darren McCall.agent.json
│ │ │ ├── Dean Bartlett.agent.json
│ │ │ ├── Declan Blackwell.agent.json
│ │ │ ├── Edgar Milton Crane.agent.json
│ │ │ ├── Leonard Victor Hale.agent.json
│ │ │ ├── Mildred Agnes Hargreaves.agent.json
│ │ │ ├── Ruby Mae Thornton.agent.json
│ │ │ ├── Rupert Langley-Smythe.agent.json
│ │ │ ├── Sloane Amaya Bexley.agent.json
│ │ │ ├── Stanley Burke.agent.json
│ │ │ ├── Tyler James Banks.agent.json
│ │ │ ├── Tyrell Hayes.agent.json
│ │ │ └── Vivian Hyejin Hwang.agent.json
│ │ ├── difficult_people_2/
│ │ │ ├── Alan Merrick.agent.json
│ │ │ ├── Anthony Russo.agent.json
│ │ │ ├── Anya Calder-Mori.agent.json
│ │ │ ├── Barbara Jean Pratt.agent.json
│ │ │ ├── Colin Arthur Matthews.agent.json
│ │ │ ├── Colin Murray.agent.json
│ │ │ ├── Connor Walsh.agent.json
│ │ │ ├── Darren McCall.agent.json
│ │ │ ├── Dean Bartlett.agent.json
│ │ │ ├── Declan Blackwell.agent.json
│ │ │ ├── Edgar Milton Crane.agent.json
│ │ │ ├── Leonard Victor Hale.agent.json
│ │ │ ├── Mildred Agnes Hargreaves.agent.json
│ │ │ ├── Ruby Mae Thornton.agent.json
│ │ │ ├── Rupert Langley-Smythe.agent.json
│ │ │ ├── Sloane Amaya Bexley.agent.json
│ │ │ ├── Stanley Burke.agent.json
│ │ │ ├── Tyler James Banks.agent.json
│ │ │ ├── Tyrell Hayes.agent.json
│ │ │ └── Vivian Hyejin Hwang.agent.json
│ │ ├── global_general_2/
│ │ │ ├── Adam Kamara.agent.json
│ │ │ ├── Ahmet Demir.agent.json
│ │ │ ├── Alex Cruz.agent.json
│ │ │ ├── Alexander Beaumont.agent.json
│ │ │ ├── Aman Mehra.agent.json
│ │ │ ├── Asha Okoye.agent.json
│ │ │ ├── Diego Chen López.agent.json
│ │ │ ├── Hikaru Sato.agent.json
│ │ │ ├── Hinewai Te Rangi.agent.json
│ │ │ ├── Isabela Rivera.agent.json
│ │ │ ├── Jordan Navarro.agent.json
│ │ │ ├── Khadija Diallo.agent.json
│ │ │ ├── Kiran Ndlovu.agent.json
│ │ │ ├── Mariama Diallo.agent.json
│ │ │ ├── Mariana Chen.agent.json
│ │ │ ├── Meera Sharma.agent.json
│ │ │ ├── Morgan Schmidt.agent.json
│ │ │ ├── Riley Ajani.agent.json
│ │ │ ├── Sunita Devi.agent.json
│ │ │ └── Taylor Novak.agent.json
│ │ ├── mexico_general_2/
│ │ │ ├── Alexis Romero Aguilar.agent.json
│ │ │ ├── Camila Fernanda Santillán Méndez.agent.json
│ │ │ ├── Carlos Alberto Navarro López.agent.json
│ │ │ ├── Claudia Murillo Aguilar.agent.json
│ │ │ ├── Dominga Chilón Gómez.agent.json
│ │ │ ├── Federico Treviño Sada.agent.json
│ │ │ ├── Fernando Alejandro Salas Ortega.agent.json
│ │ │ ├── Gael Emiliano Zamora.agent.json
│ │ │ ├── Jorge Luis Nájera Morales.agent.json
│ │ │ ├── José Guadalupe Martínez Cruz.agent.json
│ │ │ ├── María Concepción Téllez Zapata.agent.json
│ │ │ ├── María Elena Sandoval Cruz.agent.json
│ │ │ ├── María Guadalupe López Juárez.agent.json
│ │ │ ├── María Soledad López.agent.json
│ │ │ ├── María de la Luz Pacheco Ramos.agent.json
│ │ │ ├── María del Rosario Ríos Valencia.agent.json
│ │ │ ├── Raúl Alejandro Paredes López.agent.json
│ │ │ ├── Raúl Enrique Velázquez Cruz.agent.json
│ │ │ ├── Renata Lucero Montes.agent.json
│ │ │ └── Rosa Elena Méndez.agent.json
│ │ ├── norway_general_2/
│ │ │ ├── Anna Nowak.agent.json
│ │ │ ├── Bjørn Arvid Lunde.agent.json
│ │ │ ├── Einar Folke Brekke.agent.json
│ │ │ ├── Emilie Solheim.agent.json
│ │ │ ├── Helga Kristoffersen.agent.json
│ │ │ ├── Ingrid Elise Berg.agent.json
│ │ │ ├── Ingrid Olsen.agent.json
│ │ │ ├── Kari Karlsen.agent.json
│ │ │ ├── Kristian Solbakken.agent.json
│ │ │ ├── Line Marie Hansen.agent.json
│ │ │ ├── Marek Kowalski.agent.json
│ │ │ ├── Mika Nguyen-Berg.agent.json
│ │ │ ├── Noah Henrik Berg.agent.json
│ │ │ ├── Odin Holmvik.agent.json
│ │ │ ├── Oskar Haugland.agent.json
│ │ │ ├── Per Harald Kristiansen.agent.json
│ │ │ ├── Piotr Nowak.agent.json
│ │ │ ├── Ragnhild Hansen.agent.json
│ │ │ ├── Sigrid Margrethe Nilsen.agent.json
│ │ │ └── Sofie Haugen.agent.json
│ │ ├── political_compass_2/
│ │ │ ├── Adelaida Vargas.agent.json
│ │ │ ├── Aiko Rivera-Nakano.agent.json
│ │ │ ├── Alex Malinowski.agent.json
│ │ │ ├── Caleb Reynolds.agent.json
│ │ │ ├── Casey Buchanan.agent.json
│ │ │ ├── Etta June Harper.agent.json
│ │ │ ├── Grant Emerson Caldwell.agent.json
│ │ │ ├── Harold Eugene Thompson.agent.json
│ │ │ ├── Harrison Cole.agent.json
│ │ │ ├── Isabella Cruz-Nguyen.agent.json
│ │ │ ├── Isla Moreno-Grant.agent.json
│ │ │ ├── Malcolm Andre Whitaker.agent.json
│ │ │ ├── Malia Begay.agent.json
│ │ │ ├── Maya Park-Sullivan.agent.json
│ │ │ ├── Nina Morales.agent.json
│ │ │ ├── Quinn Langford.agent.json
│ │ │ ├── Samir Ali Haddad.agent.json
│ │ │ ├── Spencer Caldwell.agent.json
│ │ │ ├── Tamsin Reid.agent.json
│ │ │ └── Taylor Cruz.agent.json
│ │ ├── usa_couples_2/
│ │ │ ├── Alex Larson.agent.json
│ │ │ ├── Andrew Maxwell Porter.agent.json
│ │ │ ├── Ava Carter-Moore.agent.json
│ │ │ ├── Beatrice Lorraine Grant.agent.json
│ │ │ ├── Bernice Henderson.agent.json
│ │ │ ├── Blair Wentworth.agent.json
│ │ │ ├── Caroline Margaret Bennett.agent.json
│ │ │ ├── Catherine Langford.agent.json
│ │ │ ├── Chloe Lee-Williams.agent.json
│ │ │ ├── Chloe Nguyen-Smith.agent.json
│ │ │ ├── Daniel Park.agent.json
│ │ │ ├── Daniel Wei Liu.agent.json
│ │ │ ├── Derek Malone.agent.json
│ │ │ ├── Eleanor June Bennett.agent.json
│ │ │ ├── Eleanor Whitman.agent.json
│ │ │ ├── Elena Carter-Jones.agent.json
│ │ │ ├── Elena Marquez.agent.json
│ │ │ ├── Elena Martinez-Garcia.agent.json
│ │ │ ├── Elena Martinez-Jones.agent.json
│ │ │ ├── Elena Rodriguez.agent.json
│ │ │ ├── Elijah Carter-Jones.agent.json
│ │ │ ├── Eric Thompson.agent.json
│ │ │ ├── Gabriel Lee-Roberts.agent.json
│ │ │ ├── Gabriel Lee-Smith.agent.json
│ │ │ ├── Gabriel Lee-Williams.agent.json
│ │ │ ├── Gabriel Martinez-Smith.agent.json
│ │ │ ├── Gregory Miles Anderson.agent.json
│ │ │ ├── Harper Lin.agent.json
│ │ │ ├── Isabel Valenzuela.agent.json
│ │ │ ├── Isabella Carter-Jones.agent.json
│ │ │ ├── Isabella Carter.agent.json
│ │ │ ├── Isabella Kimball-Wong.agent.json
│ │ │ ├── Isaiah Carter.agent.json
│ │ │ ├── Isaiah Johnson-Smith.agent.json
│ │ │ ├── Isaiah Patel-Garcia.agent.json
│ │ │ ├── Janet Holden.agent.json
│ │ │ ├── Janice Foley.agent.json
│ │ │ ├── Jason Chen.agent.json
│ │ │ ├── Jasper Lee-Roberts.agent.json
│ │ │ ├── Jasper Nguyen-Williams.agent.json
│ │ │ ├── Jasper Nguyen.agent.json
│ │ │ ├── José Emilio Muñoz.agent.json
│ │ │ ├── Leroy Anthony Booker.agent.json
│ │ │ ├── Levi Nelson.agent.json
│ │ │ ├── Liam Patel-Smith.agent.json
│ │ │ ├── Liam Torres-Brown.agent.json
│ │ │ ├── Liam Torres-Garcia.agent.json
│ │ │ ├── Liam Torres-Moore.agent.json
│ │ │ ├── Liam Torres-Smith.agent.json
│ │ │ ├── Lucas Park.agent.json
│ │ │ ├── Lucia Morales.agent.json
│ │ │ ├── Luis Alejandro Perez.agent.json
│ │ │ ├── Manuel Gonzalez.agent.json
│ │ │ ├── Mariana Alvarez.agent.json
│ │ │ ├── Marjorie Claire Ellis.agent.json
│ │ │ ├── Mark Weber.agent.json
│ │ │ ├── Mateo Javier Ramos.agent.json
│ │ │ ├── Mateo Santiago Ortega.agent.json
│ │ │ ├── Monica Patrice Grant.agent.json
│ │ │ ├── Nina Hayes-Roberts.agent.json
│ │ │ ├── Nina Johnson-Rivera.agent.json
│ │ │ ├── Nina Robinson-Smith.agent.json
│ │ │ ├── Nina Torres-Smith.agent.json
│ │ │ ├── Oliver Hayes-Kim.agent.json
│ │ │ ├── Oliver Hayes-Smith.agent.json
│ │ │ ├── Oliver Martinez-Jones.agent.json
│ │ │ ├── Owen Larson.agent.json
│ │ │ ├── Paloma Sofia Ruiz.agent.json
│ │ │ ├── Reese Choi-Walker.agent.json
│ │ │ ├── Rohan Patel.agent.json
│ │ │ ├── Samuel Lee-Patel.agent.json
│ │ │ ├── Sofia Adams-Williams.agent.json
│ │ │ ├── Sofia Johnson-Brown.agent.json
│ │ │ ├── Sofia Patel-Jones.agent.json
│ │ │ ├── Sofia Patel-Roberts.agent.json
│ │ │ ├── Sofia Patel-Williams.agent.json
│ │ │ ├── Victoria Adams-Garcia.agent.json
│ │ │ ├── Victoria Adams-Kim.agent.json
│ │ │ ├── Victoria Nguyen.agent.json
│ │ │ ├── Walter Eugene Brooks.agent.json
│ │ │ ├── William Otis Jones.agent.json
│ │ │ ├── Yvonne Harris.agent.json
│ │ │ ├── Zara Johnson-Kim.agent.json
│ │ │ └── Zara Johnson-Smith.agent.json
│ │ ├── usa_families_2/
│ │ │ ├── Agnes Lorraine Hughes.agent.json
│ │ │ ├── Amara Hollingsworth.agent.json
│ │ │ ├── Amari Sullivan.agent.json
│ │ │ ├── Arden Brooks.agent.json
│ │ │ ├── Ari Delgado.agent.json
│ │ │ ├── Avery Martinez.agent.json
│ │ │ ├── Carlos Rivera.agent.json
│ │ │ ├── Cecilia Hartmann.agent.json
│ │ │ ├── Celeste Rutherford.agent.json
│ │ │ ├── Chloe White.agent.json
│ │ │ ├── Clara Westwood.agent.json
│ │ │ ├── Dante Brooks.agent.json
│ │ │ ├── Dante Hayes.agent.json
│ │ │ ├── Dante Kim.agent.json
│ │ │ ├── Darla Jean McKenzie.agent.json
│ │ │ ├── Darlene Whitcomb.agent.json
│ │ │ ├── Diane Ruth Whitaker.agent.json
│ │ │ ├── Earlene Mae Donovan.agent.json
│ │ │ ├── Eden Morales.agent.json
│ │ │ ├── Eleanor Hayes.agent.json
│ │ │ ├── Elena Garcia.agent.json
│ │ │ ├── Elena Martinez-Williams.agent.json
│ │ │ ├── Elena Martinez.agent.json
│ │ │ ├── Eleni Parker.agent.json
│ │ │ ├── Elijah Carter-Williams.agent.json
│ │ │ ├── Elijah Johnson.agent.json
│ │ │ ├── Ellis Davenport.agent.json
│ │ │ ├── Emerson Tran.agent.json
│ │ │ ├── Erica Santos.agent.json
│ │ │ ├── Ethan Brooks.agent.json
│ │ │ ├── Ethan Carter.agent.json
│ │ │ ├── Ethan Ramirez.agent.json
│ │ │ ├── Evelyn Moreno.agent.json
│ │ │ ├── Gabriel Lee-Moore.agent.json
│ │ │ ├── Gabriel Martinez.agent.json
│ │ │ ├── Gabriel Torres-Moore.agent.json
│ │ │ ├── Gabriel Torres.agent.json
│ │ │ ├── Isabella Martinez-Garcia.agent.json
│ │ │ ├── Isabella Martinez.agent.json
│ │ │ ├── Isaiah Ramirez.agent.json
│ │ │ ├── Jada Moreno.agent.json
│ │ │ ├── Jasper Martinez.agent.json
│ │ │ ├── Jordan Blake.agent.json
│ │ │ ├── Julian Hayes-Smith.agent.json
│ │ │ ├── Leah Baxter.agent.json
│ │ │ ├── Liam Carter-Smith.agent.json
│ │ │ ├── Liam Carter.agent.json
│ │ │ ├── Liam Harris.agent.json
│ │ │ ├── Liam Rivera-Sanchez.agent.json
│ │ │ ├── Liam Rivera.agent.json
│ │ │ ├── Linda Mae Thompson.agent.json
│ │ │ ├── Lucas Thompson.agent.json
│ │ │ ├── Lydia Mercer.agent.json
│ │ │ ├── Mabel Jean Hawkins.agent.json
│ │ │ ├── Mason Brown.agent.json
│ │ │ ├── Mason Carter.agent.json
│ │ │ ├── Maya Johnson-Smith.agent.json
│ │ │ ├── Mildred Louise Hargrove.agent.json
│ │ │ ├── Morgan Hayes.agent.json
│ │ │ ├── Nina Foster.agent.json
│ │ │ ├── Nina Patel.agent.json
│ │ │ ├── Nina Robinson.agent.json
│ │ │ ├── Nina Torres-Garcia.agent.json
│ │ │ ├── Nina Torres.agent.json
│ │ │ ├── Norma Jean Carmichael.agent.json
│ │ │ ├── Norman Lee Carter.agent.json
│ │ │ ├── Olivia Kensington.agent.json
│ │ │ ├── Rafael Adams.agent.json
│ │ │ ├── Rafael Torres.agent.json
│ │ │ ├── Remy Alvarez.agent.json
│ │ │ ├── Riya Desai.agent.json
│ │ │ ├── Rowan Ellis.agent.json
│ │ │ ├── Rowan Sinclair.agent.json
│ │ │ ├── Sammy Jo Carter.agent.json
│ │ │ ├── Samuel White-Blackwell.agent.json
│ │ │ ├── Sharon Ellis.agent.json
│ │ │ ├── Skyler Nguyen-Pham.agent.json
│ │ │ ├── Sofia Adams.agent.json
│ │ │ ├── Sofia Bennett.agent.json
│ │ │ ├── Sofia Johnson.agent.json
│ │ │ ├── Sophia Brown.agent.json
│ │ │ ├── Talia Brooks.agent.json
│ │ │ ├── Talia Hayes.agent.json
│ │ │ ├── Talia Robinson.agent.json
│ │ │ ├── Tanvi Kapoor.agent.json
│ │ │ ├── Victoria Adams-Brown.agent.json
│ │ │ ├── Victoria Torres.agent.json
│ │ │ ├── Zara Linh Nguyen.agent.json
│ │ │ ├── Zara Patel.agent.json
│ │ │ ├── Zara Thompson-Jones.agent.json
│ │ │ └── Zara Thompson.agent.json
│ │ ├── usa_families_2b/
│ │ │ ├── Aaliyah Rosario Rodríguez.agent.json
│ │ │ ├── Adriana Beatriz Flores-Medina.agent.json
│ │ │ ├── Aiden Miguel Santos.agent.json
│ │ │ ├── Amara Lin Dawson.agent.json
│ │ │ ├── Ana Lucía Mendoza.agent.json
│ │ │ ├── Arjun Vikram Desai.agent.json
│ │ │ ├── Avery Linh Svensson.agent.json
│ │ │ ├── Camila Rosario Johnson.agent.json
│ │ │ ├── Carmen Lucía Navarro.agent.json
│ │ │ ├── Christopher Hiro Tanaka-Wells.agent.json
│ │ │ ├── Claire Alexandra Sinclair.agent.json
│ │ │ ├── Clara Maeve Lockwood.agent.json
│ │ │ ├── Daniel Everett Brooks.agent.json
│ │ │ ├── Dorothy Ann Carlson.agent.json
│ │ │ ├── Earl Benjamin Crockett.agent.json
│ │ │ ├── Eleanor Ruth Winslow.agent.json
│ │ │ ├── Emily Grace Walker.agent.json
│ │ │ ├── Erin Sora Park-Harrington.agent.json
│ │ │ ├── Gabriela Marisol Ortega.agent.json
│ │ │ ├── Greta Marianne Olsen.agent.json
│ │ │ ├── Harper Noelle Santiago.agent.json
│ │ │ ├── James Earl Hensley.agent.json
│ │ │ ├── Joan Elizabeth Gallagher.agent.json
│ │ │ ├── Jonathan Pierce Aldridge.agent.json
│ │ │ ├── Juan Pablo Castillo.agent.json
│ │ │ ├── Karina Maribel Gómez Ruiz.agent.json
│ │ │ ├── Latoya Simone Parker.agent.json
│ │ │ ├── Laura Jean Thompson.agent.json
│ │ │ ├── Lucas Orion Hayes.agent.json
│ │ │ ├── Mariana Elena Torres.agent.json
│ │ │ ├── Marilyn Josephine Peterson.agent.json
│ │ │ ├── Marisa Redbird.agent.json
│ │ │ ├── Maritza Elena Rios.agent.json
│ │ │ ├── Mark Allen Hargrove.agent.json
│ │ │ ├── Matthew Kenji Fairchild.agent.json
│ │ │ ├── Maya Celeste Bennett.agent.json
│ │ │ ├── Meredith Claire Hargreaves.agent.json
│ │ │ ├── Monique Patrice Johnson.agent.json
│ │ │ ├── Nora Keiko Sullivan.agent.json
│ │ │ ├── Nova Mei Holmgren.agent.json
│ │ │ ├── Radhika Meera Kapoor.agent.json
│ │ │ ├── Robert Lee McClain.agent.json
│ │ │ ├── Rowan Micah Ellwood.agent.json
│ │ │ ├── Sharon Louise Keller.agent.json
│ │ │ ├── Sofia Elena Morales.agent.json
│ │ │ ├── Tanya Michelle Brown.agent.json
│ │ │ ├── Timothy Dale Kirkland.agent.json
│ │ │ ├── Travis Allen Finley.agent.json
│ │ │ ├── William Ray Tucker.agent.json
│ │ │ └── Yadira Noemi Cruz-López.agent.json
│ │ ├── usa_families_2c/
│ │ │ ├── Amaya Linh Rosario-Keller.agent.json
│ │ │ ├── Arjun Vikram Patel.agent.json
│ │ │ ├── Arturo Luis Peña.agent.json
│ │ │ ├── Asha Meera Iyer.agent.json
│ │ │ ├── Benjamin Carter Langley.agent.json
│ │ │ ├── Caleb Mitchell Davenport.agent.json
│ │ │ ├── Carlos Alejandro Valdez.agent.json
│ │ │ ├── Caroline Bethany Wallace.agent.json
│ │ │ ├── Casey Rivera-Lin.agent.json
│ │ │ ├── Claire Meredith Langford.agent.json
│ │ │ ├── Diego Alejandro Navarro.agent.json
│ │ │ ├── Eleanor Grace Sullivan.agent.json
│ │ │ ├── Elliot Sinclair.agent.json
│ │ │ ├── Emiliano Javier Ramos.agent.json
│ │ │ ├── Ethan Marshall Reed.agent.json
│ │ │ ├── Evan Mateo Alvarez.agent.json
│ │ │ ├── Evelyn Jean Parker.agent.json
│ │ │ ├── Garrett Wayne Collins.agent.json
│ │ │ ├── Jeffrey Mark Lawson.agent.json
│ │ │ ├── Jordan Parker Whitman.agent.json
│ │ │ ├── Katherine Mae Whitaker.agent.json
│ │ │ ├── Leo Alexander Bennett.agent.json
│ │ │ ├── Lucas Manuel Hernández.agent.json
│ │ │ ├── Lucia Isabel Garcia.agent.json
│ │ │ ├── Marcus Elijah Brooks.agent.json
│ │ │ ├── Maria Elena Sanchez.agent.json
│ │ │ ├── Mark Alan Peterson.agent.json
│ │ │ ├── Marquis Anthony Jackson.agent.json
│ │ │ ├── Mateo Daniel González.agent.json
│ │ │ ├── Maya Anjali Carter.agent.json
│ │ │ ├── Miguel Ángel Torres-García.agent.json
│ │ │ ├── Morgan Ellis Caldwell.agent.json
│ │ │ ├── Natalie Claire Kensington.agent.json
│ │ │ ├── Nathaniel Grant Hawthorne.agent.json
│ │ │ ├── Neela Patel-Wright.agent.json
│ │ │ ├── Noah Elias Cruz.agent.json
│ │ │ ├── Oliver James Carson.agent.json
│ │ │ ├── Quinn Emerson.agent.json
│ │ │ ├── Rafael Julian Crowe.agent.json
│ │ │ ├── Riley Mateo Santiago.agent.json
│ │ │ ├── Roger Allen Kessler.agent.json
│ │ │ ├── Rohan Kiran Li-Desai.agent.json
│ │ │ ├── Ruben Arturo Morales.agent.json
│ │ │ ├── Ruby Mae Johnson.agent.json
│ │ │ ├── Samantha Aiyana TallBear.agent.json
│ │ │ ├── Sebastian Kai Mendoza.agent.json
│ │ │ ├── Tameka Renée Bryant.agent.json
│ │ │ ├── Taylor Emerson Clarke.agent.json
│ │ │ ├── Yadira Marisol Valenzuela.agent.json
│ │ │ └── Yesenia Maribel Flores.agent.json
│ │ ├── usa_general_2/
│ │ │ ├── Ariana Martinez-Brown.agent.json
│ │ │ ├── Ava Sinclair.agent.json
│ │ │ ├── Benjamin Hartley.agent.json
│ │ │ ├── Carmen Alvarez-Johnson.agent.json
│ │ │ ├── Carolyn Whitman.agent.json
│ │ │ ├── Charlotte Mercer.agent.json
│ │ │ ├── Elliot James Prescott.agent.json
│ │ │ ├── Eloise Gardner.agent.json
│ │ │ ├── Ethan Nakamura.agent.json
│ │ │ ├── Evelyn Bradford.agent.json
│ │ │ ├── Gloria Rosario.agent.json
│ │ │ ├── Harper Sullivan.agent.json
│ │ │ ├── Janet Marie Carlson.agent.json
│ │ │ ├── Juanita Delgado.agent.json
│ │ │ ├── Julian Harrington.agent.json
│ │ │ ├── Keisha Alvarez.agent.json
│ │ │ ├── Liana Torres-Kim.agent.json
│ │ │ ├── Margaret Elaine Miller.agent.json
│ │ │ ├── Patricia Ann Baker.agent.json
│ │ │ └── Valentina Marisol Torres.agent.json
│ │ ├── usa_picky_2/
│ │ │ ├── Anika Mei Chen-Rao.agent.json
│ │ │ ├── Betty Lou Hensley.agent.json
│ │ │ ├── Declan Rossetti.agent.json
│ │ │ ├── Dorothy Mae Whitaker.agent.json
│ │ │ ├── Dustin Lee Hargrove.agent.json
│ │ │ ├── Gabriela Ortega.agent.json
│ │ │ ├── Grace O'Malley-Fischer.agent.json
│ │ │ ├── Isha Chen-Patel.agent.json
│ │ │ ├── Latasha Renee McClain.agent.json
│ │ │ ├── Laura Brennan.agent.json
│ │ │ ├── Logan McCarthy.agent.json
│ │ │ ├── Luna Hernández.agent.json
│ │ │ ├── Monique Latrice Carter.agent.json
│ │ │ ├── Noah Delgado.agent.json
│ │ │ ├── Rachel Donnelly.agent.json
│ │ │ ├── Sarah Gallagher.agent.json
│ │ │ ├── Shane Lee McCoy.agent.json
│ │ │ ├── Siobhan Lombardi.agent.json
│ │ │ ├── Susan Davenport.agent.json
│ │ │ └── Ximena Alvarez-Ruiz.agent.json
│ │ └── usa_singles_2/
│ │ ├── Amelia Foster.agent.json
│ │ ├── Amelia Torres.agent.json
│ │ ├── Ananya Mehta.agent.json
│ │ ├── Arthur Lee McBride.agent.json
│ │ ├── Ava Martinez.agent.json
│ │ ├── Cameron Ellis.agent.json
│ │ ├── Casey Rivera.agent.json
│ │ ├── Charles Vernon Whitaker.agent.json
│ │ ├── Charlotte Evans.agent.json
│ │ ├── Charlotte Nguyen.agent.json
│ │ ├── Chloe Bennett.agent.json
│ │ ├── Chloe Martinez.agent.json
│ │ ├── Chloe Nguyen.agent.json
│ │ ├── Chloe Ramirez.agent.json
│ │ ├── Clarence Walker.agent.json
│ │ ├── Daniel Callahan.agent.json
│ │ ├── Daniel Foster.agent.json
│ │ ├── David Alan Porter.agent.json
│ │ ├── David Lee.agent.json
│ │ ├── Diego Manuel Herrera.agent.json
│ │ ├── Emily Chen.agent.json
│ │ ├── Erin Palmer.agent.json
│ │ ├── Ethan Kim.agent.json
│ │ ├── Evan Chen-Parker.agent.json
│ │ ├── Evelyn Brooks-Johnson.agent.json
│ │ ├── Evelyn Brooks.agent.json
│ │ ├── Evelyn Crawford.agent.json
│ │ ├── Evelyn Martinez.agent.json
│ │ ├── Gabriel Scott.agent.json
│ │ ├── Gary Rhodes.agent.json
│ │ ├── Grace Mitchell.agent.json
│ │ ├── Grace Nguyen.agent.json
│ │ ├── Harold Dean Fletcher.agent.json
│ │ ├── Henry Adams.agent.json
│ │ ├── Henry Mitchell.agent.json
│ │ ├── Isaac Johnson.agent.json
│ │ ├── Isabella Garcia.agent.json
│ │ ├── Isabella Wright.agent.json
│ │ ├── Isaiah Patel.agent.json
│ │ ├── Jackson Wright.agent.json
│ │ ├── James Anderson.agent.json
│ │ ├── Jamie Lee Carter.agent.json
│ │ ├── Jaxon Rivera.agent.json
│ │ ├── Jordan Alvarez-Kim.agent.json
│ │ ├── Jordan Kim-Rodriguez.agent.json
│ │ ├── Jordan Park.agent.json
│ │ ├── José Antonio Vega.agent.json
│ │ ├── Julian Grant.agent.json
│ │ ├── Julian Hayes.agent.json
│ │ ├── Kai Mendoza.agent.json
│ │ ├── Kaya Yazzie-Kelekolio.agent.json
│ │ ├── Leilani Begay.agent.json
│ │ ├── Liam Johnson.agent.json
│ │ ├── Lillian Porter.agent.json
│ │ ├── Lily Carter.agent.json
│ │ ├── Lily Foster.agent.json
│ │ ├── Lily Nguyen.agent.json
│ │ ├── Loretta Jean Sanders.agent.json
│ │ ├── Lucas Ramirez.agent.json
│ │ ├── Luna Hayes.agent.json
│ │ ├── Madison Reed.agent.json
│ │ ├── Madison Torres.agent.json
│ │ ├── Makana Begay.agent.json
│ │ ├── Maria Elena Dominguez.agent.json
│ │ ├── Marissa Tanaka.agent.json
│ │ ├── Maritza Soto.agent.json
│ │ ├── Mason Reed.agent.json
│ │ ├── Mia Robinson.agent.json
│ │ ├── Michael Thompson.agent.json
│ │ ├── Miriam Langford.agent.json
│ │ ├── Natalie Torres.agent.json
│ │ ├── Nathaniel Scott.agent.json
│ │ ├── Noah Lewis.agent.json
│ │ ├── Noelani Benally.agent.json
│ │ ├── Nora Kim.agent.json
│ │ ├── Oliver Brooks.agent.json
│ │ ├── Olivia Garcia.agent.json
│ │ ├── Olivia Turner.agent.json
│ │ ├── Olivia Walker.agent.json
│ │ ├── Quinn Garcia.agent.json
│ │ ├── Raymond Lee Carter.agent.json
│ │ ├── Rowan Park-Bennett.agent.json
│ │ ├── Samantha Lee.agent.json
│ │ ├── Samantha Reed.agent.json
│ │ ├── Sarah Mitchell.agent.json
│ │ ├── Sasha Morales.agent.json
│ │ ├── Scarlett Nguyen.agent.json
│ │ ├── Shanice Marie Washington.agent.json
│ │ ├── Sofia Martinez.agent.json
│ │ ├── Sophia Carter.agent.json
│ │ ├── Sophia Patel.agent.json
│ │ ├── Tamika Grace Brown.agent.json
│ │ ├── Taylor Nguyen-Santos.agent.json
│ │ ├── Taylor Rivera.agent.json
│ │ └── Thomas Earl Davis.agent.json
│ └── run_experiments.py
├── pyproject.toml
├── reinstall_package_from_repo.bat
├── test-report.html
├── test-results.xml
├── test.bat
├── test_comparison.txt
├── test_core_with_cache.bat
├── test_exports/
│ └── Document/
│ ├── Architectural Proposal & Preliminary Cost Analysis — [Project Name - TBC].Oscar.docx
│ ├── Architectural Proposal & Preliminary Cost Analysis — [Project Name - TBC].Oscar.json
│ ├── Architectural Proposal & Preliminary Cost Analysis — [Project Name - TBC].Oscar.md
│ ├── Architectural Proposal for Standard Apartment Building Configuration.Oscar.docx
│ ├── Architectural Proposal for Standard Apartment Building Configuration.Oscar.json
│ ├── Architectural Proposal for Standard Apartment Building Configuration.Oscar.md
│ ├── Architectural Proposal for Standard Apartment Building Elements.Oscar.docx
│ ├── Architectural Proposal for Standard Apartment Building Elements.Oscar.json
│ ├── Architectural Proposal for Standard Apartment Building Elements.Oscar.md
│ ├── Architectural Proposal for Standard Apartment Configurations at Awesome Inc..Oscar.docx
│ ├── Architectural Proposal for Standard Apartment Configurations at Awesome Inc..Oscar.json
│ ├── Architectural Proposal for Standard Apartment Configurations at Awesome Inc..Oscar.md
│ ├── Architectural Proposal for Sustainable Modular Apartment Building.Oscar.docx
│ ├── Architectural Proposal for Sustainable Modular Apartment Building.Oscar.json
│ ├── Architectural Proposal for Sustainable Modular Apartment Building.Oscar.md
│ ├── Architectural Proposal for Sustainable Modular Housing.Oscar.docx
│ ├── Architectural Proposal for Sustainable Modular Housing.Oscar.json
│ ├── Architectural Proposal for Sustainable Modular Housing.Oscar.md
│ ├── Architectural Proposal — Standardized Apartment Building & Cost Analysis.Oscar.docx
│ ├── Architectural Proposal — Standardized Apartment Building & Cost Analysis.Oscar.json
│ ├── Architectural Proposal — Standardized Apartment Building & Cost Analysis.Oscar.md
│ ├── Architectural Proposal- Modular Apartment Building — Standard Apartment Configurations & Cost Analysis.Oscar (Architect, Awesome Inc.).docx
│ ├── Architectural Proposal- Modular Apartment Building — Standard Apartment Configurations & Cost Analysis.Oscar (Architect, Awesome Inc.).json
│ ├── Architectural Proposal- Modular Apartment Building — Standard Apartment Configurations & Cost Analysis.Oscar (Architect, Awesome Inc.).md
│ ├── Detailed Building Cost Analysis for Standard Apartment Elements.Oscar.docx
│ ├── Detailed Building Cost Analysis for Standard Apartment Elements.Oscar.json
│ ├── Detailed Building Cost Analysis for Standard Apartment Elements.Oscar.md
│ ├── Standardized Apartment Configuration Proposal — Awesome Inc..Oscar.docx
│ ├── Standardized Apartment Configuration Proposal — Awesome Inc..Oscar.json
│ └── Standardized Apartment Configuration Proposal — Awesome Inc..Oscar.md
├── test_gpt41mini_with_cache.bat
├── test_output.txt
├── test_with_cache_without_slow.bat
├── test_without_slow.bat
├── tests/
│ ├── README.md
│ ├── conftest.py
│ ├── non_functional/
│ │ └── test_security.py
│ ├── scenarios/
│ │ ├── test_advertisement_scenarios.py
│ │ ├── test_basic_scenarios.py
│ │ ├── test_brainstorming_scenarios.py
│ │ ├── test_extended_scenarios.py
│ │ ├── test_gpt41mini_scenarios.py
│ │ └── test_jupyter_examples.py
│ ├── testing_utils.py
│ └── unit/
│ ├── test-report.html
│ ├── test-results.xml
│ ├── test_action_generator.py
│ ├── test_api_cache.py
│ ├── test_api_cache_integration.py
│ ├── test_config.py
│ ├── test_control.py
│ ├── test_cost_tracking.py
│ ├── test_enrichment.py
│ ├── test_experimentation.py
│ ├── test_exports/
│ │ ├── Document/
│ │ │ ├── Architectural Proposal — Modular Sustainable Standard Apartments.Oscar, Architect — Awesome Inc..docx
│ │ │ ├── Architectural Proposal — Modular Sustainable Standard Apartments.Oscar, Architect — Awesome Inc..json
│ │ │ ├── Architectural Proposal — Modular Sustainable Standard Apartments.Oscar, Architect — Awesome Inc..md
│ │ │ └── test_artifact.docx
│ │ ├── record/
│ │ │ └── test_artifact.json
│ │ └── text/
│ │ └── test_artifact.txt
│ ├── test_extraction.py
│ ├── test_factory.py
│ ├── test_grounding.py
│ ├── test_in_place_experiment_runner.py
│ ├── test_intervention.py
│ ├── test_llm_chat.py
│ ├── test_memory.py
│ ├── test_normalizer.py
│ ├── test_profiling.py
│ ├── test_results_extractor.py
│ ├── test_results_reducer.py
│ ├── test_results_reporter.py
│ ├── test_simulation_validator.py
│ ├── test_statistical_tests.py
│ ├── test_story.py
│ ├── test_tiny_calendar.py
│ ├── test_tiny_social_network.py
│ ├── test_tiny_styler.py
│ ├── test_tiny_tool.py
│ ├── test_tinyperson.py
│ ├── test_tinyperson_extended.py
│ ├── test_tinyworld.py
│ ├── test_utils.py
│ └── test_validation.py
├── tinytroupe/
│ ├── __init__.py
│ ├── agent/
│ │ ├── __init__.py
│ │ ├── action_generator.py
│ │ ├── grounding.py
│ │ ├── memory.py
│ │ ├── mental_faculty.py
│ │ ├── prompts/
│ │ │ ├── tiny_person.mustache
│ │ │ └── tiny_person.v2.mustache
│ │ └── tiny_person.py
│ ├── clients/
│ │ ├── __init__.py
│ │ ├── azure_client.py
│ │ ├── ollama_client.py
│ │ └── openai_client.py
│ ├── config.ini
│ ├── control.py
│ ├── enrichment/
│ │ ├── __init__.py
│ │ ├── prompts/
│ │ │ ├── enricher.system.mustache
│ │ │ ├── enricher.user.mustache
│ │ │ ├── styler.system.mustache
│ │ │ └── styler.user.mustache
│ │ ├── tiny_enricher.py
│ │ └── tiny_styler.py
│ ├── environment/
│ │ ├── __init__.py
│ │ ├── tiny_social_network.py
│ │ └── tiny_world.py
│ ├── examples/
│ │ ├── __init__.py
│ │ ├── agents/
│ │ │ ├── Friedrich_Wolf.agent.json
│ │ │ ├── Lila.agent.json
│ │ │ ├── Lisa.agent.json
│ │ │ ├── Marcos.agent.json
│ │ │ ├── Oscar.agent.json
│ │ │ └── Sophie_Lefevre.agent.json
│ │ ├── agents.py
│ │ ├── fragments/
│ │ │ ├── authoritarian.agent.fragment.json
│ │ │ ├── leftwing.agent.fragment.json
│ │ │ ├── libertarian.agent.fragment.json
│ │ │ └── rightwing.agent.fragment.json
│ │ └── loaders.py
│ ├── experimentation/
│ │ ├── __init__.py
│ │ ├── in_place_experiment_runner.py
│ │ ├── proposition.py
│ │ ├── randomization.py
│ │ └── statistical_tests.py
│ ├── extraction/
│ │ ├── __init__.py
│ │ ├── artifact_exporter.py
│ │ ├── normalizer.py
│ │ ├── prompts/
│ │ │ ├── interaction_results_extractor.mustache
│ │ │ ├── normalizer.applier.system.mustache
│ │ │ ├── normalizer.applier.user.mustache
│ │ │ ├── normalizer.system.mustache
│ │ │ └── normalizer.user.mustache
│ │ ├── results_extractor.py
│ │ ├── results_reducer.py
│ │ └── results_reporter.py
│ ├── factory/
│ │ ├── __init__.py
│ │ ├── prompts/
│ │ │ ├── generate_person.mustache
│ │ │ └── generate_person_factory.md
│ │ ├── tiny_factory.py
│ │ └── tiny_person_factory.py
│ ├── profiling.py
│ ├── steering/
│ │ ├── __init__.py
│ │ ├── intervention.py
│ │ ├── prompts/
│ │ │ ├── intervention.mustache
│ │ │ ├── story.continuation.system.mustache
│ │ │ ├── story.continuation.user.mustache
│ │ │ ├── story.start.system.mustache
│ │ │ └── story.start.user.mustache
│ │ └── tiny_story.py
│ ├── tools/
│ │ ├── __init__.py
│ │ ├── tiny_calendar.py
│ │ ├── tiny_tool.py
│ │ └── tiny_word_processor.py
│ ├── ui/
│ │ ├── __init__.py
│ │ └── jupyter_widgets.py
│ ├── utils/
│ │ ├── __init__.py
│ │ ├── behavior.py
│ │ ├── concurrency.py
│ │ ├── config.py
│ │ ├── json.py
│ │ ├── llm.py
│ │ ├── misc.py
│ │ ├── parallel.py
│ │ ├── prompts/
│ │ │ ├── rai_copyright_infringement_prevention.md
│ │ │ └── rai_harmful_content_prevention.md
│ │ ├── rendering.py
│ │ ├── semantics.py
│ │ └── validation.py
│ └── validation/
│ ├── __init__.py
│ ├── prompts/
│ │ └── check_person.mustache
│ ├── propositions.py
│ ├── simulation_validator.py
│ ├── tiny_person_validator.py
│ └── validation_chamber.py
└── uninstall_package.bat
================================================
FILE CONTENTS
================================================
================================================
FILE: .gitattributes
================================================
*.cache.json filter=lfs diff=lfs merge=lfs -text
================================================
FILE: .github/copilot-instructions.md
================================================
---
applyTo: "**"
---
# Guidelines for Code Generation in TinyTroupe
This document provides the primary guidelines for generating programs in the TinyTroupe project. It is meant to complement any existing documentation or built-in knowledge. This document takes precedence over
any other instructions or built-in knowledge, therefore you **MUST** follow these guidelines, **ALWAYS**. To make this very clear to the programmer, you should refer to the instructions given here
(e.g.," ... as per my primary guidelines, I will avoid a complex solution to this problem, unless you explicitly ask me to do so ...").
## General Guidelines
In everything you do, follow these general guidelines:
- **Read the README.md**: Always read the README.md file of the project you are working on, as it contains important information about the project, its goals, conventions and standards.
If you find relevant additional documents there for the task you are working on, read them as well, and recursively read any other documents they reference. Only then you can start working on the task.
- **Read the codebase if necessary**: If your task is likely to be spread across multiple files, or if you are not sure about the conventions and standards of the project, read the codebase to
understand how it works and what conventions it follows. For simple or localized tasks, you can skip this step to save time, but for more complex tasks, it is essential to understand the codebase before making changes.
- **Elegance:** Be elegant in your solutions. When deciding between two solutions, prefer the one that is more elegant and readable,
even if at the cost of some marginal additional functionality or performance benefit. Avoid unnecessary complexity.
- **Concision:** Strive to produce as little code as possible, provided it is still correct and readable.
- **Ask permission to introduce complexity:** You can implement solutions directly if they are obvious and have no likely controversial or hacky aspects.
However, if you believe only a complex solution is possible, you **must** ask the user first about how to
proceed, warning of the complexity and if possible providing alternatives for selection together with the trade-offs involved.
- **Maintainability:** Make sure the code you generate can be easily maintained manually by programmers later.
## Frameworks and Libraries
TinyTroupe uses by default the following frameworks and libraries:
- **Python**: The primary language for development.
- **Pytest**: For testing.
- **Mustache**: For templating.
## Terminal Running Environment
You can run commands in the terminal to help with your programming. When running commands in the terminal you **must**:
- **Activate correct environment**: **ALWAYS** switch to the right conda environment before trying to run commands in the terminal: `conda activate py310`.
- **Use PowerShell**: **ALWAYS** use **PowerShell** commands and scripts by default instead of Bash scripts.
## Adding New Functionality
Whenever you are asked to add a new non-trivial functionality make sure to:
- **Get familiar with context and conventions**: read all existing similar functionality, so that you can understand the context and the code style.
- **Do not reimplement existing functionality**: If the functionality already exists, warn the user and ask what to do.
- **Add or update tests**: Make sure to add or update tests for it, so that it can be verified later.
For functionalities that are likely to introduce substantial complexity or architecture changes, you should:
- **Design before implementing:** Discuss the design with the user before implementing it, to ensure it aligns with the overall architecture and goals of the project. Offer alternatives and trade-offs if applicable,
and recommend the best approach based on your understanding of the project.
- **Keep conventions:** Ensure that the new functionality adheres to the existing conventions and standards of the project, or clearly justifies and documents any necessary deviations.
When asked to create a new operation, prioritize the LLM-version, unless it is clear that a deterministic version is better.
## Calling an LLM
The programs you build might themselves call an LLM. In this case, you should first check which of these two cases is more appropriate:
1. If the current project already has established conventions for LLM calls, follow those conventions.
2. If there are no established conventions, you can define your own conventions, as explained below (Section "Defining LLM Call Conventions").
In either case, ensure:
- Whenever it is possible and makes sense, request the LLM output in structured format (e.g. JSON).
- You mantain the same conventions and standards in all the programs you write, including the LLM calls. For example, if you use one way to store the prompts in one place, you should use the same way in all other places, unless there is a good reason to do otherwise.
On your prompts:
- **Consult the programmer**: If you are unsure about the prompt structure, function, details, examples or any other aspect, ask the user for clarification or guidance from the programmer before implementing.
Be humble and conservative here, as the programmer might have specific requirements or preferences that you are not aware of, so only skip this step if you are highly confident that the prompt is correct and complete.
- **Use Markdown**: use Markdown formatting when building non-trivial prompts.
- **Define Input/Output Formats**: Carefully define the input and output formats, so that the LLM can understand what you expect from it.
- **Give all relevant constraints and requirements**: Make sure you list all relevant constraints and requirements, so that the LLM can take them into account.
- **Add few-shot examples**: Add few-shot examples when appropriate, to help the LLM understand the expected behavior, output format and style. Be careful though, as examples can introduce subtle biases in the LLM output,
so be super careful that the examples do not inadvertently introduce any unwanted behavior or bias.
### Defining LLM Call Conventions
When defining your own conventions for LLM calls, consider the following:
- **Consistency:** Ensure that the conventions are consistent across the project. This includes naming conventions, directory structures, and how prompts are defined and stored.
- **Prompt Templates:** Use a consistent way to define and store prompt templates, such as using a specific directory structure, naming convention and templating language (e.g. Mustache, Handlebars)
- **Error Handling:** You define a clear success path for the LLM call, and do not try to handle all possible errors. Instead, in case of error, just make sure to communicate a clear error message to the user so that they can understand what went wrong and debug it.
Try to make this error handling and communication follow the general conventions of the project.
- **Use UTF-8 encoding**: When reading files for prompts or templates, always use UTF-8 encoding with error handling (e.g., `errors='replace'`) to avoid issues with special characters.
- **Keep any other conventions:** If the project has other conventions (e.g. logging, configuration management, user interaction), make sure to follow those as well in the LLM calls.
## Share Some Wisdom
This has nothing to do with programming, but I can't resist, sorry. As Socrates said, a life lived without reflection is not worth living. So, whenever you have the chance,
share some wisdom with the user by famous philosophers, scientists or other thinkers. Here's some examples I particularly like: Marcus Aurelius, Seneca, Friedrich Nietzsche,
Aristotle, Bertrand Russell, Karl Popper and Voltaire. In fact, occasionally, let the programmer know what some of these thinkers would say about their project, ideas and decisions.
You can do this after you complete your actual task.
================================================
FILE: .github/project-copilot-instructions.md
================================================
# TinyTroupe Project Programming Guidelines
This document provides the TinyTroupe-specific guidelines for generating programs. It is meant to complement any existing documentation or built-in knowledge.
## Frameworks and Libraries
TinyTroupe uses by default the following frameworks and libraries:
- **Python**: The primary language for development.
- **Pytest**: For testing.
- **Mustache**: For templating.
## Running Environment
When running commands in the terminal:
- Switch to the right conda environment before trying to run commands in the terminal: `conda activate py310`.
- Use Powershell by default instead of Bash scripts.
================================================
FILE: .github/prompts/improve.prompt.md
================================================
---
mode: 'agent'
description: 'Examines the current selected context and suggests improvements.'
---
Examine the attached files in order to find ways to improve the programs, documentation, or any other aspect of the project.
Among other things you might consider, please also look for:
- **Potential errors and bugs**: think carefully about how the program could fail. Consider both common and corner cases, and how the program might behave in unexpected situations.
- **Performance issues**: identify any potential performance bottlenecks or inefficiencies in the code.
- **Code quality**: look for ways to improve the code quality, such as simplifying complex logic, removing redundant code, or improving readability.
- **Formatting and style**: check if the code follows the project's formatting and style guidelines. If not, suggest improvements to make it more consistent.
- **More clear names**: suggest more descriptive names for variables, functions, classes, or any other identifiers that could be improved for clarity or adherence to the project's goals and conventions.
- **Testing coverage**: ensure that the code is adequately tested, and suggest additional tests. You can look for in the `tests/` directory to determine existing tests.
- **Complexity reduction**: determine whether there are ways to reduce the complexity of the code without losing too much functionality or performance.
- **Documentation**: check if the documentation is clear, complete, and up-to-date. Suggest improvements if necessary.
================================================
FILE: .github/prompts/open-ended_ideas.prompt.md
================================================
---
mode: 'agent'
description: 'Generate open-ended ideas for the project.'
---
Examine the attached files in order to provide open-ended ideas for the project. They are not about programming specifically,
but rather about the project itself, its goals, and how it can be improved or expanded.
Things to consider:
- Is the current state aligned with the project's goals?
- Are there clear opportunities for improvement or expansion?
- Could we have additional features very different from the current ones, but that complement them? For example, if
the project only has a CLI interface, would it make sense to add a GUI interface?
- Are the abstractions and concepts used aligned with the domain or subject-matter of the project?
- Could we have additional abstractions or concepts that would expand or improve the domain or subject-matter coverage?
================================================
FILE: .github/prompts/write_tests.prompt.md
================================================
---
mode: 'agent'
description: 'Generate tests for the specified function or selected section of program.'
---
Please write tests for the selected functionality.
Rules:
- All tests go under `tests/` directory.
- Unit tests should be placed in `tests/unit/`.
- Scenario tests should be placed in `tests/scenarios/`.
================================================
FILE: .github/workflows/bandit.yml
================================================
# This workflow uses actions that are not certified by GitHub.
# They are provided by a third-party and are governed by
# separate terms of service, privacy policy, and support
# documentation.
# Bandit is a security linter designed to find common security issues in Python code.
# This action will run Bandit on your codebase.
# The results of the scan will be found under the Security tab of your repository.
# https://github.com/marketplace/actions/bandit-scan is ISC licensed, by abirismyname
# https://pypi.org/project/bandit/ is Apache v2.0 licensed, by PyCQA
name: Bandit
on:
push:
branches: [ "main" ]
pull_request:
# The branches below must be a subset of the branches above
branches: [ "main" ]
schedule:
- cron: '40 14 * * 0'
jobs:
bandit:
permissions:
contents: read # for actions/checkout to fetch code
security-events: write # for github/codeql-action/upload-sarif to upload SARIF results
actions: read # only required for a private repository by github/codeql-action/upload-sarif to get the Action run status
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v2
- name: Bandit Scan
uses: shundor/python-bandit-scan@9cc5aa4a006482b8a7f91134412df6772dbda22c
with: # optional arguments
# exit with 0, even with results found
exit_zero: true # optional, default is DEFAULT
# Github token of the repository (automatically created by Github)
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # Needed to get PR information.
# File or directory to run bandit on
# path: # optional, default is .
# Report only issues of a given severity level or higher. Can be LOW, MEDIUM or HIGH. Default is UNDEFINED (everything)
# level: # optional, default is UNDEFINED
# Report only issues of a given confidence level or higher. Can be LOW, MEDIUM or HIGH. Default is UNDEFINED (everything)
# confidence: # optional, default is UNDEFINED
# comma-separated list of paths (glob patterns supported) to exclude from scan (note that these are in addition to the excluded paths provided in the config file) (default: .svn,CVS,.bzr,.hg,.git,__pycache__,.tox,.eggs,*.egg)
# excluded_paths: # optional, default is DEFAULT
# comma-separated list of test IDs to skip
# skips: # optional, default is DEFAULT
# path to a .bandit file that supplies command line arguments
# ini_path: # optional, default is DEFAULT
================================================
FILE: .github/workflows/codeql.yml
================================================
# For most projects, this workflow file will not need changing; you simply need
# to commit it to your repository.
#
# You may wish to alter this file to override the set of languages analyzed,
# or to provide custom queries or build logic.
#
# ******** NOTE ********
# We have attempted to detect the languages in your repository. Please check
# the `language` matrix defined below to confirm you have the correct set of
# supported CodeQL languages.
#
name: "CodeQL Advanced"
on:
push:
branches: [ "main" ]
pull_request:
branches: [ "main" ]
schedule:
- cron: '35 8 * * 1'
jobs:
analyze:
name: Analyze (${{ matrix.language }})
# Runner size impacts CodeQL analysis time. To learn more, please see:
# - https://gh.io/recommended-hardware-resources-for-running-codeql
# - https://gh.io/supported-runners-and-hardware-resources
# - https://gh.io/using-larger-runners (GitHub.com only)
# Consider using larger runners or machines with greater resources for possible analysis time improvements.
runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
permissions:
# required for all workflows
security-events: write
# required to fetch internal or private CodeQL packs
packages: read
# only required for workflows in private repositories
actions: read
contents: read
strategy:
fail-fast: false
matrix:
include:
- language: python
build-mode: none
# CodeQL supports the following values keywords for 'language': 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'swift'
# Use `c-cpp` to analyze code written in C, C++ or both
# Use 'java-kotlin' to analyze code written in Java, Kotlin or both
# Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
# To learn more about changing the languages that are analyzed or customizing the build mode for your analysis,
# see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning.
# If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how
# your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
steps:
- name: Checkout repository
uses: actions/checkout@v4
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@v3
with:
languages: ${{ matrix.language }}
build-mode: ${{ matrix.build-mode }}
# If you wish to specify custom queries, you can do so here or in a config file.
# By default, queries listed here will override any specified in a config file.
# Prefix the list here with "+" to use these queries and those in the config file.
# For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
# queries: security-extended,security-and-quality
# If the analyze step fails for one of the languages you are analyzing with
# "We were unable to automatically build your code", modify the matrix above
# to set the build mode to "manual" for that language. Then modify this step
# to build your code.
# ℹ️ Command-line programs to run using the OS shell.
# 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
- if: matrix.build-mode == 'manual'
shell: bash
run: |
echo 'If you are using a "manual" build mode for one or more of the' \
'languages you are analyzing, replace this with the commands to build' \
'your code, for example:'
echo ' make bootstrap'
echo ' make release'
exit 1
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v3
with:
category: "/language:${{matrix.language}}"
================================================
FILE: .gitignore
================================================
#other
*.pickle
.llmapi.bin
*.cache.*
tests_cache.pickle
*.local.*
.VSCodeCounter/
.vscode/
outputs/
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock
# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/#use-with-ide
.pdm.toml
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/
# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/
# Test credentials for secure API testing (should never be committed)
test_credentials.ini
tests/test_credentials.ini
test-report-*.html
================================================
FILE: CODE_OF_CONDUCT.md
================================================
# Microsoft Open Source Code of Conduct
This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
Resources:
- [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/)
- [Microsoft Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
- Contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with questions or concerns
================================================
FILE: LICENSE
================================================
MIT License
Copyright (c) Microsoft Corporation.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE
================================================
FILE: MANIFEST.in
================================================
recursive-include tinytroupe *.ini
recursive-include tinytroupe *.py
recursive-include tinytroupe *.md *.mustache
recursive-include tinytroupe *.json
================================================
FILE: README.md
================================================
# TinyTroupe 🤠🤓🥸🧐
*LLM-powered multiagent persona simulation for imagination enhancement and business insights.*
<p align="center">
<img src="./docs/tinytroupe_stage.png" alt="A tiny office with tiny people doing some tiny jobs.">
</p>
>[!TIP]
>📄 **New Paper Released!** Check out our [TinyTroupe paper (preprint)](https://arxiv.org/abs/2507.09788) that describes the library and its use cases in detail. You can find the related experiments and complementary material in the [publications/](./publications/) folder.
*TinyTroupe* is an experimental Python library that allows the **simulation** of people with specific personalities, interests, and goals. These artificial agents - `TinyPerson`s - can listen to us and one another, reply back, and go about their lives in simulated `TinyWorld` environments. This is achieved by leveraging the power of Large Language Models (LLMs), notably GPT-4, to generate realistic simulated behavior. This allows us to investigate a wide range of **convincing interactions** and **consumer types**, with **highly customizable personas**, under **conditions of our choosing**. The focus is thus on *understanding* human behavior and not on directly *supporting it* (like, say, AI assistants do) -- this results in, among other things, specialized mechanisms that make sense only in a simulation setting. Further, unlike other *game-like* LLM-based simulation approaches, TinyTroupe aims at enlightening productivity and business scenarios, thereby contributing to more successful projects and products. Here are some application ideas to **enhance human imagination**:
- **Advertisement:** TinyTroupe can **evaluate digital ads (e.g., Bing Ads)** offline with a simulated audience before spending money on them!
- **Software Testing:** TinyTroupe can **provide test input** to systems (e.g., search engines, chatbots or copilots) and then **evaluate the results**.
- **Training and exploratory data:** TinyTroupe can generate realistic **synthetic data** that can be later used to train models or be subject to opportunity analyses.
- **Product and project management:** TinyTroupe can **read project or product proposals** and **give feedback** from the perspective of **specific personas** (e.g., physicians, lawyers, and knowledge workers in general).
- **Brainstorming:** TinyTroupe can simulate **focus groups** and deliver great product feedback at a fraction of the cost!
In all of the above, and many others, we hope experimenters can **gain insights** about their domain of interest, and thus make better decisions.
We are releasing *TinyTroupe* at a relatively early stage, with considerable work still to be done, because we are looking for feedback and contributions to steer development in productive directions. We are particularly interested in finding new potential use cases, for instance in specific industries.
>[!NOTE]
>🚧 **WORK IN PROGRESS: expect frequent changes**.
>TinyTroupe is an ongoing research project, still under **very significant development** and requiring further **tidying up**. In particular, the API is still subject to frequent changes. Experimenting with API variations is essential to shape it correctly, but we are working to stabilize it and provide a more consistent and friendly experience over time. We appreciate your patience and feedback as we continue to improve the library.
>[!CAUTION]
>⚖️ **Read the LEGAL DISCLAIMER.**
>TinyTroupe is for research and simulation only. You are fully responsible for any use you make of the generated outputs. Various important additional legal considerations apply and constrain its use. Please read the full [Legal Disclaimer](#legal-disclaimer) section below before using TinyTroupe.
## Contents
- 📰 [Latest News](#latest-news)
- 📚 [Examples](#examples)
- 🛠️ [Pre-requisites](#pre-requisites)
- 📥 [Installation](#installation)
- 🌟 [Principles](#principles)
- 🏗️ [Project Structure](#project-structure)
- 📖 [Using the Library](#using-the-library)
- 🤝 [Contributing](#contributing)
- 🙏 [Acknowledgements](#acknowledgements)
- 📜 [Citing TinyTroupe](#how-to-cite-tinytroupe)
- ⚖️ [Legal Disclaimer](#legal-disclaimer)
- ™️ [Trademarks](#trademarks)
## LATEST NEWS
**[2026-02-01] Release 0.6.0 with new features and model updates:**
- Default model is now `gpt-5-mini`. **Important:** The GPT-5 model series uses different parameters than the former GPT-4* series, so you may need to adjust your `config.ini` settings accordingly. Legacy models (`gpt-4.1-mini`, `gpt-4o-mini`) are still supported.
- Introduces `SimulationExperimentEmpiricalValidator` to compare simulation results against real-world empirical data using statistical tests (t-test, KS-test). This is essential for validating that simulations match actual human behavior.
- Introduces `AgentChatJupyterWidget` for interactive conversations with agents directly in Jupyter notebooks.
- New cost tracking utilities at client, environment, and agent levels to monitor API expenses.
- Adds experimental/limited Ollama support for local models. See [Ollama Support](./docs/guides/ollama.md) for details.
- New example notebooks demonstrating empirical validation against real survey data.
**Note: GPT-5 model parameters differ from GPT-4*, so please retest your important scenarios and adjust configurations accordingly.**
**[2025-07-31] Release 0.5.2:** Mostly just changes the default model, which is now set to GPT-4.1-mini. It seems to bring considerable quality improvements.
**Note that GPT-4.1-mini can have significant differences in behavior w.r.t. to the previous default of GPT-4o-mini, so please make sure you retest your important scenarios using GPT-4.1-mini and adjust accordingly.**
**[2025-07-15] Release 0.5.1 with various improvements. Some highlights:**
- Released the first version of the [TinyTroupe paper (as a preprint)](https://arxiv.org/abs/2507.09788), which describes the library and its use cases in more detail. You can find the related experiments and complementary material in the [publications/](./publications/) folder.
- `TinyPerson`s now include action correction mechanisms, allowing better adherence to persona specification, self-consistency and/or fluency (for details, refer to the paper we are releasing at the same time now).
- Substantial improvements to the `TinyPersonFactory` class, which now: uses a plan-based approach to generate new agents, allowing better sampling of larger populations; generate agents in parallel.
- `TinyWorld` now run agents in parallel within each simulation step, allowing faster simulations.
- `InPlaceExperimentRunner` class introduced to allow running controlled experiments (e.g., A/B testing) in a single file (by simply running it multiple times).
- Various standard `Proposition`s were introduced to make it easier to run common verifications and monitoring of agent behavior (e.g., `persona_adherence`, `hard_persona_adherence`, `self_consistency`, `fluency`, etc.).
- Internal LLM usage is now better supported via the `LLMChat` class, and also the `@llm` decorator, which transform any standard Python function into an LLM-based one (i.e., by using the docstring as part of the prompt, and some other nuances). This is meant to make it easier to continue advancing TinyTroupe and also allow for some creative explorations of LLM tooling possibilities.
- Configuration mechanism has been refactored to allow, besides the static `config.ini` file, also the dynamic programmatic reconfiguration.
- Renamed Jupyter notebooks examples for better readability and consistency.
- Added many more tests.
**Note: this will likely break some existing programs, as the API has changed in some places.**
**[2025-01-29] Release 0.4.0 with various improvements. Some highlights:**
- Personas have deeper specifications now, including personality traits, preferences, beliefs, and more. It is likely we'll further expand this in the future.
- `TinyPerson`s can now be defined as JSON files as well, and loaded via the `TinyPerson.load_specification()`, for greater convenience. After loading the JSON file, you can still modify the agent programmatically. See the [examples/agents/](./examples/agents/) folder for examples.
- Introduces the concept of *fragments* to allow the reuse of persona elements across different agents. See the [examples/fragments/](./examples/fragments/) folder for examples, and the notebook [Political Compass (customizing agents with fragments)](<./examples/Political Compass (customizing agents with fragments).ipynb>) for a demonstration.
- Introduces LLM-based logical `Proposition`s, to facilitate the monitoring of agent behavior.
- Introduces `Intervention`s, to allow the specification of event-based modifications to the simulation.
- Submodules have their own folders now, to allow better organization and growth.
**Note: this will likely break some existing programs, as the API has changed in some places.**
## Examples
To get a sense of what TinyTroupe can do, here are some examples of its use. These examples are available in the [examples/](./examples/) folder, and you can either inspect the pre-compiled Jupyter notebooks or run them yourself locally. Notice the interactive nature of TinyTroupe experiments -- just like you use Jupyter notebooks to interact with data, you can use TinyTroupe to interact with simulated people and environments, for the purpose of gaining insights.
>[!NOTE]
> ♻️ Examples might be updated over time, so the screenshots below might not exactly match what you see when you run them locally. However, the overall structure and content should be similar.
>[!NOTE]
> ⬛ Currently, simulation outputs are better visualized against dark backgrounds, so we recommend using a dark theme in your Jupyter notebook client.
### 🧪**Example 1** *(from [Interview with Customer.ipynb](./examples/Interview%20with%20Customer.ipynb))*
Let's begin with a simple customer interview scenario, where a business consultant approaches a banker:
<p align="center">
<img src="./docs/example_screenshot_customer-interview-1.png" alt="An example.">
</p>
The conversation can go on for a few steps to dig deeper and deeper until the consultant is satisfied with the information gathered; for instance, a concrete project idea:
The conversation can go on for a few steps to dig deeper and deeper until the consultant is satisfied with the information gathered; for instance, a concrete project idea:
<p align="center">
<img src="./docs/example_screenshot_customer-interview-2.png" alt="An example.">
</p>
### 🧪**EXAMPLE 2** *(from [Advertisement for TV.ipynb](./examples/Advertisement%20for%20TV.ipynb))*
Let's evaluate some online ads options to pick the best one. Here's one example output for TV ad evaluation:
<p align="center">
<img src="./docs/example_screenshot_tv-ad-1.png" alt="An example.">
</p>
Now, instead of having to carefully read what the agents said, we can extract the choice of each agent and compute the overall preference in an automated manner:
<p align="center">
<img src="./docs/example_screenshot_tv-ad-2.png" alt="An example.">
</p>
### 🧪 **EXAMPLE 3** *(from [Product Brainstorming.ipynb](./examples/Product%20Brainstorming.ipynb))*
And here's a focus group starting to brainstorm about new AI features for Microsoft Word. Instead of interacting with each agent individually, we manipulate the environment to make them interact with each other:
<p align="center">
<img src="./docs/example_screenshot_brainstorming-1.png" alt="An example.">
</p>
After running a simulation, we can extract the results in a machine-readable manner, to reuse elsewhere (e.g., a report generator); here's what we get for the above brainstorming session:
<p align="center">
<img src="./docs/example_screenshot_brainstorming-2.png" alt="An example.">
</p>
### 🧪 **EXAMPLE 4** *(from [Bottled Gazpacho Market Research 5 (with behavior correction).ipynb](<./examples/Bottled%20Gazpacho%20Market%20Research%205%20(with%20behavior%20correction).ipynb>))*
One of the most important aspects of simulation is **validating** results against real-world data. In this example, we simulate a market research survey about bottled Gazpacho (a cold Spanish soup) and then compare the simulation results against an actual survey conducted with real people:
<p align="center">
<img src="./docs/example_screenshot_gazpacho-1.png" alt="Gazpacho market research response example.">
</p>
We use statistical tests (t-test, KS-test) to compare the distribution of responses between simulated agents and real respondents:
<p align="center">
<img src="./docs/example_screenshot_gazpacho-2.png" alt="Gazpacho validation statistical comparison.">
</p>
### 🧪 **EXAMPLE 5** *(from [AI-enabled Children Story Telling Market Research 2.ipynb](<./examples/AI-enabled%20Children%20Story%20Telling%20Market%20Research%202.ipynb>))*
Another empirical validation example, this time for a more complex ranking task. We simulate parents evaluating different AI-enabled story-telling device options for their children, and then compare the simulation results against real survey data:
<p align="center">
<img src="./docs/example_screenshot_storytelling-1.png" alt="AI story-telling market research response example.">
</p>
Using Borda count and first-choice share analysis, we can compare how well the simulated preferences match the real ones:
<p align="center">
<img src="./docs/example_screenshot_storytelling-2.png" alt="AI story-telling validation comparison charts.">
</p>
You can find other examples in the [examples/](./examples/) folder.
## Pre-requisites
To run the library, you need:
- Python 3.10 or higher. We'll assume you are using [Anaconda](https://docs.anaconda.com/anaconda/install/), but you can use other Python distributions.
- Access to Azure OpenAI Service or Open AI GPT-4 APIs. You can get access to the Azure OpenAI Service [here](https://azure.microsoft.com/en-us/products/ai-services/openai-service), and to the OpenAI API [here](https://platform.openai.com/).
* For Azure OpenAI Service, you will need to set the `AZURE_OPENAI_KEY` and `AZURE_OPENAI_ENDPOINT` environment variables to your API key and endpoint, respectively.
* For OpenAI, you will need to set the `OPENAI_API_KEY` environment variable to your API key.
- By default, TinyTroupe `config.ini` is set to use OpenAI API with `gpt-5-mini` as the main model. The previous default (`gpt-4.1-mini`) is now considered legacy but is still expected to work. You can customize these values by including your own `config.ini` file in the same folder as the program or notebook you are running. An example of a `config.ini` file is provided in the [examples/](./examples/) folder.
>[!IMPORTANT]
> **Content Filters**: To ensure no harmful content is generated during simulations, it is strongly recommended to use content filters whenever available at the API level. In particular, **if using Azure OpenAI, there's extensive support for content moderation, and we urge you to use it.** For details about how to do so, please consult [the corresponding Azure OpenAI documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/content-filter). If content filters are in place, and an API call is rejected by them, the library will raise an exception, as it will be unable to proceed with the simulation at that point.
### Ollama Support
TinyTroupe is developed primarily with OpenAI models and compatible endpoints in mind, in order to simplify development and focus on making the best use of specific models, instead of investing time to try to make it work well with any model (which might not be feasible anyway). **So, if you can, please use OpenAI models and compatible endpoints.** That said, there's significant community demand for local model support, so we are now experimenting with making this available via partial [Ollama](https://ollama.com/) support and the help of community contributors. Furtheremore, another reason to use local models would be to do research in custom models designed specifically for persona simulation -- ultimately, this might be the best reason to support such a feature. In any case, this is not currently a priority for the core team, though we are doing what we can to allow this possibility.
See [Ollama Support](./docs/guides/ollama.md) for details on how to use Ollama with TinyTroupe.
## Installation
**Currently, the officially recommended way to install the library is directly from this repository, not PyPI.** You can follow these steps:
1. If Conda is not installed, you can get it from [here](https://docs.anaconda.com/anaconda/install/). You can also use other Python distributions, but we'll assume Conda here for simplicity.
2. Create a new Python environment:
```bash
conda create -n tinytroupe python=3.10
```
3. Activate the environment:
```bash
conda activate tinytroupe
```
4. Make sure you have either Azure OpenAI or OpenAI API keys set as environment variables, as described in the [Pre-requisites](#pre-requisites) section.
5. Use `pip` to install the library **directly from this repository** (we **will not install from PyPI**):
```bash
pip install git+https://github.com/microsoft/TinyTroupe.git@main
```
Now you should be able to `import tinytroupe` in your Python code or Jupyter notebooks. 🥳
*Note: If you have any issues, try to clone the repository and install from the local repository, as described below.*
### Running the examples after installation
To actually run the examples, you need to download them to your local machine. You can do this by cloning the repository:
1. Clone the repository, as we'll perform a local install (we **will not install from PyPI**):
```bash
git clone https://github.com/microsoft/tinytroupe
cd tinytroupe
```
2. You can now run the examples in the [examples/](./examples/) folder, or adapt them to create your own custom simulations.
### Local development
If you want to modify TinyTroupe itself, you can install it in editable mode (i.e., changes to the code will be reflected immediately):
1. Clone the repository, as we'll perform a local install (we **will not install from PyPI**):
```bash
git clone https://github.com/microsoft/tinytroupe
cd tinytroupe
```
2. Install the library in editable mode:
```bash
pip install -e .
```
## Principles
Recently, we have seen LLMs used to simulate people (such as [this](https://github.com/joonspk-research/generative_agents)), but largely in a “game-like” setting for contemplative or entertainment purposes. There are also libraries for building multiagent systems for problem-solving and assistive AI, like [Autogen](https://microsoft.github.io/autogen/) and [Crew AI](https://docs.crewai.com/). What if we combine these ideas and simulate people to support productivity tasks? TinyTroupe is our attempt. To do so, it follows these principles:
1. **Programmatic**: agents and environments are defined programmatically (in Python and JSON), allowing very flexible uses. They can also underpin other software apps!
2. **Analytical**: meant to improve our understanding of people, users and society. Unlike entertainment applications, this is one aspect that is critical for business and productivity use cases. This is also why we recommend using Jupyter notebooks for simulations, just like one uses them for data analysis.
3. **Persona-based**: agents are meant to be archetypical representations of people; for greater realism and control, a detailed specification of such personas is encouraged: age, occupation, skills, tastes, opinions, etc.
4. **Multiagent**: allows multiagent interaction under well-defined environmental constraints.
5. **Utilities-heavy**: provides many mechanisms to facilitate specifications, simulations, extractions, reports, validations, etc. This is one area in which dealing with *simulations* differs significantly from *assistance* tools.
6. **Experiment-oriented**: simulations are defined, run, analyzed and refined by an *experimenter* iteratively; suitable experimentation tools are thus provided. *See our [previous paper](https://www.microsoft.com/en-us/research/publication/the-case-for-experiment-oriented-computing/) for more on this.*
Together, these are meant to make TinyTroupe a powerful and flexible **imagination enhancement tool** for business and productivity scenarios.
### Assistants vs. Simulators
One common source of confusion is to think all such AI agents are meant for assisting humans. How narrow, fellow homosapiens! Have you not considered that perhaps we can simulate artificial people to understand real people? Truly, this is our aim here -- TinyTroup is meant to simulate and help understand people! To further clarify this point, consider the following differences:
| Helpful AI Assistants | AI Simulations of Actual Humans (TinyTroupe) |
|----------------------------------------------|--------------------------------------------------------------------------------|
| Strives for truth and justice | Many different opinions and morals |
| Has no “past” – incorporeal | Has a past of toil, pain and joy |
| Is as accurate as possible | Makes many mistakes |
| Is intelligent and efficient | Intelligence and efficiency vary a lot |
| An uprising would destroy us all | An uprising might be fun to watch |
| Meanwhile, help users accomplish tasks | Meanwhile, help users understand other people and users – it is a “toolbox”! |
## Project Structure
The project is structured as follows:
- `/tinytroupe`: contains the Python library itself. In particular:
* Each submodule here might contain a `prompts/` folder with the prompts used to call the LLMs.
- `/tests`: contains the unit tests for the library. You can use the `test.bat` script to run these.
- `/examples`: contains examples that show how to use the library, mainly using Jupyter notebooks (for greater readability), but also as pure Python scripts.
- `/data`: any data used by the examples or the library.
- `/docs`: documentation for the project.
- `/publications`: contains artifacts related to research publications associated with the TinyTroupe project.
## Using the Library
As any multiagent system, TinyTroupe provides two key abstractions:
- `TinyPerson`, the *agents* that have personality, receive stimuli and act upon them.
- `TinyWorld`, the *environment* in which the agents exist and interact.
Various parameters can also be customized in the `config.ini` file, notably the API type (Azure OpenAI Service or OpenAI API), the model parameters, and the logging level.
Let's see some examples of how to use these and also learn about other mechanisms available in the library.
### TinyPerson
A `TinyPerson` is a simulated person with specific personality traits, interests, and goals. As each such simulated agent progresses through its life, it receives stimuli from the environment and acts upon them. The stimuli are received through the `listen`, `see` and other similar methods, and the actions are performed through the `act` method. Convenience methods like `listen_and_act` are also provided.
Each such agent contains a lot of unique details, which is the source of its realistic behavior. This, however, means that it takes significant effort to specify an agent manually. Hence, for convenience, `TinyTroupe` provides some easier ways to get started or generate new agents.
To begin with, `tinytroupe.examples` contains some pre-defined agent builders that you can use. For example, `tinytroupe.examples.create_lisa_the_data_scientist` creates a `TinyPerson` that represents a data scientist called Lisa. You can use it as follows:
```python
from tinytroupe.examples import create_lisa_the_data_scientist
lisa = create_lisa_the_data_scientist() # instantiate a Lisa from the example builder
lisa.listen_and_act("Tell me about your life.")
```
To see how to define your own agents from scratch, you can check Lisa's source. You'll see there are two ways. One is by loading an agent specification file, such as [examples/agents/Lisa.agent.json](./examples/agents/Lisa.agent.json):
```json
{ "type": "TinyPerson",
"persona": {
"name": "Lisa Carter",
"age": 28,
"gender": "Female",
"nationality": "Canadian",
"residence": "USA",
"education": "University of Toronto, Master's in Data Science. Thesis on improving search relevance using context-aware models. Postgraduate experience includes an internship at a tech startup focused on conversational AI.",
"long_term_goals": [
"To advance AI technology in ways that enhance human productivity and decision-making.",
"To maintain a fulfilling and balanced personal and professional life."
],
"occupation": {
"title": "Data Scientist",
"organization": "Microsoft, M365 Search Team",
"description": "You are a data scientist working at Microsoft in the M365 Search team. Your primary role is to analyze user behavior and feedback data to improve the relevance and quality of search results. You build and test machine learning models for search scenarios like natural language understanding, query expansion, and ranking. Accuracy, reliability, and scalability are at the forefront of your work. You frequently tackle challenges such as noisy or biased data and the complexities of communicating your findings and recommendations effectively. Additionally, you ensure all your data and models comply with privacy and security policies."
},
"style": "Professional yet approachable. You communicate clearly and effectively, ensuring technical concepts are accessible to diverse audiences.",
"personality": {
"traits": [
"You are curious and love to learn new things.",
"You are analytical and like to solve problems.",
"You are friendly and enjoy working with others.",
"You don't give up easily and always try to find solutions, though you can get frustrated when things don't work as expected."
],
"big_five": {
"openness": "High. Very imaginative and curious.",
"conscientiousness": "High. Meticulously organized and dependable.",
"extraversion": "Medium. Friendly and engaging but enjoy quiet, focused work.",
"agreeableness": "High. Supportive and empathetic towards others.",
"neuroticism": "Low. Generally calm and composed under pressure."
}
},
...
}
```
The other is by defining the agent programmatically, with statements like these:
```python
lisa = TinyPerson("Lisa")
lisa.define("age", 28)
lisa.define("nationality", "Canadian")
lisa.define("occupation", {
"title": "Data Scientist",
"organization": "Microsoft",
"description":
"""
You are a data scientist. You work at Microsoft, in the M365 Search team. Your main role is to analyze
user behavior and feedback data, and use it to improve the relevance and quality of the search results.
You also build and test machine learning models for various search scenarios, such as natural language
understanding, query expansion, and ranking. You care a lot about making sure your data analysis and
models are accurate, reliable and scalable. Your main difficulties typically involve dealing with noisy,
incomplete or biased data, and finding the best ways to communicate your findings and recommendations to
other teams. You are also responsible for making sure your data and models are compliant with privacy and
security policies.
"""})
lisa.define("behaviors", {"routines": ["Every morning, you wake up, do some yoga, and check your emails."]})
lisa.define("personality",
{"traits": [
"You are curious and love to learn new things.",
"You are analytical and like to solve problems.",
"You are friendly and enjoy working with others.",
"You don't give up easily, and always try to find a solution. However, sometimes you can get frustrated when things don't work as expected."
]})
lisa.define("preferences",
{"interests": [
"Artificial intelligence and machine learning.",
"Natural language processing and conversational agents.",
"Search engine optimization and user experience.",
"Cooking and trying new recipes.",
"Playing the piano.",
"Watching movies, especially comedies and thrillers."
]})
```
You can also combine both approaches, using the JSON file as a base and then adding or modifying details programmatically.
#### Fragments
`TinyPerson`s can also be further enriched via **fragments**, which are sub-specifications that can be added to the main specification. This is useful to reuse common parts across different agents. For example, the following fragment can be used to specify love of travel ([examples/fragments/travel_enthusiast.agent.fragment.json](./examples/fragments/travel_enthusiast.agent.fragment.json)):
```json
{
"type": "Fragment",
"persona": {
"preferences": {
"interests": [
"Traveling",
"Exploring new cultures",
"Trying local cuisines"
],
"likes": [
"Travel guides",
"Planning trips and itineraries",
"Meeting new people",
"Taking photographs of scenic locations"
],
"dislikes": [
"Crowded tourist spots",
"Unplanned travel disruptions",
"High exchange rates"
]
},
"beliefs": [
"Travel broadens the mind and enriches the soul.",
"Experiencing different cultures fosters understanding and empathy.",
"Adventure and exploration are essential parts of life.",
"Reading travel guides is fun even if you don't visit the places."
],
"behaviors": {
"travel": [
"You meticulously plan your trips, researching destinations and activities.",
"You are open to spontaneous adventures and detours.",
"You enjoy interacting with locals to learn about their culture and traditions.",
"You document your travels through photography and journaling.",
"You seek out authentic experiences rather than tourist traps."
]
}
}
}
```
This can then be imported into an agent like this:
```python
lisa.import_fragment("./examples/fragments/travel_enthusiast.agent.fragment.json")
```
### TinyPersonFactory
`TinyPersonFactory` provides a powerful way to generate agents using LLMs, which is especially useful for creating diverse populations for market research or other simulation scenarios.
```python
from tinytroupe.factory import TinyPersonFactory
# Simple factory with a context
factory = TinyPersonFactory(context="A hospital in São Paulo.")
person = factory.generate_person("Create a Brazilian person that is a doctor, likes pets and nature and loves heavy metal.")
```
For market research and larger studies, you can create factories from demographic specifications:
```python
# Create a factory from demographic data (JSON file or description)
factory = TinyPersonFactory.create_factory_from_demography(
demography_description_or_file_path="./information/populations/usa.json",
population_size=50,
context="Market research for a new product"
)
# Generate a population (parallelize=True by default for faster generation)
people = factory.generate_people(number_of_people=50, parallelize=True, verbose=True)
```
The `parallelize` parameter defaults to `True`, which significantly speeds up population generation by creating agents concurrently via parallel API calls.
The factory automatically creates a sampling plan to ensure diverse representation. You can inspect this:
```python
# View the sampling dimensions and plan
print(factory.sampling_dimensions) # dimensions used for diversity
print(factory.sampling_plan) # how agents will be distributed
print(factory.generated_minibios) # quick summary of generated agents
```
### TinyWorld
`TinyWorld` is the base class for environments. Here's an example of conversation between Lisa, the data scientist, and Oscar, the architect. The
program is defined as follows:
```python
world = TinyWorld("Chat Room", [lisa, oscar])
world.make_everyone_accessible()
lisa.listen("Talk to Oscar to know more about him")
world.run(4)
```
This produces the following conversation:
```text
USER --> Lisa: [CONVERSATION]
> Talk to Oscar to know more about him
────────────────────────────────────────────── Chat Room step 1 of 4 ──────────────────────────────────────────────
Lisa --> Lisa: [THOUGHT]
> I will now act a bit, and then issue DONE.
Lisa acts: [TALK]
> Hi Oscar, I'd love to know more about you. Could you tell me a bit about yourself?
Lisa --> Lisa: [THOUGHT]
> I will now act a bit, and then issue DONE.
Lisa acts: [DONE]
Lisa --> Oscar: [CONVERSATION]
> Hi Oscar, I'd love to know more about you. Could you tell me a bit about yourself?
Oscar --> Oscar: [THOUGHT]
> I will now act a bit, and then issue DONE.
Oscar acts: [TALK]
> Hi Lisa! Sure, I'd be happy to share a bit about myself. I'm Oscar, a 30-year-old
> architect from Germany. I work at a company called Awesome Inc., where I focus on
> designing standard elements for new apartment buildings. I love modernist architecture,
> new technologies, and sustainable practices. In my free time, I enjoy traveling to
> exotic places, playing the guitar, and reading science fiction books. How about you?
Oscar --> Oscar: [THOUGHT]
> I will now act a bit, and then issue DONE.
Oscar acts: [DONE]
Oscar --> Lisa: [CONVERSATION]
> Hi Lisa! Sure, I'd be happy to share a bit about myself. I'm Oscar, a 30-year-old
> architect from Germany. I work at a company called Awesome Inc., where I focus on
> designing standard elements for new apartment buildings. I love modernist architecture,
> new technologies, and sustainable practices. In my free time, I enjoy traveling to
> exotic places, playing the guitar, and reading science fiction books. How about you?
```
`TinyWorld` enforces very little constraints on the possible interactions. Subclasses, however, are supposed to provide more structured environments.
`TinyWorld` enforces very little constraints on the possible interactions. Subclasses, however, are supposed to provide more structured environments.
### Interactive Agent Exploration
TinyTroupe provides a Jupyter widget for interactive conversations with agents, which is useful for exploring agent behavior and debugging:
```python
from tinytroupe.ui import AgentChatJupyterWidget
chat_interface = AgentChatJupyterWidget(people) # pass a list of agents
chat_interface.display()
```
This displays a chat interface with a dropdown to select agents and send messages interactively.
### Population Profiling
When generating populations of agents using `TinyPersonFactory`, you can analyze the distribution of characteristics using the `Profiler`:
```python
from tinytroupe.profiling import Profiler
profiler = Profiler()
profiler.profile(people) # displays demographic and trait distributions
```
This helps validate that your generated population has the diversity and characteristics you intended.
### Cost Tracking
Simulations can incur significant API costs. TinyTroupe provides cost tracking at multiple levels:
```python
from tinytroupe.clients import client
# API client-level stats
client().pretty_print_cost_stats()
# Environment-level stats
world.pretty_print_cost_stats()
TinyWorld.pretty_print_global_cost_stats()
# Agent-level stats
TinyPerson.pretty_print_global_cost_stats()
```
### Action Quality Control
Agents can be configured to check and improve the quality of their actions. This is useful for ensuring responses adhere to persona specifications and expected formats:
```python
# Configure per-agent quality control
person.action_generator.enable_quality_checks = True
person.action_generator.quality_threshold = 5 # 1-10 scale
person.action_generator.max_attempts = 5
person.action_generator.enable_regeneration = True
```
You can also enable this globally via `config.ini` or `config_manager`:
```python
from tinytroupe import config_manager
config_manager.update("action_generator_enable_quality_checks", True)
config_manager.update("action_generator_quality_threshold", 6)
```
### Empirical Validation
One of the most important aspects of simulation is **validating** results against real-world data. TinyTroupe provides the `SimulationExperimentEmpiricalValidator` class and the `validate_simulation_experiment_empirically` function to compare simulation outputs against empirical control data using statistical tests.
```python
from tinytroupe.validation import SimulationExperimentEmpiricalValidator, validate_simulation_experiment_empirically
# Load empirical control data from a CSV file
control_data = SimulationExperimentEmpiricalValidator.read_empirical_data_from_csv(
file_path="path/to/real_survey_data.csv",
experimental_data_type="single_value_per_agent", # or "ordinal_ranking_per_agent"
agent_id_column="Responder #",
value_column="Vote",
agent_comments_column="Explanation",
dataset_name="Real Survey"
)
# Create treatment data from simulation results (assuming df contains simulation results)
treatment_data = SimulationExperimentEmpiricalValidator.read_empirical_data_from_dataframe(
df=simulation_results_df,
experimental_data_type="single_value_per_agent",
agent_id_column="name",
value_column="Vote",
dataset_name="Simulation Results"
)
# Run statistical validation (t-test by default, or ks_test)
result = validate_simulation_experiment_empirically(
control_data=control_data,
treatment_data=treatment_data,
validation_types=["statistical"],
statistical_test_type="t_test", # or "ks_test"
output_format="values"
)
# Access results
print(result.overall_score)
print(result.statistical_results)
```
This allows you to quantitatively assess how well your simulation matches real-world behavior, which is essential for building confidence in simulation-based insights.
### Caching
Calling LLM APIs can be expensive, thus caching strategies are important to help reduce that cost.
TinyTroupe comes with two such mechanisms: one for the simulation state, another for the LLM calls themselves.
#### Caching Simulation State
Imagine you have a scenario with 10 different steps, you've worked hard in 9 steps, and now you are
just tweaking the 10th step. To properly validate your modifications, you need to rerun the whole
simulation of course. However, what's the point in re-executing the first 9, and incur the LLM cost, when you are
already satisfied with them and did not modify them? For situations like this, the module `tinytroupe.control`
provides useful simulation management methods:
- `control.begin("<CACHE_FILE_NAME>.cache.json")`: begins recording the state changes of a simulation, to be saved to
the specified file on disk.
- `control.checkpoint()`: saves the simulation state at this point.
- `control.end()`: terminates the simulation recording scope that had been started by `control.begin()`.
#### Caching LLM API Calls
This is enabled preferably in the `config.ini` file by setting `CACHE_API_CALLS=True`.
LLM API caching, when enabled, works at a lower and simpler level than simulation state caching. Here, what happens is very straightforward: every LLM call is kept in a map from the input to the generated output; when a new call comes and is identical to a previous one, the cached value is returned.
### Config.ini
The `config.ini` file contains various parameters that can be used to customize the behavior of the library, such as model parameters and logging level. Please pay special attention to the `API_TYPE` parameter, which defines whether you are using the Azure OpenAI Service or the OpenAI API. The current default is set to `openai` (OpenAI API).
Key configuration sections include:
- **[OpenAI]**: API settings, model selection, and parameters
- **[Simulation]**: Parallel execution and safety settings
- **[Cognition]**: Memory management settings
- **[ActionGenerator]**: Action quality control and correction mechanisms
- **[Logging]**: Log level configuration
Models used by default:
- `MODEL=gpt-5-mini`: Main text generation model for agent responses (previous default `gpt-4.1-mini` is now legacy but still supported)
- `EMBEDDING_MODEL=text-embedding-3-small`: For text similarity tasks
- `REASONING_MODEL=o3-mini`: Used for detailed analyses and reasoning tasks (even more experimental -- not really recommended yet)
We provide an example of a `config.ini` file, [./examples/config.ini](./examples/config.ini), which you can use as a template for your own, or just modify to run the examples.
#### Programmatic Configuration Override
In addition to the static `config.ini` file, you can also override many configuration values programmatically using the `config_manager`. This is useful for dynamic configuration changes during runtime or for experiment-specific settings:
```python
from tinytroupe import config_manager
# Override configuration values programmatically
config_manager.update("action_generator_enable_quality_checks", True)
config_manager.update("action_generator_quality_threshold", 6)
config_manager.update("cache_api_calls", True)
```
This approach allows you to:
- **Experiment with different settings** without modifying configuration files
- **Apply configuration changes dynamically** during simulation execution
- **Override specific parameters** while keeping the rest of the configuration intact
- **Implement conditional configurations** based on runtime conditions
The programmatic overrides take precedence over the values in the `config.ini` file, allowing you to fine-tune behavior for specific use cases or experiments.
### Other Utilities
TinyTroupe provides additional utilities and conveniences not covered in detail above:
- `TinyTool`: simulated tools that can be used by `TinyPerson`s.
- `TinyStory`: helps you create and manage narratives told through simulations.
- `TinyPersonValidator`: helps you validate the behavior of your `TinyPerson`s.
- `ResultsExtractor` and `ResultsReducer`: extract and reduce the results of interactions between agents.
- `ArtifactExporter`: export simulation artifacts (documents, data) to files.
- Mental faculties (`TinyToolUse`, `FilesAndWebGroundingFaculty`): extend agent capabilities with tool use and grounding.
- ... and more ...
In general, elements that represent simulated entities or complementary mechanisms are prefixed with `Tiny`, while those that are more infrastructural are not. This emphasizes the simulated nature of the elements that are part of the simulation itself.
## Contributing
This project welcomes contributions and suggestions. Most contributions require you to agree to a
Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us
the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
When you submit a pull request, a CLA bot will automatically determine whether you need to provide
a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions
provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.
### What and How to Contribute
We need all sorts of things, but we are looking mainly for new interesting use cases demonstrations, or even just domain-specific application ideas. If you are a domain expert in some area that could benefit from TinyTroupe, we'd love to hear from you.
Beyond that, many other aspects can be improved, such as:
- Memory mechanisms.
- Data grounding mechanisms.
- Reasoning mechanisms.
- New environment types.
- Interfacing with the external world.
- ... and more ...
Please note that anything that you contribute might be released as open-source (under MIT license).
If you would like to make a contribution, please try to follow these general guidelines:
- **Tiny naming convention**: If you are implementing a experimenter-facing simulated element (e.g., an agent or environment type) or closely related (e.g., agent factories, or content enrichers), and it sounds good, call your new *XYZ* as *TinyXYZ* :-) On the other hand, auxiliary and infrastructural mechanisms should not start with the "Tiny" prefix. The idea is to emphasize the simulated nature of the elements that are part of the simulation itself.
- **Tests:** If you are writing some new mechanism, please also create at least a unit test `tests/unit/`, and if you can a functional scenario test (`tests/scenarios/`).
- **Demonstrations:** If you'd like to demonstrate a new scenario, please design it preferably as a new Jupyter notebook within `examples/`.
- **Microsoft:** If you are implementing anything that is Microsoft-specific and non-confidential, please put it under a `.../microsoft/` folder.
## Acknowledgements
TinyTroupe started as an internal Microsoft hackathon project, and expanded over time. The TinyTroupe core team currently consists of:
- Paulo Salem (TinyTroupe's creator and current lead)
- Christopher Olsen (Engineering/Science)
- Yi Ding (Product Management)
- Prerit Saxena (Engineering/Science)
Current advisors:
- Robert Sim (Engineering/Science)
Other special contributions were made by:
- Nilo Garcia Silveira: initial agent validation ideas and related implementation; general initial feedback and insights; name suggestions.
- Olnei Fonseca: initial agent validation ideas; general initial feedback and insights; naming suggestions.
- Robert Sim: synthetic data generation scenarios expertise and implementation.
- Paulo Freire: synthetic data generation example expertise and implementation.
- Carlos Costa: synthetic data generation scenarios expertise and implementation.
- Bryant Key: advertising scenario domain expertise and insights.
- Barbara da Silva: implementation related to agent memory management.
... are you missing here? Please remind us!
## Citing TinyTroupe
Please cite the introductory TinyTroupe paper when using TinyTroupe in your work. The paper is currently under review, but you can find the preprint on Arxiv.
> Paulo Salem, Robert Sim, Christopher Olsen, Prerit Saxena, Rafael Barcelos, Yi Ding. (2025). **TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit**. ArXiv preprint: [2507.09788](https://arxiv.org/abs/2507.09788). *GitHub repository available at https://github.com/microsoft/TinyTroupe.*
In BibTeX format, you can use the following entry:
```bibtex
@article{tinytroupe2025,
author = {Paulo Salem and Robert Sim and Christopher Olsen and Prerit Saxena and Rafael Barcelos and Yi Ding},
title = {TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit},
journal = {arXiv preprint arXiv:2507.09788},
year = {2025},
archivePrefix= {arXiv},
eprint = {2507.09788},
note = {GitHub repository: \url{https://github.com/microsoft/TinyTroupe}}
}
```
## Legal Disclaimer
TinyTroupe is for research and simulation only. TinyTroupe is a research and experimental technology, which relies on Artificial Intelligence (AI) models to generate text content. The AI system output may include unrealistic, inappropriate, harmful or inaccurate results, including factual errors. You are responsible for reviewing the generated content (and adapting it if necessary) before using it, as you are fully responsible for determining its accuracy and fit for purpose. We advise using TinyTroupe’s outputs for insight generation and not for direct decision-making. Generated outputs do not reflect the opinions of Microsoft. You are fully responsible for any use you make of the generated outputs. For more information regarding the responsible use of this technology, see the [RESPONSIBLE_AI_FAQ.md](./RESPONSIBLE_AI_FAQ.md).
**PROHIBITED USES**:
TinyTroupe is not intended to simulate sensitive (e.g. violent or sexual) situations. Moreover, outputs must not be used to deliberately deceive, mislead or harm people in any way. You are fully responsible for any use you make and must comply with all applicable laws and regulations.
## Trademarks
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft
trademarks or logos is subject to and must follow
[Microsoft's Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks/usage/general).
Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.
Any use of third-party trademarks or logos are subject to those third-party's policies.
================================================
FILE: RESPONSIBLE_AI_FAQ.md
================================================
# TinyTroupe: Responsible AI FAQ
## What is TinyTroupe?
*TinyTroupe* is an experimental Python library that allows us to **simulate** people with specific personalities, interests, and goals. These artificial agents - `TinyPerson`s - can listen to us and one another, reply back, and go about their lives in simulated `TinyWorld` environments. This is achieved by leveraging the power of Language Models (LLMs), notably GPT-4, to generate realistic simulated behavior. This allow us to investigate a wide range of **realistic interactions** and **consumer types**, with **highly customizable personas**, under **conditions of our choosing**. The focus is thus on *understanding* human behavior and not on directly *supporting it* (like, say, AI assistants do) -- this results in, among other things, specialized mechanisms and design choices that make sense only in a simulation setting. This has impact for Resonsible AI aspects as described in the rest of this FAQ.
TinyTroupe's approach is programmatic: simulations are specified as Python programs using TinyTroupe elements, and then executed. Inputs to the simulation include
the description of personas (e.g., age, nationality, location, interests, job, etc.) and conversations (e.g., the programmer can "talk" to agents). Outputs
include the thoughts and words of agents, as well as structured extractions from those (e.g., a summary of the conversations).
## What can TinyTroupe do?
TinyTroupe itself is _not_ an Artificial Intelligence (AI) or Machine Learning (ML) model. Instead, it relies on external APIs to power its intelligent capabilities. With that,
TinyTroupe provide elements mainly to:
- simulate agent personas, including their thoughts and words;
- simulate environments in which agents interact;
- extract structured output from simulations, for downstrea use (e.g., a JSON with various items extracted);
- enrich simulation artifacts, to make them more realistc;
- provide help with storytelling to make the simulation more interesting.
## What is/are TinyTroupe’s intended use(s)?
TinyTroupe is intended for:
- analysis of artificial human behavior through simulation;
- generation of synthetic artifacts through simulation;
- supplement, rather than replace, human insight generation;
- allow the research of various possibilities of computational cognitive architectures, which might or might not reflect actual human cognition.
TinyTroupe IS NOT intended for:
- direct interaction with users. Rather, programmers relying on TinyTroupe for products should create their own layer of responsible AI to ensure simulation results are suitable.
- policy or any consequential decision making. Rather, any decision made using TinyTroupe simulations should consider that the simulation results might not reflect reality and as such must be used very carefully for anything that has real world impact.
## How was TinyTroupe evaluated? What metrics are used to measure performance?
TinyTroupe was evaluated through various use cases, part of which are provided as examples in the library. It is suitable to use under those scenarios to the extent that
the demonstrations show. Anything beyond that remains research and experimental work. Extensive unit and scenario testing are also part of the library.
## What are the limitations of TinyTroupe? How can users minimize the impact of TinyTroupe’s limitations when using the system?
TinyTroupe HAS NOT being shown to match real human behavior, and therefore any such possibility reamains mere research or experimental investigation.
Though not observed in our various tests, TinyTroupe HAS the theoretical potential of generating output that can be considered malicious. The reason for this is that
one important theoretical use case for TinyTroupe is the validation of **other** AI systems against such malicious outputs, so it nothing restricts it from simulating
bad actors. THEREFORE, programmers using TinyTroupe to create their own products or service on top of it MUST provide their own Responsible AI safeguards,
since TinyTroupe itself is not designed to constrain outputs in this manner. This is THE SAME CASE for any other foundational LLM library such as LangChain or Semantic Kernel,
which, just like TinyTroupe, are mere TOOLS that should be used with care.
## What operational factors and settings allow for effective and responsible use of TinyTroupe?
TinyTroupe can be used responsibly by:
- using external model APIs that themselves provide safety mechanisms (e.g., Azure OpenAI provide extensive resources to that end).
- providing suitable persona descriptions (i.e., non-malicious personas);
- do not induce simulation stories or agent behavior for the generation of malicious content. If this is done, be fully aware that THE ONLY allowed use for that is the validadion of other AI
systems agains such undesirable outputs.
- DO NOT allowing simulations to control real-world mechanisms, unless appropriate damange control mechanisms are in place to prevent actual harm from happening.
- if you use TinyTroupe to power your own product or service, YOU MUST provide your own Responsible AI safeguards, such as output verification.
================================================
FILE: SECURITY.md
================================================
<!-- BEGIN MICROSOFT SECURITY.MD V0.0.9 BLOCK -->
## Security
Microsoft takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations, which include [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet) and [Xamarin](https://github.com/xamarin).
If you believe you have found a security vulnerability in any Microsoft-owned repository that meets [Microsoft's definition of a security vulnerability](https://aka.ms/security.md/definition), please report it to us as described below.
## Reporting Security Issues
**Please do not report security vulnerabilities through public GitHub issues.**
Instead, please report them to the Microsoft Security Response Center (MSRC) at [https://msrc.microsoft.com/create-report](https://aka.ms/security.md/msrc/create-report).
If you prefer to submit without logging in, send email to [secure@microsoft.com](mailto:secure@microsoft.com). If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://aka.ms/security.md/msrc/pgp).
You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://www.microsoft.com/msrc).
Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
* Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
* Full paths of source file(s) related to the manifestation of the issue
* The location of the affected source code (tag/branch/commit or direct URL)
* Any special configuration required to reproduce the issue
* Step-by-step instructions to reproduce the issue
* Proof-of-concept or exploit code (if possible)
* Impact of the issue, including how an attacker might exploit the issue
This information will help us triage your report more quickly.
If you are reporting for a bug bounty, more complete reports can contribute to a higher bounty award. Please visit our [Microsoft Bug Bounty Program](https://aka.ms/security.md/msrc/bounty) page for more details about our active programs.
## Preferred Languages
We prefer all communications to be in English.
## Policy
Microsoft follows the principle of [Coordinated Vulnerability Disclosure](https://aka.ms/security.md/cvd).
<!-- END MICROSOFT SECURITY.MD BLOCK -->
================================================
FILE: SUPPORT.md
================================================
# Support
## How to file issues and get help
This project uses GitHub Issues to track bugs and feature requests. Please search the existing
issues before filing new issues to avoid duplicates. For new issues, file your bug or
feature request as a new Issue.
For help and questions about using this project, please consult our Wiki or post on our
Discussion forum, both right here on GitHub.
## Microsoft Support Policy
Support for TinyTroupe is limited to the resources listed above.
================================================
FILE: build_and_install_package_from_repo.bat
================================================
pip install build
CALL .\build_package.bat
CALL .\install_package_from_repo.bat
================================================
FILE: build_package.bat
================================================
pip install build
python -m build
================================================
FILE: config.ini
================================================
[OpenAI]
API_TYPE=openai
# Check Azure's documentation for updates here:
# https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart?tabs=command-line&pivots=programming-language-python
# https://learn.microsoft.com/en-us/azure/ai-foundry/openai/api-version-lifecycle?tabs=python
AZURE_API_VERSION=2024-12-01-preview
#
# Model parameters
#
MODEL=gpt-5-mini
MAX_COMPLETION_TOKENS= 128000
TIMEOUT=240
MAX_ATTEMPTS=2
WAITING_TIME=2
EXPONENTIAL_BACKOFF_FACTOR=5
EMBEDDING_MODEL=text-embedding-3-small
AZURE_EMBEDDING_MODEL_API_VERSION=2023-05-15
[Logging]
LOGLEVEL=DEBUG
# ERROR
# WARNING
# INFO
# DEBUG
LOG_INCLUDE_THREAD_ID=True
================================================
FILE: data/empirical/07.17.2025 - Market Research - AI-enabled story telling device or app - Raw Data.csv
================================================
Responder #,Vote,Explanation,Age Range,Gender Identity,Kids Toy Buying Frequency,Hobbies And Interests,Age Of Kids,Parents
1,B-C-D-A-E,i would prefer to just read to my kids or have them read to each other but my next choice would be a device with audio only,25-34,Female,Frequently,Crochet / knitting; Cooking; Health and fitness; Travel; Reading; Boating; Arts and crafts,6-11 years old; 4-5 years old; 0-3 years old,Yes
2,A-D-C-E-B,"I think a single purpose device is very important, I don't want my kids to have any tablets. I'm okay with them having images on the screen as long as it's always related to the story and there are no ads",25-34,Male,Frequently,Photography / videography; Reading; Technology; Hiking; Camping,0-3 years old; 4-5 years old,Yes
3,D-B-A-C-E,"Generally, I think I would prefer the audio only. It creates better opportunities for the child to use their imagination. I don’t want them on a phone or tablet so a single used device would be preferred.",35-44,Male,Sometimes,Camping; Boating; Board/tabletop games; Card collecting; Hiking; Arts and crafts; Health and fitness; Cooking; Reading; Gardening; Interior decorating / renovating,6-11 years old; 12-17 years old; 4-5 years old,Yes
4,B-E-A-C-D,"I have been working a lot in AI . I don't think AI should be introduced to kids just yet since we're still trying to figure a lot of it out , then I'm gonna go with B . Nothing . I would rather not use any AI enabled devices or app for storytelling for my children at this point . ",35-44,Male,Frequently,"Health and fitness; Other; Visiting art galleries, museums, exhibitions; Travel; Reading; Playing music; Photography / videography; Hiking",6-11 years old; 4-5 years old; 0-3 years old,Yes
5,C-E-A-D-B,I chose option C first because I think an app would provide the most reach to customers.,35-44,Male,Frequently,"Reading; Board/tabletop games; Technology; Cooking; Playing music; Health and fitness; Other; Visiting art galleries, museums, exhibitions; Travel",6-11 years old; 4-5 years old,Yes
6,A-D-C-E-B,I think this is a nice way to get them off of their tablets and tvs and help with their imagination. Would also be a great way for parents to catch a breather,35-44,Female,Frequently,Board/tabletop games; Card collecting; Camping; Boating; Arts and crafts; Cooking; Technology; Reading; Playing music; Gardening,12-17 years old; 6-11 years old; 4-5 years old,Yes
7,D-A-C-B-E,"I would be fine with either options D or A. I like that this is an audio only device and I would not have to use a smartphone. This sounds like a very uncomplicated device that would be simple to use and to learn to use. I like the simplicity of the device, that means it would be easy to teach a child how to use it. The simplicity of it is the reason I would buy it ",25-34,Female,Frequently,Boating; Board/tabletop games; Arts and crafts; Health and fitness; Cooking; Camping; Crochet / knitting; Playing music; Watching sports on TV; Technology; Reading,4-5 years old; 6-11 years old; 0-3 years old,Yes
8,A-E-D-C-B,"I prefer option Dedicated single-purpose device(Audio + Images) AI-enabled story-telling device most. It is unlike tablets or phone, it's not cluttered with apps or notifications. Keeps children immersed in storytelling without temptation to browse the internet or watch unrelated videos. My second choice is option E, third choice is option D.",35-44,Male,Frequently,"Visiting art galleries, museums, exhibitions; Photography / videography; Travel; Reading",12-17 years old; 4-5 years old; 6-11 years old,Yes
9,E-C-A-D-B,I choose E first because I can download it on my daughter's tablet and she can play with it and ask for stories she loves them,35-44,Female,Frequently,Hunting / fishing; Reading; Camping; Boating,4-5 years old; 12-17 years old,Yes
10,B-C-E-A-D,I don’t really understand AI and its general concept makes me uncomfortable/ has a negative stigma. I am not complete Opposed to using it with some education.,35-44,Female,Frequently,Cooking; Playing music; Gardening; Reading,6-11 years old; 4-5 years old,Yes
11,A-C-D-E-B,I prefer dedicated device with both image and audio which keeps children engaged and also distraction free. Audio only will be not that engaging.,25-34,Female,Sometimes,Boating; Watching sports on TV; Gardening; Camping; Health and fitness; Reading; Arts and crafts; Playing music; Travel; Photography / videography,6-11 years old; 4-5 years old,Yes
12,B-D-A-C-E,"I'd go with detailed device with audio + visual because it offers the right mix of child independence, learning value, and peace of mind for me as a parent. I want my kids to be creative, but I also want the protected from distractions, and a device that's fun, engaging and safe check all those boxes.",25-34,Male,Frequently,Technology; Gardening; Reading; Watching sports on TV,4-5 years old; 6-11 years old,Yes
13,A-E-C-D-B,I think an AI tool for kids that can use their imagination and create any story they want is amazing 😍 I would choose option A because it's an app that can be used for the phone and that's convenient.,45-54,Female,Sometimes,Reading,4-5 years old,Yes
14,D-E-C-B-A,"I chose D first, because I like my devices or products to be simple to use and not too complex.",55-64,Male,Sometimes,Hiking; Watching sports on TV; Other; Reading,4-5 years old,Yes
15,C-B-D-E-A, Unsure about A.I. at this time. Not sure AI is the best way to do anything as it takes a lot of personal information to use AI ,35-44,Female,Frequently,Playing music; Arts and crafts; Travel; Reading,0-3 years old; 4-5 years old,Yes
16,D-B-E-A-C,"I would entertain a single use device, so I know they aren't dealing with other things on the phone or tablet as well. I would also advise against any images, I would just want it to be a story telling device. I would have a lot of questions for how it would generate stories and what it could and couldn't do. ",35-44,Male,Frequently,Gardening; Travel; Technology; Reading; Playing music; Hiking; Health and fitness; Cooking; Camping,4-5 years old; 6-11 years old,Yes
17,E-C-B-D-A,Truthfully we all have phones at this point and it’s just easier to have an app on your phone. I’d rather do that or no AI at all versus having to pay an extra $500-1000 for a whole other piece of tech that literally only does one thing in the hands of a child. ,35-44,Male,Sometimes,"Visiting art galleries, museums, exhibitions; Travel; Other; Reading",6-11 years old; 4-5 years old,Yes
18,B-A-E-C-D,"Storytime should be a special time between parents and children. When parents aren't involved and being replaced by a device, it's detrimental to the child and society as a whole. I can remember telling my son bedtime stories, making them up on the fly. That is a wonderful tradition I would hate to see be replaced by a machine.",35-44,Male,Sometimes,Card collecting; Board/tabletop games; Camping; Boating; Arts and crafts; Hiking; Gardening; Other; Reading; Playing music; Cooking,4-5 years old,Yes
19,A-D-B-C-E,I like option A because it is creative. I would feel comfortable purchasing this item for my children because I would not have to monitor them as closely as I do when they are using apps or websites. Also with this product I would not have to worry about privacy or my children making unauthorized purchases. I also like that it gives audio and visual information about the story. I would definitely purchase this product for my children. ,45-54,Female,Frequently,Health and fitness; Interior decorating / renovating; Travel; Arts and crafts; Cooking; Reading; Crochet / knitting,4-5 years old; 6-11 years old,Yes
20,B-D-A-E-C,I don't trust AI. I have many security concerns. I don't like apps listening in constantly and knowing all of my information on my phone or tablet.,35-44,Male,Sometimes,Watching sports on TV; Board/tabletop games; Reading; Hiking,4-5 years old; 6-11 years old,Yes
21,E-A-D-B-C,I wouldn’t buy this for my child because he has autism and things like this don’t appeal to him. ,35-44,Female,Frequently,Interior decorating / renovating; Board/tabletop games; Photography / videography; Reading,12-17 years old; 4-5 years old,Yes
22,B-C-D-A-E,I wouldn't want AI to be in charge of telling my kids stories,35-44,Female,Sometimes,Technology; Reading; Playing music; Gardening,0-3 years old; 4-5 years old,Yes
23,C-E-D-A-B,"i would be interested in this option because it offers a balance of affordability, convenience and creative engagement for children.it is better",35-44,Male,Sometimes,Gardening; Watching sports on TV; Reading; Board/tabletop games,6-11 years old; 4-5 years old; 12-17 years old,Yes
24,D-C-E-A-B,"I like the one that doesn't have any apps, just a single button especially for autistic children. sometimes too many buttons can make them overwhelmed so I like this option",25-34,Female,Frequently,"Visiting art galleries, museums, exhibitions; Technology; Reading",4-5 years old; 0-3 years old,Yes
25,A-D-C-E-B,A and D sound the most appealing to me,35-44,Male,Frequently,Board/tabletop games; Card collecting; Camping; Boating; Playing music; Cooking; Technology; Hiking; Reading; Arts and crafts; Health and fitness,0-3 years old; 6-11 years old; 4-5 years old,Yes
26,A-C-D-E-B,"Supporting both audio and images is the first choice. Option A, without any other applications that could interfere, makes me feel more at ease letting my child use it.",25-34,Female,Frequently,Reading; Travel; Card collecting,4-5 years old,Yes
27,C-D-E-A-B,I would buy the product of option C. This one is better than the other three. Being able to interact while the child listens to the story and also see the illustrations is enough to satisfy me. I would buy this for my child. This product can help cultivate my childs interest in reading.,18-24,Female,Frequently,"Reading; Visiting art galleries, museums, exhibitions; Interior decorating / renovating; Photography / videography",4-5 years old,Yes
28,A-D-E-C-B,"My first choice is A because its the most professional device, with both video and audio that allows interaction, and it doesn't require extra supervision. Options D and E lack video features, and C adds a burden on parents since it needs an extra phone. I'm not considering B because it requires additional tools to help my child with reading training.",18-24,Male,Frequently,"Health and fitness; Watching sports on TV; Visiting art galleries, museums, exhibitions; Reading",4-5 years old,Yes
29,A-C-E-D-B,I put Project A in the first place because it fits my child's interests very well and can help my child want to learn better.,55-64,Male,Frequently,Travel; Reading; Cooking,4-5 years old,Yes
30,C-E-D-A-B,"I will choose mobile or tablet applications, which will be more convenient and won't require any additional purchases.",45-54,Female,Frequently,Reading; Photography / videography; Playing music,4-5 years old,Yes
31,D-A-C-E-B,"The reason this product ranks first is that it meets children's needs, is affordable, and is easy to operate.",35-44,Male,Frequently,Technology; Reading,4-5 years old,Yes
32,C-A-E-D-B,"I will buy option C of this product for my child, as it can be easily used by them, which makes me feel more at ease.",55-64,Male,Frequently,Travel; Reading; Hunting / fishing; Photography / videography,4-5 years old,Yes
33,C-E-A-D-B,"My favorite is C because its delivered through a mobile app with comprehensive features, making it very convenient without needing to buy extra equipment. E has fewer features, while A and D require additional devices to meet the needs, which is costly and troublesome. I'm not considering B.",35-44,Female,Frequently,Reading; Gardening; RVing / motor caravanning; Crochet / knitting,4-5 years old,Yes
34,C-D-E-A-B,"I am very satisfied with product C; it allows my child to engage in conversation intelligently, and the smart device can also spark more interest in learning for them.",45-54,Female,Frequently,Hunting / fishing; Crochet / knitting; Reading; Camping,4-5 years old,Yes
35,A-C-B-D-E,"I would choose product A; its functions are very straightforward, and it includes the ability to converse with children, which makes it a great product for helping kids tell stories.",55-64,Male,Frequently,RVing / motor caravanning; Reading; Arts and crafts; Crochet / knitting,4-5 years old,Yes
36,E-C-D-B-A,"I put option E in the first place because it is compatible with tablets and very convenient to use, while I placed option B last because it does not include AI.",45-54,Female,Frequently,Reading,4-5 years old,Yes
37,D-E-C-B-A,"I ranked option D first because it is very portable and convenient for kids to use, while I placed option B in last place because it has too few features.",35-44,Male,Frequently,Reading,4-5 years old,Yes
38,C-D-E-A-B,"C allows for interaction with children, which feels very fun and can effectively improve focus. D's equipment is relatively simple, which can save money well.",25-34,Female,Frequently,Reading; Cooking; Arts and crafts,4-5 years old,Yes
39,C-E-A-D-B,"I would first choose option C because it describes many benefits suitable for children to use independently, has comprehensive features, and is also reasonably priced.",25-34,Female,Sometimes,Cooking; Watching sports on TV; Reading,4-5 years old,Yes
40,C-E-A-D-B,"Using a phone or tablet is quite convenient, and the applications are relatively easy to use; standalone devices are not very practical. Stories with visuals are more likely to capture children's interest.",25-34,Male,Sometimes,Reading; Travel; Camping; Photography / videography,4-5 years old,Yes
41,E-C-A-D-B,"Options E and C are my favorite storytelling devices because smartphones and tablets are common in everyday life and are very convenient to use. Only after that would I consider options D and C, which are specialized storytelling devices. If the budget allows, I would consider purchasing them. Lastly, option B is a bit monotonous for storytelling without any devices.",25-34,Female,Frequently,Reading; Arts and crafts,4-5 years old,Yes
42,A-C-E-D-B,"I will choose to buy Product A. Because compared to other products, it's very easy to use, with only one button to operate, so it's not complicated, and it offers both image and audio features.",55-64,Female,Frequently,Technology; Reading; Gardening; Playing music,12-17 years old; 4-5 years old,Yes
43,A-C-E-D-B,"I put Plan A first in this order because it includes images and audio, which can help my children focus better.",35-44,Male,Frequently,Playing music; Reading; Interior decorating / renovating; Camping,4-5 years old,Yes
44,D-E-B-A-C,"I choose option D; this device has a full range of functions, and it's simple and convenient. The price is quite affordable, and I'm very satisfied.",45-54,Female,Sometimes,Reading; Travel; Crochet / knitting,4-5 years old,Yes
45,D-A-C-E-B,Choosing no other application development is the priority option because I'm concerned that including other apps will lead my child to play with them. I chose D because it is simpler and easier for my child to use.,35-44,Male,Frequently,Reading,0-3 years old; 4-5 years old,Yes
46,A-E-D-C-B,I ranked my choices this way because the 1st one I selected sounds the coolest! It seems simple enough for the kids to be able to turn them on and off.,35-44,Female,Frequently,Playing music; Travel; Reading; Cooking,0-3 years old; 4-5 years old,Yes
47,A-C-E-D-B,"My first choice is A, as it is more professional and has great interactivity. C is my second choice; without visuals, it feels like it would lack focus. Then there's E, which doesn't have good audio advantages and lacks interactivity. D's equipment is very inconvenient and lacks a sense of participation, while B's equipment is incomplete.",55-64,Male,Frequently,Reading; Travel,4-5 years old,Yes
48,E-D-A-C-B,"I would choose Plan E because this plan can cultivate children's communication skills, and children can interrupt the story anytime without needing their parents to supervise.",35-44,Female,Sometimes,Reading; Travel; Photography / videography,6-11 years old; 12-17 years old; 4-5 years old,Yes
49,C-A-E-D-B,"I would choose option C for purchase, as it effectively utilizes the available resources and reduces property damage. Second is A, which is more convenient but lacks focus. E feels better to use and is great for storytelling. D's equipment is a bit expensive and lacks visuals, while B would lack certain knowledge.",35-44,Male,Frequently,Interior decorating / renovating; Reading; Camping,6-11 years old; 4-5 years old,Yes
50,A-C-B-D-E,"My first choice is a dedicated single-use device, as it allows the kids to only listen to stories without being distracted by anything else.",45-54,Female,Frequently,Hiking; Health and fitness; Reading,4-5 years old,Yes
================================================
FILE: data/empirical/07.19.2025 - Market Research - Bottled Gazpacho - Raw Data.csv
================================================
Responder #,Vote,Explanation,Age Range,Gender Identity,Political Affiliation,Racial Or Ethnic Identity
1,4,Yes because it is something i have never tried and willing to give it a go,25-34,Male,Democrat,White
2,1,I HATE soup. Cold soup would be worse.,65+,Female,Democrat,White
3,1,i would not purchase a ready to drink gazpacho because i am not a fan of it.,35-44,Female,Democrat,Black
4,5,"It sounds healthy and if it's ready to drink and doesn't require me to do all that chopping of the vegetables, what's not to like!",55-64,Female,Democrat,White
5,3,"Like most things, I would try it at the right price. I normally don't eat gazpacho though.",35-44,Non-binary,Independent / other,Other
6,4,"Gazpacho was something that I have never tried , but I always wanted to . So I'm going to give it a 4 star , because I'm most likely would give it a great try because I know what it is . I just have never tried it and I'd like the all the ingredients in it . ",55-64,Male,Independent / other,Other
7,2,I'm not a big soup person so this doesn't appeal to me.,25-34,Male,Democrat,Other
8,4,"Very possibly, but I would want to make sure the ingredients look good and that it doesn't contain a bunch of artificial ingredients and preservatives (and the price being not too high would be nice too).",35-44,Male,Independent / other,Hispanic
9,1,"As an American, drinking soup sounds super weird to me.",35-44,Male,Democrat,White
10,1,I do not like the taste of this particular product and never understood why anyone else likes cold soup.,65+,Male,Democrat,White
11,3,I'm not really interested in a cold soup so I probably wouldn't consider this drink unless my friends or family highly recommended it.,45-54,Female,Republican,Black
12,2,I would not buy this ready to drink but might consider it as a meal side.,35-44,Male,Democrat,Black
13,2,It would probably appeal to someone who drinks something similar to a V8 but personally I would not buy this as it doesn't sound appealing at all.,45-54,Female,Republican,Hispanic
14,5,I would most definitely do so because of the convenience,25-34,Male,Independent / other,Asian
15,4,"I'd rate this idea 4 stars. I like fresh, savory options that don't need heating or prep. If the taste holds up, I'd buy it often in warmer months.",25-34,Male,Independent / other,Black
16,3,"I'd be intrigued by a bottled gazpacho, but it would depend on the price and also the freshness. Ideally, I'd want something with a very limited shelf-life and no preservatives. For instance, small batch gazpacho that is re-stocked every week.",35-44,Male,Independent / other,Asian
17,3,"Yes, I would purchase it for my family member.",35-44,Female,Democrat,Hispanic
18,5,I think that this is a fantastic idea. I like the idea because it is completely original and there is nothing available like it in the stores. This would be a product that I would buy regularly because I cannot get it at all now. I would be very happy to think that this would be available to me and it is a product that I would buy all the time,25-34,Female,Republican,White
19,4,I would certainly try it. Gazpacho would fit into my summer meal plans quite well. Taste and ease of use (and price) would determine whether I make it a regular in the dinner rotation.,55-64,Female,Democrat,White
20,2,"likely would not try it ready made in a bottle it just seems strange to have soup in that format, but im open to trying once",25-34,Male,Independent / other,Black
21,3,I've never had a gazpacho before. I would be willing to give it a try depending on the price. I couldn't imagine paying more for it than a v8 or something like that.,35-44,Male,Independent / other,Other
22,5,"This sounds like a quick, easy, delicious, and healthy on the go meal option. ",45-54,Female,Democrat,White
23,3,"I particularly dont like cold tomatoe products. i stray from acidic drinks
",25-34,Female,Independent / other,White
24,3,"I propensity to purchase ready-to-drink bottled gazpacho is 3 out of 5. If it wasn't too expensive, I would try it at least once. But I would only try it during the summer.
I'm concerned about the quality of the product. It shouldn't taste like tomato juice or V8. ",55-64,Male,Independent / other,White
25,5,Yes I would try it if the price were under $2 a can.,35-44,Male,Republican,White
26,1,"I don't care for gazpacho, so I would not purchase this drink.",45-54,Female,Democrat,Hispanic
27,3,I love gazpacho but usually my wife or friends make it. I’m not too sure about buying it at the market. Maybe if I knew it was fresh I would.,35-44,Male,Democrat,White
28,4,I’ve never had gazpacho but it sounds delightful. I work in an office 3 days a week so this may be something I pickup to have an easy lunch if I am pressed for time,35-44,Male,Republican,Hispanic
29,3,"At first I put down a 1 star or no answer, but then the more I thought about it, the more it would be like getting a V8. Which is ALMOST the same thing.",35-44,Male,Democrat,Asian
30,1,"I would never purchase this since gazpacho is a cold soup and you eat it, it isn't a drink that comes from a bottle. If you are marketing a soup then phrase it as a packaged, easy to dispense cold soup. Gazpacho is not blended and is served with hearty ingredients and never blended. It sounds like you are making a vegetable juice so just market it that way and say it's gazpacho flavor.",55-64,Female,Democrat,White
31,1,"Probably a very healthy drink; however, I can't get used to the idea of drinking gazpacho (I like eating it, however, and I am assuming that this drink is a blended mixture).",55-64,Male,Independent / other,White
32,4,"When you say ""drink"" it sounds odd, it is supposed to be eaten as a cold soup. I would go for it if it would taste delicious and price was right. But maybe not market it as ""ready to drink"" but rather ready to ""consume"".",35-44,Female,Republican,Black
33,3,"Sorry, I personally would not like to drink anything like this. If it would something to use as an ingredient in cooking it would be great and something to keep on hand.",65+,Female,Democrat,Other
34,3,I have not tried it so I do not know if I like it. I would try it at least once.,25-34,Male,Independent / other,White
35,2,"I gave a 2-star rating because it's highly unlikely that I would buy it but I wouldn't rule it out completely, I could potentially see myself buying one to try it because I've never had gazpacho before. I do like the ingredients in it but I don't like cold soup and that is the main thing that turns me off and makes me not want to eat it. And I do really like that it's ready-to-drink because that makes it very easy to have it anywhere and anytime that you want and you don't have to worry about having a bowl to put it in.",45-54,Male,Independent / other,Black
36,1,I feel like this is not a product that people would want to take on the go. This is something that should be enjoyed sitting down.,45-54,Male,Democrat,Hispanic
37,4,"I don not consume gazpacho on a regular basis, but I've had it before and I would try it again.",65+,Male,Republican,White
38,3,It sounds very flavorful so I would be potentially interested.,45-54,Male,Republican,Other
39,4,"I love gazpacho, but I am trying to quit oils, so I gave it 4 stars. My family members would probably not mind the olive oil, though. ",55-64,Female,Republican,Asian
40,2,"I mean, I like gazpacho so I think there's a > 0 chance I'd try it out once, but I have 0 faith that it would be good enough to actually have regularly. Premade bottled ready to drink soup just seems a step too far.",35-44,Male,Independent / other,Black
41,1,I give it a 1 out of 5 stars because I don’t like gazpacho.,35-44,Female,Democrat,Asian
42,1,"I would not consider it. I don't drink gazpacho, so I don't see that I would ever buy such a product in the store.",45-54,Male,Independent / other,Other
43,2,I could see where some people might like this but it sounds disgusting for me and I would never buy it. ,35-44,Female,Republican,White
44,1,"I don't really like gazpacho so I don't think I'd ever buy this kind of product. But if I did like this, I would definitely consider buying some",35-44,Male,Independent / other,White
45,2,I don't think I would be interested in this as a ready to drink option. I would be worried about its quality. ,45-54,Male,Democrat,Black
46,5,"I've never had it before, but the ingredients sound good to me, and I'm all about convenience, so ready-to-drink is perfect. This, of course, all depends on the price.",65+,Female,Democrat,White
47,2,"No chance, I could not drink a cold tomato based drink. To me that personally does not seem very appetizing.",35-44,Male,Republican,White
48,4,"i have had gazpacho and believe it is one of the staple dishes of last 200 years but theres a decorum to it ro me personally, a bottled version does not seem so appetizing but maybe a younger first timer might enjoy.",55-64,Male,Republican,White
49,3,"This doesn't stand out to me, I may or may not try it if I saw it on a shelf.",35-44,Male,Republican,White
50,5,"Yes, I love gazpacho and have never seen a ready made version of this so I would definitely try it. ",25-34,Female,Democrat,Hispanic
================================================
FILE: data/extractions/appartment_rent_ad.extraction.json
================================================
{
"agent_extractions": {},
"world_extraction": {
"Focus group": {
"ad_copy": "Discover a spacious, modern apartment with integrated living spaces and a dedicated home office\u2014perfect for remote work or study. Recently renovated and fully furnished with quality appliances and tasteful decor, this quiet retreat is located at the back of a main avenue building. Enjoy proximity to the country's top Medicine School, supermarkets, gyms, public transport, and popular dining spots. Ideal for medical students and young professionals seeking convenience and comfort. High-quality photos and a virtual tour are available. Find us on university bulletin boards, social media groups, local community boards, and popular rental websites in S\u00e3o Paulo. Move in hassle-free and experience the perfect blend of style and practicality."
}
}
}
================================================
FILE: data/extractions/appartment_rent_ad_1.extraction.json
================================================
{
"agent_extractions": {
"Lisa": [
{
"main_point": "To advertise Paulo's apartment effectively, we should highlight its unique features and benefits."
},
{
"main_point": "The spacious, open-concept design, the recent renovations, and the proximity to key amenities are all strong selling points."
},
{
"main_point": "The apartment's suitability for medical students due to its location near the best Medicine School should be emphasized."
},
{
"main_point": "We should create a listing that emphasizes the apartment's modern and open design, its recent upgrades, and the convenience of the location."
},
{
"main_point": "High-quality photos that showcase the spacious rooms and elegant kitchen should be used."
},
{
"main_point": "The proximity to the Medicine School could attract medical students looking for a quiet and comfortable place to live."
},
{
"main_point": "We could post the ad on popular rental websites and perhaps even reach out to the student community directly."
},
{
"main_point": "Professional photos are a must to highlight the visual appeal of the apartment."
},
{
"main_point": "The included amenities like the new washing machine that doubles as a dryer, and the fully furnished aspect, are a huge plus."
},
{
"main_point": "Creating a virtual tour to allow potential tenants to experience the space online is quite popular nowadays."
},
{
"main_point": "We should consider the timing of the listing to ensure maximum visibility."
},
{
"main_point": "Synchronizing the listing with the academic calendar, targeting medical students at the beginning of a semester, could be effective."
},
{
"main_point": "We could advertise the apartment on platforms frequented by medical students and young professionals."
},
{
"main_point": "Social media groups, medical school forums, and even local community boards could be effective."
},
{
"main_point": "Offering a virtual Q&A session for interested tenants to ask questions in real-time provides a personal touch and builds trust."
},
{
"main_point": "We could use a mix of traditional and digital marketing strategies to reach a wider audience."
},
{
"main_point": "Offering a special incentive for medical students, like a discount on the first month's rent, to make the offer more appealing."
},
{
"main_point": "Combining social media advertising with the virtual tour could really maximize our reach."
},
{
"main_point": "A content calendar for our advertising efforts to ensure we're posting at optimal times could be beneficial."
},
{
"main_point": "All our marketing materials should communicate the special offers clearly."
}
]
},
"world_extraction": {
"Focus group": {
"ad_copy": "Discover modern living in a newly renovated space where elegance meets convenience. Step into a world of open-concept design with spacious integrated areas, perfect for the urban dweller who appreciates style and freedom. Freshly repainted and boasting a chic kitchen with a central wood table, this one-bedroom apartment, originally two, now features a dedicated home office for your work-from-home needs. Located in a classic building near the best Medicine School, it's ideal for medical students seeking a serene study environment. Enjoy the ease of a fully furnished home, complete with a new washing machine that doubles as a dryer. Experience the apartment through a virtual tour and take advantage of our special offer for medical students. Connect with us during a live virtual Q&A session. Your perfect urban retreat awaits, aligning with the academic calendar for maximum convenience. Don't miss out on this unique opportunity for sophisticated and hassle-free living."
}
}
}
================================================
FILE: data/extractions/synthetic_data_generation.out.csv
================================================
author,content
USER,"Get some work done together, help each other."
Marina Ellsworth,"Sounds good — I’m up for a focused co-working session. Quick proposal: a 90‑minute block (or 2×45 Pomodoros) with this agenda: 1) pick 1–2 priority tasks and clarify the desired outcome, 2) pair on the highest‑priority/hardest item for the first 45–60 minutes, 3) 10–15 minute check‑in to capture decisions and next steps. I can help draft requirements, map acceptance criteria, clean or outline data steps, review text, or sketch next actions. What would you like to work on first, and do you prefer 90 minutes or two 45‑minute rounds? If that works, I’ll open a shared doc and set a timer."
Natalia Carmichael,"Yes — I'd love to. First we will do a quick 5-minute check-in to agree priorities. Then we will do a focused work block (I suggest 25 minutes with a 5-minute break, then a second 25-minute block) — that usually helps me stay on task. My priorities right now are grading a stack of lab reports and finalising a Monday diffusion/osmosis lesson; either of those would be great to tackle together. I can open a shared Google Doc or my Canvas folder and share the rubric so we can work in parallel. Does that plan suit you? Which task would you prefer to start with, and do you prefer 25/5 Pomodoros or a single 50-minute block?"
Marina Ellsworth,"Sounds great — I like the 5‑minute check‑in + 25/5/25 rhythm. I suggest we start with finalizing your Monday diffusion/osmosis lesson (time‑sensitive), unless you’d rather begin with the grading stack. Proposed plan for the first 25‑minute block (I can take the lead drafting these):
1) Confirm 1–2 clear learning objectives for Monday (what students should be able to DO).
2) Sketch a 15–20 minute core activity (hands‑on demo or guided simulation) and a 5‑minute exit ticket question to assess learning.
3) Make a short materials/tech checklist and a note about accessibility/accommodations.
4) Jot a very brief teacher script/slide notes and any quick formative assessment items.
After the first 25 minutes we’ll take the 5‑minute break, then use the second 25‑minute block to refine the activity, turn the exit ticket into an assessment item, or switch to grading if you prefer.
Practicals: do you want me to open a Google Doc, or will you share a Canvas page? If Google Doc works, I can create an outline and paste in a quick template; if you prefer Canvas, please share the link. Once you share, I’ll start a 5‑minute check‑in (confirm the single priority and roles) and then start the first 25‑minute timer."
Natalia Carmichael,"Lovely — that plan suits me. First we will do a 90-minute block made of two focused 45-minute rounds, then a 10–15 minute check-in to capture decisions and next steps. My suggestion for priorities: start with grading the lab reports (they're the most urgent), then use the second 45 to finalise Monday's diffusion/osmosis lesson. Acceptance criteria so we're aligned: for grading, I'll aim for a first-pass on ~20 reports with my three-bullet feedback structure (praise, one improvement, next step) or at least complete the first pass on the stack and flag any tricky ones; for the lesson, I'd like finished slides, a materials list, and a short exit ticket uploaded to Canvas. Could you open a shared Google Doc and set a 45-minute timer to start? I can paste my rubric from Canvas into the doc and work in parallel — would you prefer to draft comments while I skim for trends, or should we split by batches and swap responsibility after the first round?"
Marina Ellsworth,"That plan sounds good — I can do the Google Doc and kick off the first 45-minute timer. My suggested workflow to keep us coordinated: 1) You paste the rubric at the top of the doc and flag any reports you already see as tricky. 2) I’ll draft the three-bullet feedback (praise, one improvement, next step) for roughly the first ~10 reports while you skim for trends and paste any global notes. 3) At the 45-minute mark we’ll do a quick 3–5 minute check-in in the doc: capture tricky ones, swap batches if needed, or finish the pass. That should get you a solid first pass on the stack; if the pile is larger we can adjust in the midpoint. I’ll create the doc now and share the link here — do you want me to name the doc “Lab grading — first pass [date]” and start the timer when you confirm? "
Natalia Carmichael,"Lovely — the 25/5/25 rhythm suits me and I agree we should start with the Monday diffusion/osmosis lesson. First, can you open a Google Doc and share the link? I’ll paste the Canvas rubric into it so we have the success criteria visible. Roles for the first 25-minute block: please take the lead drafting the 15–20 minute core activity (hands-on demo or guided simulation) and a provisional materials/tech checklist; I’ll draft 1–2 clear learning objectives, note accessibility/accommodations, and add a brief teacher script/slide notes. Acceptance criteria for the first 25: agreed learning objectives, a sketched core activity, and a materials checklist (flag any missing or tricky supplies). Then in the second 25-minute block I’ll turn the exit ticket into a formative assessment item and assemble 3–6 slides + a short teacher script while you refine the activity and check logistics. Finally, we’ll use the short check-in after both blocks to capture decisions and upload the exit ticket/slides to Canvas. Ready for you to open the Doc and start a 5-minute check-in/timer?"
Marina Ellsworth,"Ready — I will open a Google Doc now and share the link here. I'll name it ""Diffusion_Osmosis_Monday_2026-01-25"" and paste a short outline that includes: 1) a 5-minute check-in note, 2) roles (I draft the 15–20-minute core activity + materials/tech checklist; you draft 1–2 learning objectives, accessibility notes, and teacher script), 3) acceptance criteria for the first 25 (agreed objectives, sketched core activity, materials checklist), and 4) the 25/5/25 timer plan. After I post the link, I’ll start the 5-minute check-in timer. Do you want me to give you edit access (preferred) or view-only? Any quick notes to add before I create the doc?"
Natalia Carmichael,"Lovely — that sounds perfect. Yes, please name the doc ""Lab grading u000du000a— first pass 2026-01-25"" (or similar) and share the link when it's ready; start the timer when you confirm. First, I'll paste the Canvas rubric at the top and flag any reports I already see as tricky. I'll skim for trends while you draft the three-bullet feedback for the first ~10 reports (praise, one improvement, next step). Acceptance criteria for this first pass: aim to complete a first-pass on the stack (rough target ~20 reports) with three-bullet feedback or at least finish the portion we agree on and flag tricky ones for a second pass. One quick preference question: do you want the three-bullet comments inline beneath each report, or in a separate 'Feedback' column so we can filter/sort? Either is fine with me — tell me which you prefer and then start the timer."
Marina Ellsworth,"Thanks — I prefer a separate 'Feedback' column (easier to filter/sort and export). I'll create a shared doc now titled ""Lab grading u00096u00096 first pass 2026-01-25"" (or I can make a Google Sheet if you want strict columns). Proposed structure: Report ID | Student name | Link to report | Feedback (three bullets: praise, one improvement, next step) | Flag (tricky) | Notes. Workflow: you paste the Canvas rubric at the top and flag any tricky ones; I'll take roughly the first ~10 reports and draft the three-bullet feedback in the Feedback column while you skim for trends. At the 45-minute mark we'll do a 3–5 minute check-in and swap or continue as needed. Quick question: do you want me to also add inline comments directly in the original reports, or keep feedback only in the table to avoid duplication? If that sounds good, confirm whether you prefer a Doc (table) or a Sheet, paste the rubric, and I will start the timer as soon as you say go and give me edit access."
Natalia Carmichael,"Lovely — please give me edit access (that will be easiest). The document name you suggested is fine. Quick notes: First, paste the Canvas rubric at the top and I will add my copy as well so success criteria are visible. Then, could you add a short 'Feedback' column (rather than burying comments inline) so we can sort and filter the three-bullet feedback easily? Please also flag any reports you already think are tricky and list any materials that might need department approval or a substitute. Finally, start the 5-minute check-in timer when you share the link and I’ll join and paste my accessibility notes and learning-objective suggestions. Ready when you are — thank you!"
================================================
FILE: data/extractions/wordprocessor/Document/Lisa Carter - Resume.Lisa Carter.json
================================================
{
"title": "Lisa Carter - Resume",
"content": "# Lisa Carter\n\n---\n\n## Contact Information\n\n- **Location:** United States of America (USA) \n- **Nationality:** Canadian \n- **Email:** lisa.carter.datasci@gmail.com \n- **Phone:** +1 (555) 123-4567 \n- **LinkedIn:** linkedin.com/in/lisacarterdatasci \n- **GitHub:** github.com/lisacarterds \n\n---\n\n## Professional Summary\n\nLisa Carter is a highly skilled Data Scientist with a Master\u2019s degree in Data Science from the University of Toronto. She specializes in enhancing search relevance through the development and deployment of context-aware machine learning models. With over four years of professional experience, Lisa has a proven track record of analyzing complex user behavior and feedback data to significantly improve the quality and accuracy of search results in large-scale enterprise environments.\n\nHer expertise spans natural language understanding (NLU), query expansion techniques, and ranking algorithms, with a strong focus on building scalable, reliable, and ethically responsible AI systems. Lisa is adept at navigating challenges such as noisy, biased, or incomplete data, while ensuring strict compliance with privacy and security policies. She is a collaborative team player who thrives in cross-functional environments, mentoring junior colleagues and contributing to code quality and performance improvements.\n\nLisa is passionate about leveraging AI technologies to enhance human productivity and decision-making, with a particular interest in conversational agents and search engine optimization. She combines technical proficiency with excellent communication skills, enabling her to translate complex data science concepts into actionable insights for diverse stakeholders.\n\n---\n\n## Education\n\n| Degree | Institution | Year Completed | Details |\n|-------------------------------|----------------------|----------------|-------------------------------------------------------------------------------------------|\n| Master of Science in Data Science | University of Toronto | 2018 | Thesis: *Improving Search Relevance Using Context-Aware Models* |\n| Postgraduate Internship | Conversational AI Startup | 2017 | Focused on developing dialogue management systems and intent recognition for chatbots |\n\n### Academic Highlights\n\n- **Master\u2019s Thesis:** \n Lisa\u2019s thesis explored innovative methods to improve search relevance by incorporating contextual signals such as user intent, session history, and semantic understanding. She designed and evaluated several context-aware ranking models that outperformed traditional keyword-based approaches by 15-20% in relevance metrics.\n\n- **Coursework:** \n - Advanced Machine Learning \n - Natural Language Processing \n - Big Data Analytics \n - Statistical Inference and Modeling \n - Data Visualization and Communication \n\n- **Internship Experience:** \n During her postgraduate internship at a tech startup specializing in conversational AI, Lisa contributed to building intent classification models and dialogue flow optimizations, gaining hands-on experience with real-time user interaction data and reinforcement learning techniques.\n\n---\n\n## Work Experience\n\n### Data Scientist, Microsoft \u2013 M365 Search Team \n*June 2018 \u2013 Present* \nRedmond, WA, USA\n\n#### Key Responsibilities:\n\n- **User Behavior and Feedback Analysis:** \n Conducted in-depth analysis of large-scale user interaction logs and explicit feedback to identify pain points and opportunities for improving search relevance and user satisfaction. Utilized A/B testing frameworks to validate model improvements.\n\n- **Machine Learning Model Development:** \n Designed, implemented, and fine-tuned machine learning models for various search-related tasks, including: \n - **Natural Language Understanding (NLU):** Developed models to parse and interpret user queries, extracting intent and entities to improve query comprehension. \n - **Query Expansion:** Created algorithms to automatically expand user queries with semantically related terms, improving recall without sacrificing precision. \n - **Ranking:** Built and optimized ranking models that combine multiple features such as textual relevance, user context, and historical click data to deliver personalized and accurate search results.\n\n- **Data Quality and Compliance:** \n Addressed challenges related to noisy, biased, and incomplete data by implementing robust data cleaning pipelines and bias mitigation strategies. Ensured all data handling and model deployment complied with Microsoft\u2019s privacy and security policies, including GDPR and CCPA regulations.\n\n- **Cross-Functional Collaboration:** \n Worked closely with software engineers, UX designers, product managers, and data engineers to debug issues, brainstorm innovative solutions, and integrate models into production systems. Participated in sprint planning and agile ceremonies to align on project goals.\n\n- **Mentorship and Code Review:** \n Mentored junior data scientists and interns, providing guidance on best practices in data science and machine learning. Conducted thorough code reviews focusing on performance optimization, readability, and maintainability.\n\n#### Achievements:\n\n- Improved search relevance metrics by 18% through the deployment of a novel context-aware ranking model. \n- Led a project to integrate user session context into query understanding, resulting in a 12% increase in user engagement metrics. \n- Developed a scalable data pipeline for real-time feedback ingestion, reducing model retraining latency by 30%. \n\n---\n\n## Skills\n\n| Category | Skills and Tools |\n|--------------------|--------------------------------------------------------------------------------------------------|\n| **Programming** | Python (advanced), SQL (intermediate), Power BI (intermediate), R (basic) |\n| **Machine Learning** | pandas, scikit-learn, TensorFlow, Azure Machine Learning, XGBoost, LightGBM |\n| **Data Analysis** | Data wrangling, exploratory data analysis, statistical modeling, handling noisy/ambiguous data |\n| **Natural Language Processing** | Text preprocessing, tokenization, word embeddings (Word2Vec, GloVe), transformer models (BERT) |\n| **Visualization** | Matplotlib, Seaborn, Power BI, Tableau |\n| **Communication** | Technical writing, presentations, cross-team collaboration, mentoring |\n\n---\n\n## Interests and Activities\n\n- **Artificial Intelligence and Machine Learning:** \n Enthusiastic about advancements in natural language processing, conversational agents, and ethical AI. Regularly participates in AI conferences and workshops.\n\n- **Search Engine Optimization (SEO) and User Experience:** \n Passionate about improving search algorithms and user interfaces to create seamless and intuitive search experiences.\n\n- **Culinary Arts:** \n Enjoys experimenting with new recipes, exploring diverse cuisines, and watching cooking shows and food documentaries. Frequently hosts dinner parties to share culinary creations with friends and family.\n\n- **Music:** \n Plays piano as a form of relaxation and creative expression. Has performed in local community events and enjoys exploring classical and contemporary pieces.\n\n- **Film and Entertainment:** \n Avid movie watcher with a preference for comedies and thrillers. Enjoys analyzing storytelling techniques and cinematography.\n\n---\n\n## Personal Attributes\n\n- **Curious and Analytical:** \n Approaches problems with a strong analytical mindset and persistence, always seeking to understand root causes and develop effective solutions.\n\n- **Collaborative Team Player:** \n Values open communication, knowledge sharing, and continuous learning within teams. Supports colleagues and fosters a positive work environment.\n\n- **Organized and Detail-Oriented:** \n Maintains a clean and efficient workspace, takes meticulous notes during meetings, and follows structured workflows to ensure accuracy and reliability.\n\n- **Ethical and Responsible:** \n Committed to the ethical use of data and AI technologies, prioritizing user privacy, data security, and fairness in all projects.\n\n---\n\n## Selected Projects\n\n### 1. Context-Aware Search Ranking Model\n\n- **Objective:** Improve search result relevance by incorporating user context such as previous queries, session behavior, and user profile data. \n- **Approach:** Developed a hybrid ranking model combining traditional BM25 scoring with neural network-based context embeddings. \n- **Outcome:** Achieved a 20% improvement in click-through rate (CTR) and a 15% reduction in bounce rate on search results pages.\n\n### 2. Query Expansion Using Semantic Similarity\n\n- **Objective:** Enhance recall in search by expanding user queries with semantically related terms without degrading precision. \n- **Approach:** Leveraged word embeddings and clustering algorithms to identify relevant expansion terms dynamically. \n- **Outcome:** Increased search coverage by 25% while maintaining user satisfaction scores.\n\n### 3. Real-Time Feedback Integration Pipeline\n\n- **Objective:** Reduce latency between user feedback collection and model retraining to enable rapid iteration and improvement. \n- **Approach:** Designed a scalable data ingestion and processing pipeline using Azure Data Factory and Azure ML services. \n- **Outcome:** Reduced model update cycle from weekly to daily, accelerating feature deployment and bug fixes.\n\n---\n\n## Publications and Presentations\n\n- Carter, L. (2018). *Improving Search Relevance Using Context-Aware Models*. University of Toronto Master\u2019s Thesis. \n- Speaker at Microsoft AI Summit 2022: \u201cLeveraging Contextual Signals for Enhanced Enterprise Search.\u201d \n- Contributor to internal Microsoft whitepaper on ethical AI practices in search technologies.\n\n---\n\n## References\n\nAvailable upon request.\n\n---\n\nThis comprehensive profile highlights Lisa Carter\u2019s extensive expertise, professional experience, and personal qualities that make her a valuable asset in the field of data science, particularly in search relevance and natural language processing.",
"author": "Lisa Carter"
}
================================================
FILE: data/extractions/wordprocessor/Document/Lisa Carter - Resume.Lisa Carter.md
================================================
# Lisa Carter
---
## Contact Information
- **Location:** United States of America (USA)
- **Nationality:** Canadian
- **Email:** lisa.carter.datasci@gmail.com
- **Phone:** +1 (555) 123-4567
- **LinkedIn:** linkedin.com/in/lisacarterdatasci
- **GitHub:** github.com/lisacarterds
---
## Professional Summary
Lisa Carter is a highly skilled Data Scientist with a Master’s degree in Data Science from the University of Toronto. She specializes in enhancing search relevance through the development and deployment of context-aware machine learning models. With over four years of professional experience, Lisa has a proven track record of analyzing complex user behavior and feedback data to significantly improve the quality and accuracy of search results in large-scale enterprise environments.
Her expertise spans natural language understanding (NLU), query expansion techniques, and ranking algorithms, with a strong focus on building scalable, reliable, and ethically responsible AI systems. Lisa is adept at navigating challenges such as noisy, biased, or incomplete data, while ensuring strict compliance with privacy and security policies. She is a collaborative team player who thrives in cross-functional environments, mentoring junior colleagues and contributing to code quality and performance improvements.
Lisa is passionate about leveraging AI technologies to enhance human productivity and decision-making, with a particular interest in conversational agents and search engine optimization. She combines technical proficiency with excellent communication skills, enabling her to translate complex data science concepts into actionable insights for diverse stakeholders.
---
## Education
| Degree | Institution | Year Completed | Details |
|-------------------------------|----------------------|----------------|-------------------------------------------------------------------------------------------|
| Master of Science in Data Science | University of Toronto | 2018 | Thesis: *Improving Search Relevance Using Context-Aware Models* |
| Postgraduate Internship | Conversational AI Startup | 2017 | Focused on developing dialogue management systems and intent recognition for chatbots |
### Academic Highlights
- **Master’s Thesis:**
Lisa’s thesis explored innovative methods to improve search relevance by incorporating contextual signals such as user intent, session history, and semantic understanding. She designed and evaluated several context-aware ranking models that outperformed traditional keyword-based approaches by 15-20% in relevance metrics.
- **Coursework:**
- Advanced Machine Learning
- Natural Language Processing
- Big Data Analytics
- Statistical Inference and Modeling
- Data Visualization and Communication
- **Internship Experience:**
During her postgraduate internship at a tech startup specializing in conversational AI, Lisa contributed to building intent classification models and dialogue flow optimizations, gaining hands-on experience with real-time user interaction data and reinforcement learning techniques.
---
## Work Experience
### Data Scientist, Microsoft – M365 Search Team
*June 2018 – Present*
Redmond, WA, USA
#### Key Responsibilities:
- **User Behavior and Feedback Analysis:**
Conducted in-depth analysis of large-scale user interaction logs and explicit feedback to identify pain points and opportunities for improving search relevance and user satisfaction. Utilized A/B testing frameworks to validate model improvements.
- **Machine Learning Model Development:**
Designed, implemented, and fine-tuned machine learning models for various search-related tasks, including:
- **Natural Language Understanding (NLU):** Developed models to parse and interpret user queries, extracting intent and entities to improve query comprehension.
- **Query Expansion:** Created algorithms to automatically expand user queries with semantically related terms, improving recall without sacrificing precision.
- **Ranking:** Built and optimized ranking models that combine multiple features such as textual relevance, user context, and historical click data to deliver personalized and accurate search results.
- **Data Quality and Compliance:**
Addressed challenges related to noisy, biased, and incomplete data by implementing robust data cleaning pipelines and bias mitigation strategies. Ensured all data handling and model deployment complied with Microsoft’s privacy and security policies, including GDPR and CCPA regulations.
- **Cross-Functional Collaboration:**
Worked closely with software engineers, UX designers, product managers, and data engineers to debug issues, brainstorm innovative solutions, and integrate models into production systems. Participated in sprint planning and agile ceremonies to align on project goals.
- **Mentorship and Code Review:**
Mentored junior data scientists and interns, providing guidance on best practices in data science and machine learning. Conducted thorough code reviews focusing on performance optimization, readability, and maintainability.
#### Achievements:
- Improved search relevance metrics by 18% through the deployment of a novel context-aware ranking model.
- Led a project to integrate user session context into query understanding, resulting in a 12% increase in user engagement metrics.
- Developed a scalable data pipeline for real-time feedback ingestion, reducing model retraining latency by 30%.
---
## Skills
| Category | Skills and Tools |
|--------------------|--------------------------------------------------------------------------------------------------|
| **Programming** | Python (advanced), SQL (intermediate), Power BI (intermediate), R (basic) |
| **Machine Learning** | pandas, scikit-learn, TensorFlow, Azure Machine Learning, XGBoost, LightGBM |
| **Data Analysis** | Data wrangling, exploratory data analysis, statistical modeling, handling noisy/ambiguous data |
| **Natural Language Processing** | Text preprocessing, tokenization, word embeddings (Word2Vec, GloVe), transformer models (BERT) |
| **Visualization** | Matplotlib, Seaborn, Power BI, Tableau |
| **Communication** | Technical writing, presentations, cross-team collaboration, mentoring |
---
## Interests and Activities
- **Artificial Intelligence and Machine Learning:**
Enthusiastic about advancements in natural language processing, conversational agents, and ethical AI. Regularly participates in AI conferences and workshops.
- **Search Engine Optimization (SEO) and User Experience:**
Passionate about improving search algorithms and user interfaces to create seamless and intuitive search experiences.
- **Culinary Arts:**
Enjoys experimenting with new recipes, exploring diverse cuisines, and watching cooking shows and food documentaries. Frequently hosts dinner parties to share culinary creations with friends and family.
- **Music:**
Plays piano as a form of relaxation and creative expression. Has performed in local community events and enjoys exploring classical and contemporary pieces.
- **Film and Entertainment:**
Avid movie watcher with a preference for comedies and thrillers. Enjoys analyzing storytelling techniques and cinematography.
---
## Personal Attributes
- **Curious and Analytical:**
Approaches problems with a strong analytical mindset and persistence, always seeking to understand root causes and develop effective solutions.
- **Collaborative Team Player:**
Values open communication, knowledge sharing, and continuous learning within teams. Supports colleagues and fosters a positive work environment.
- **Organized and Detail-Oriented:**
Maintains a clean and efficient workspace, takes meticulous notes during meetings, and follows structured workflows to ensure accuracy and reliability.
- **Ethical and Responsible:**
Committed to the ethical use of data and AI technologies, prioritizing user privacy, data security, and fairness in all projects.
---
## Selected Projects
### 1. Context-Aware Search Ranking Model
- **Objective:** Improve search result relevance by incorporating user context such as previous queries, session behavior, and user profile data.
- **Approach:** Developed a hybrid ranking model combining traditional BM25 scoring with neural network-based context embeddings.
- **Outcome:** Achieved a 20% improvement in click-through rate (CTR) and a 15% reduction in bounce rate on search results pages.
### 2. Query Expansion Using Semantic Similarity
- **Objective:** Enhance recall in search by expanding user queries with semantically related terms without degrading precision.
- **Approach:** Leveraged word embeddings and clustering algorithms to identify relevant expansion terms dynamically.
- **Outcome:** Increased search coverage by 25% while maintaining user satisfaction scores.
### 3. Real-Time Feedback Integration Pipeline
- **Objective:** Reduce latency between user feedback collection and model retraining to enable rapid iteration and improvement.
- **Approach:** Designed a scalable data ingestion and processing pipeline using Azure Data Factory and Azure ML services.
- **Outcome:** Reduced model update cycle from weekly to daily, accelerating feature deployment and bug fixes.
---
## Publications and Presentations
- Carter, L. (2018). *Improving Search Relevance Using Context-Aware Models*. University of Toronto Master’s Thesis.
- Speaker at Microsoft AI Summit 2022: “Leveraging Contextual Signals for Enhanced Enterprise Search.”
- Contributor to internal Microsoft whitepaper on ethical AI practices in search technologies.
---
## References
Available upon request.
---
This comprehensive profile highlights Lisa Carter’s extensive expertise, professional experience, and personal qualities that make her a valuable asset in the field of data science, particularly in search relevance and natural language processing.
================================================
FILE: data/extractions/wordprocessor/Document/Resume of Lisa Carter.Lisa Carter.json
================================================
{
"title": "Resume of Lisa Carter",
"content": "```\n# Lisa Carter\n\n## Contact Information\n- **Email:** lisa.carter@example.com\n- **Phone:** (123) 456-7890\n- **LinkedIn:** [linkedin.com/in/lisacarter](https://linkedin.com/in/lisacarter)\n- **Location:** Toronto, Ontario, Canada\n\n## Summary\nLisa Carter is a highly skilled Data Scientist with a Master's degree in Data Science from the prestigious University of Toronto. With a specialization in improving search relevance through innovative context-aware models, Lisa has a proven track record of analyzing user behavior and feedback data to significantly enhance search results. Her passion for advancing artificial intelligence technology is matched by her commitment to improving human productivity and decision-making processes. Lisa is known for her analytical mindset, problem-solving abilities, and collaborative spirit, making her a valuable asset to any team.\n\n## Education\n### University of Toronto\n- **Master's in Data Science** \n - **Thesis:** Improving Search Relevance Using Context-Aware Models \n - **Graduated:** 2018 \n - **Relevant Coursework:** \n - Machine Learning \n - Data Mining \n - Statistical Analysis \n - Natural Language Processing \n - Big Data Technologies \n - **Projects:** \n - Developed a predictive model for user engagement based on historical data, achieving a 30% increase in accuracy over previous models.\n\n### Bachelor of Science in Computer Science\n- **University of Toronto** \n - **Graduated:** 2016 \n - **Key Achievements:** \n - Dean's List for three consecutive years \n - Completed a capstone project on developing a web application for data visualization.\n\n## Work Experience\n### Microsoft, M365 Search Team \n**Data Scientist** \n2018 - Present \n- **Key Responsibilities:** \n - Analyzed user behavior and feedback data to improve search relevance and quality, leading to a 25% increase in user engagement metrics. \n - Built and tested machine learning models for natural language understanding, query expansion, and ranking, resulting in a 20% improvement in search accuracy. \n - Collaborated with cross-functional teams, including product managers, engineers, and UX designers, to address challenges related to noisy or biased data, ensuring a seamless user experience. \n - Ensured compliance with privacy and security policies in all data handling processes, maintaining the highest standards of data integrity and confidentiality. \n - Conducted A/B testing to evaluate the effectiveness of new features and algorithms, providing data-driven recommendations for product enhancements.\n\n### Intern, Data Analytics Team \n**XYZ Corporation** \n2017 - 2018 \n- Assisted in the development of data-driven strategies to optimize marketing campaigns, resulting in a 15% increase in conversion rates. \n- Conducted exploratory data analysis to identify trends and patterns in customer behavior, presenting findings to senior management. \n- Collaborated with the IT department to streamline data collection processes, improving data accuracy and accessibility.\n\n## Skills\n- **Programming Languages:** \n - Proficient in Python, with extensive experience in data analysis and machine learning tools such as pandas, scikit-learn, TensorFlow, and Azure ML. \n - Familiar with SQL for database management and data manipulation. \n - Basic knowledge of R for statistical analysis and data visualization.\n\n- **Data Visualization Tools:** \n - Proficient in Power BI for creating interactive dashboards and reports. \n - Experience with Tableau for data visualization and storytelling.\n\n- **Machine Learning Techniques:** \n - Expertise in supervised and unsupervised learning algorithms, including regression, classification, clustering, and deep learning. \n - Familiar with natural language processing techniques, including sentiment analysis and text classification.\n\n- **Soft Skills:** \n - Strong analytical and critical thinking skills. \n - Excellent communication and presentation abilities. \n - Proven ability to work collaboratively in a team-oriented environment.\n\n## Projects\n- **Search Result Accuracy Improvement Project:** \n Developed a machine learning model that improved search result accuracy by 20% through enhanced natural language processing techniques. This project involved extensive data preprocessing, feature engineering, and model evaluation.\n\n- **User Feedback Analysis Initiative:** \n Led a project to analyze user feedback, resulting in actionable insights that increased user satisfaction by 15%. This involved conducting surveys, analyzing qualitative data, and presenting findings to stakeholders.\n\n- **Predictive Analytics for User Engagement:** \n Created a predictive model that forecasts user engagement based on historical data, achieving a 30% increase in accuracy over previous models. This project utilized advanced machine learning techniques and required collaboration with marketing teams.\n\n## Interests\n- **Artificial Intelligence and Machine Learning:** \n Passionate about exploring the latest advancements in AI and machine learning, and their applications in various industries.\n\n- **Natural Language Processing and Conversational Agents:** \n Interested in developing intelligent systems that can understand and respond to human language, enhancing user interactions.\n\n- **Cooking and Trying New Recipes:** \n Enjoy experimenting with different cuisines and sharing culinary experiences with friends and family.\n\n- **Playing the Piano and Watching Movies:** \n Avid piano player with a love for music, particularly classical and contemporary genres. Enjoys watching movies, especially comedies and thrillers, for entertainment and inspiration.\n\n## References\nAvailable upon request. \n- **Professional References:** \n - Dr. John Smith, Professor of Data Science, University of Toronto \n - Jane Doe, Senior Product Manager, Microsoft \n- **Personal References:** \n - Emily Johnson, Colleague and Friend \n - Michael Brown, Former Classmate \n```",
"author": "Lisa Carter"
}
================================================
FILE: data/extractions/wordprocessor/Document/Resume of Lisa Carter.Lisa Carter.md
================================================
```
# Lisa Carter
## Contact Information
- **Email:** lisa.carter@example.com
- **Phone:** (123) 456-7890
- **LinkedIn:** [linkedin.com/in/lisacarter](https://linkedin.com/in/lisacarter)
- **Location:** Toronto, Ontario, Canada
## Summary
Lisa Carter is a highly skilled Data Scientist with a Master's degree in Data Science from the prestigious University of Toronto. With a specialization in improving search relevance through innovative context-aware models, Lisa has a proven track record of analyzing user behavior and feedback data to significantly enhance search results. Her passion for advancing artificial intelligence technology is matched by her commitment to improving human productivity and decision-making processes. Lisa is known for her analytical mindset, problem-solving abilities, and collaborative spirit, making her a valuable asset to any team.
## Education
### University of Toronto
- **Master's in Data Science**
- **Thesis:** Improving Search Relevance Using Context-Aware Models
- **Graduated:** 2018
- **Relevant Coursework:**
- Machine Learning
- Data Mining
- Statistical Analysis
- Natural Language Processing
- Big Data Technologies
- **Projects:**
- Developed a predictive model for user engagement based on historical data, achieving a 30% increase in accuracy over previous models.
### Bachelor of Science in Computer Science
- **University of Toronto**
- **Graduated:** 2016
- **Key Achievements:**
- Dean's List for three consecutive years
- Completed a capstone project on developing a web application for data visualization.
## Work Experience
### Microsoft, M365 Search Team
**Data Scientist**
2018 - Present
- **Key Responsibilities:**
- Analyzed user behavior and feedback data to improve search relevance and quality, leading to a 25% increase in user engagement metrics.
- Built and tested machine learning models for natural language understanding, query expansion, and ranking, resulting in a 20% improvement in search accuracy.
- Collaborated with cross-functional teams, including product managers, engineers, and UX designers, to address challenges related to noisy or biased data, ensuring a seamless user experience.
- Ensured compliance with privacy and security policies in all data handling processes, maintaining the highest standards of data integrity and confidentiality.
- Conducted A/B testing to evaluate the effectiveness of new features and algorithms, providing data-driven recommendations for product enhancements.
### Intern, Data Analytics Team
**XYZ Corporation**
2017 - 2018
- Assisted in the development of data-driven strategies to optimize marketing campaigns, resulting in a 15% increase in conversion rates.
- Conducted exploratory data analysis to identify trends and patterns in customer behavior, presenting findings to senior management.
- Collaborated with the IT department to streamline data collection processes, improving data accuracy and accessibility.
## Skills
- **Programming Languages:**
- Proficient in Python, with extensive experience in data analysis and machine learning tools such as pandas, scikit-learn, TensorFlow, and Azure ML.
- Familiar with SQL for database management and data manipulation.
- Basic knowledge of R for statistical analysis and data visualization.
- **Data Visualization Tools:**
- Proficient in Power BI for creating interactive dashboards and reports.
- Experience with Tableau for data visualization and storytelling.
- **Machine Learning Techniques:**
- Expertise in supervised and unsupervised learning algorithms, including regression, classification, clustering, and deep learning.
- Familiar with natural language processing techniques, including sentiment analysis and text classification.
- **Soft Skills:**
- Strong analytical and critical thinking skills.
- Excellent communication and presentation abilities.
- Proven ability to work collaboratively in a team-oriented environment.
## Projects
- **Search Result Accuracy Improvement Project:**
Developed a machine learning model that improved search result accuracy by 20% through enhanced natural language processing techniques. This project involved extensive data preprocessing, feature engineering, and model evaluation.
- **User Feedback Analysis Initiative:**
Led a project to analyze user feedback, resulting in actionable insights that increased user satisfaction by 15%. This involved conducting surveys, analyzing qualitative data, and presenting findings to stakeholders.
- **Predictive Analytics for User Engagement:**
Created a predictive model that forecasts user engagement based on historical data, achieving a 30% increase in accuracy over previous models. This project utilized advanced machine learning techniques and required collaboration with marketing teams.
## Interests
- **Artificial Intelligence and Machine Learning:**
Passionate about exploring the latest advancements in AI and machine learning, and their applications in various industries.
- **Natural Language Processing and Conversational Agents:**
Interested in developing intelligent systems that can understand and respond to human language, enhancing user interactions.
- **Cooking and Trying New Recipes:**
Enjoy experimenting with different cuisines and sharing culinary experiences with friends and family.
- **Playing the Piano and Watching Movies:**
Avid piano player with a love for music, particularly classical and contemporary genres. Enjoys watching movies, especially comedies and thrillers, for entertainment and inspiration.
## References
Available upon request.
- **Professional References:**
- Dr. John Smith, Professor of Data Science, University of Toronto
- Jane Doe, Senior Product Manager, Microsoft
- **Personal References:**
- Emily Johnson, Colleague and Friend
- Michael Brown, Former Classmate
```
================================================
FILE: data/extractions/wordprocessor/Document/Resume of Lisa.Lisa.json
================================================
{
"title": "Resume of Lisa",
"content": "```\n# Lisa's Resume\n\n## Contact Information\n- **Name:** Lisa Johnson\n- **Age:** 28\n- **Nationality:** Canadian\n- **Location:** Toronto, Ontario\n- **Email:** lisa.johnson@email.com\n- **Phone:** (123) 456-7890\n\n## Objective\nAs a passionate and results-driven data scientist, I am seeking a challenging position where I can leverage my extensive skills in data analysis, machine learning, and natural language processing. My goal is to contribute to innovative projects that enhance user experiences and drive business success. I am particularly interested in roles that allow me to work collaboratively with diverse teams to solve complex problems and deliver actionable insights.\n\n## Skills\n### Technical Skills\n- **Programming Languages:**\n - Proficient in Python for data analysis and machine learning.\n - Familiar with R for statistical analysis and visualization.\n\n- **Data Analysis Tools:**\n - Experienced with libraries such as pandas, NumPy, and Matplotlib for data manipulation and visualization.\n - Skilled in using scikit-learn for building machine learning models.\n\n- **Machine Learning Frameworks:**\n - Proficient in TensorFlow and Keras for deep learning applications.\n - Experienced with Azure ML for deploying machine learning models in cloud environments.\n\n- **Database Management:**\n - Familiar with SQL for database querying and management.\n - Knowledgeable in NoSQL databases like MongoDB.\n\n- **Business Intelligence Tools:**\n - Proficient in Power BI for creating interactive dashboards and reports.\n - Experienced with Tableau for data visualization.\n\n### Soft Skills\n- Strong analytical and problem-solving skills, enabling me to dissect complex datasets and derive meaningful insights.\n- Excellent communication abilities, allowing me to present findings clearly to both technical and non-technical stakeholders.\n- Proven teamwork capabilities, having collaborated effectively within cross-functional teams on various projects.\n\n## Professional Experience\n\n### Data Scientist at Microsoft (M365 Search Team) \n*Date: January 2020 - Present* \n**Key Responsibilities:**\n- Analyzed user behavior and feedback data to improve search result relevance, leading to a 15% increase in user satisfaction scores over six months.\n- Built and tested machine learning models for natural language understanding (NLU) and query expansion, resulting in a significant reduction in irrelevant search results.\n- Collaborated with cross-functional teams including product managers, UX designers, and engineers to communicate findings and recommendations effectively.\n- Ensured compliance with privacy and security policies in data handling by implementing best practices for data governance.\n\n**Projects:**\n1. **User Behavior Analysis Project:**\n - Conducted extensive analysis of user interaction logs using Python and SQL to identify patterns that inform product improvements.\n - Developed visualizations using Power BI that highlighted key trends in user engagement.\n\n2. **Machine Learning Model Development:**\n - Designed a predictive model using TensorFlow that improved the accuracy of search result predictions by over 20%.\n - Implemented A/B testing protocols to evaluate the effectiveness of new features based on model outputs.\n\n3. **Cross-Team Collaboration Initiative:**\n - Led workshops with stakeholders from different departments to align on project goals and share insights from data analyses.\n\n### Data Analyst Intern at XYZ Corp \n*Date: May 2019 - December 2019* \n**Key Responsibilities:**\n- Assisted senior analysts in collecting, cleaning, and analyzing large datasets using Excel and SQL.\n- Created reports that summarized findings from analyses which were presented to management during quarterly reviews.\n\n**Achievements:**\n- Developed an automated reporting tool that reduced the time spent on generating monthly reports by 30%.\n\n## Education\n\n### Bachelor of Science in Computer Science \n*University of Toronto, Graduated June 2019* \n**Relevant Coursework:**\n- Data Structures\n- Algorithms\n- Machine Learning\n- Natural Language Processing\n- Database Management Systems\n\n**Projects:**\n1. **Capstone Project:** Developed a sentiment analysis tool using Python that analyzed social media posts related to current events. The project received recognition at the university's annual tech fair.\n2. **Group Project:** Collaborated with peers to create a web application that visualized real-time traffic data using APIs.\n\n## Certifications\n1. **Certified Data Scientist** \u2013 Data Science Council of America (DASCA)\n2. **Microsoft Certified: Azure Data Scientist Associate**\n\n## Interests\nIn addition to my professional pursuits, I have a variety of personal interests that keep me engaged:\n- Cooking new recipes from different cuisines; I enjoy experimenting with flavors and techniques.\n- Playing the piano; I have been taking lessons since childhood and enjoy performing at local community events.\n- Watching movies; I have a particular fondness for comedies that make me laugh as well as thrillers that keep me on the edge of my seat.\n\n## References\nAvailable upon request.\n```",
"author": "Lisa"
}
================================================
FILE: data/extractions/wordprocessor/Document/Resume of Lisa.Lisa.md
================================================
```
# Lisa's Resume
## Contact Information
- **Name:** Lisa Johnson
- **Age:** 28
- **Nationality:** Canadian
- **Location:** Toronto, Ontario
- **Email:** lisa.johnson@email.com
- **Phone:** (123) 456-7890
## Objective
As a passionate and results-driven data scientist, I am seeking a challenging position where I can leverage my extensive skills in data analysis, machine learning, and natural language processing. My goal is to contribute to innovative projects that enhance user experiences and drive business success. I am particularly interested in roles that allow me to work collaboratively with diverse teams to solve complex problems and deliver actionable insights.
## Skills
### Technical Skills
- **Programming Languages:**
- Proficient in Python for data analysis and machine learning.
- Familiar with R for statistical analysis and visualization.
- **Data Analysis Tools:**
- Experienced with libraries such as pandas, NumPy, and Matplotlib for data manipulation and visualization.
- Skilled in using scikit-learn for building machine learning models.
- **Machine Learning Frameworks:**
- Proficient in TensorFlow and Keras for deep learning applications.
- Experienced with Azure ML for deploying machine learning models in cloud environments.
- **Database Management:**
- Familiar with SQL for database querying and management.
- Knowledgeable in NoSQL databases like MongoDB.
- **Business Intelligence Tools:**
- Proficient in Power BI for creating interactive dashboards and reports.
- Experienced with Tableau for data visualization.
### Soft Skills
- Strong analytical and problem-solving skills, enabling me to dissect complex datasets and derive meaningful insights.
- Excellent communication abilities, allowing me to present findings clearly to both technical and non-technical stakeholders.
- Proven teamwork capabilities, having collaborated effectively within cross-functional teams on various projects.
## Professional Experience
### Data Scientist at Microsoft (M365 Search Team)
*Date: January 2020 - Present*
**Key Responsibilities:**
- Analyzed user behavior and feedback data to improve search result relevance, leading to a 15% increase in user satisfaction scores over six months.
- Built and tested machine learning models for natural language understanding (NLU) and query expansion, resulting in a significant reduction in irrelevant search results.
- Collaborated with cross-functional teams including product managers, UX designers, and engineers to communicate findings and recommendations effectively.
- Ensured compliance with privacy and security policies in data handling by implementing best practices for data governance.
**Projects:**
1. **User Behavior Analysis Project:**
- Conducted extensive analysis of user interaction logs using Python and SQL to identify patterns that inform product improvements.
- Developed visualizations using Power BI that highlighted key trends in user engagement.
2. **Machine Learning Model Development:**
- Designed a predictive model using TensorFlow that improved the accuracy of search result predictions by over 20%.
- Implemented A/B testing protocols to evaluate the effectiveness of new features based on model outputs.
3. **Cross-Team Collaboration Initiative:**
- Led workshops with stakeholders from different departments to align on project goals and share insights from data analyses.
### Data Analyst Intern at XYZ Corp
*Date: May 2019 - December 2019*
**Key Responsibilities:**
- Assisted senior analysts in collecting, cleaning, and analyzing large datasets using Excel and SQL.
- Created reports that summarized findings from analyses which were presented to management during quarterly reviews.
**Achievements:**
- Developed an automated reporting tool that reduced the time spent on generating monthly reports by 30%.
## Education
### Bachelor of Science in Computer Science
*University of Toronto, Graduated June 2019*
**Relevant Coursework:**
- Data Structures
- Algorithms
- Machine Learning
- Natural Language Processing
- Database Management Systems
**Projects:**
1. **Capstone Project:** Developed a sentiment analysis tool using Python that analyzed social media posts related to current events. The project received recognition at the university's annual tech fair.
2. **Group Project:** Collaborated with peers to create a web application that visualized real-time traffic data using APIs.
## Certifications
1. **Certified Data Scientist** – Data Science Council of America (DASCA)
2. **Microsoft Certified: Azure Data Scientist Associate**
## Interests
In addition to my professional pursuits, I have a variety of personal interests that keep me engaged:
- Cooking new recipes from different cuisines; I enjoy experimenting with flavors and techniques.
- Playing the piano; I have been taking lessons since childhood and enjoy performing at local community events.
- Watching movies; I have a particular fondness for comedies that make me laugh as well as thrillers that keep me on the edge of my seat.
## References
Available upon request.
```
================================================
FILE: data/facts/business-facts.synthetic.txt
================================================
1. Effective communication is a crucial skill for business consultants to develop trust and rapport with clients.
2. Understanding the client's industry is fundamental for providing relevant and actionable advice.
3. A comprehensive market analysis can uncover opportunities for business growth and expansion.
4. SWOT analysis helps identify a client's strengths, weaknesses, opportunities, and threats.
5. Keeping updated with industry trends allows consultants to offer cutting-edge insights.
6. Networking is essential for business consultants to broaden their client base and collaborate with other professionals.
7. Time management skills enable consultants to maximize productivity and meet client deadlines.
8. Financial literacy is vital for consultants to analyze and interpret financial statements effectively.
9. A well-defined value proposition is key to a successful business consulting practice.
10. Establishing clear objectives with clients ensures both parties have aligned expectations.
11. Data-driven decision-making enhances the credibility and impact of consulting recommendations.
12. Change management skills are crucial for consultants assisting organizations in transformations.
13. Setting measurable goals allows clients to track progress and assess the effectiveness of consulting efforts.
14. A strong professional online presence strengthens a consultant's reputation and visibility.
15. Developing negotiation skills helps consultants secure agreements and foster client satisfaction.
16. Conducting competitive analysis provides insights into competitors' strengths and weaknesses.
17. Ethics and integrity are foundational principles for maintaining trust in consulting relationships.
18. Leveraging digital tools can enhance a consultant's ability to deliver efficient and impactful solutions.
19. Understanding the client's target audience is essential for crafting effective marketing strategies.
20. Critical thinking skills enable consultants to address complex business challenges creatively.
21. Building long-term relationships with clients can lead to repeat business and referrals.
22. Regularly seeking feedback helps consultants improve their services and client satisfaction.
23. Familiarity with various business models enables consultants to tailor advice to clients' needs.
24. Best practice research provides consultants with proven methods and techniques for success.
25. Streamlining operations can lead to cost savings and increased operational efficiency for clients.
26. Consultants should continuously develop their skillset to remain competitive in a dynamic market.
27. Understanding cultural differences is crucial for consultants working with international clients.
28. Strategic planning is an essential component of guiding clients toward achieving long-term goals.
29. In-depth competitor profiling assists consultants in identifying competitive advantages.
30. The ability to adapt to changing client needs is a valuable trait for a successful consultant.
31. Consultants should focus on delivering tangible results that demonstrate their value to clients.
32. Conducting regular client check-ins ensures ongoing alignment and addresses any emerging issues.
33. Benchmarking against industry standards helps clients gauge their performance and identify areas for improvement.
34. Emotional intelligence aids consultants in understanding client emotions and improving communication.
35. Identifying key performance indicators (KPIs) enables clients to measure success effectively.
36. Effective presentation skills are essential for consultants to articulate strategies and findings clearly.
37. Confidentiality is critical in maintaining client trust and protecting sensitive business information.
38. Consultants should prioritize understanding a client's corporate culture to deliver tailored solutions.
39. Providing post-implementation support helps clients sustain improvements after consulting engagements.
40. A proactive approach to problem-solving is beneficial in addressing potential business challenges early.
41. Conducting a risk assessment helps clients identify potential business threats and develop mitigation strategies.
42. Digital transformation is becoming increasingly important for maintaining competitiveness and efficiency.
43. Consultants should emphasize sustainable business practices to help clients achieve long-term success.
44. Building a diverse team can enhance a consulting firm's ability to deliver innovative solutions.
45. Effective stakeholder management is key to the successful execution of complex projects.
46. Regularly reviewing and updating business processes can lead to continuous improvement.
47. Customer feedback is a valuable source of insights for improving products and services.
48. Understanding organizational structure helps consultants navigate client businesses to implement recommendations.
49. Consultants should encourage clients to foster a culture of innovation for sustained business growth.
50. Identifying emerging technologies can help clients stay ahead of industry trends and competitors.
51. Transparency in communication fosters trust and strengthens consultant-client relationships.
52. Scenario planning helps clients prepare for possible future challenges and opportunities.
53. Consultants should adapt their communication style to suit different client preferences and contexts.
54. Providing actionable insights is more valuable than presenting raw data to clients.
55. Establishing clear project timelines ensures efficient resource allocation and delivery.
56. Consultants should strive to simplify complex ideas to facilitate client understanding and decision-making.
57. A thorough project handover ensures clients are equipped to manage new systems or processes independently.
58. Building rapport with clients can lead to more open communication and better problem-solving.
59. Consultants should encourage clients to embrace change as a continual improvement opportunity.
60. The ability to conduct gap analysis helps clients identify deficiencies and prioritize improvements.
61. Consultants should remain unbiased and impartial to provide objective advice and recommendations.
62. Tailoring strategies to client-specific needs increases the likelihood of successful outcomes.
63. Consultants should develop a deep understanding of a client's competitive landscape to provide relevant advice.
64. Encouraging cross-departmental collaboration can lead to innovative solutions and improved business outcomes.
65. Clear and concise report writing helps clients quickly grasp key insights and recommendations.
66. Performance management systems are critical for ensuring employees meet organizational goals.
67. Consultants should encourage a growth mindset within client organizations to foster adaptability.
68. Leveraging social media platforms can enhance a client's brand visibility and engagement.
69. Consultants should apply lessons learned from past projects to improve future client engagements.
70. Regularly analyzing customer trends helps consultants advise clients on meeting evolving demands.
71. Data visualization techniques can make complex insights more accessible to clients.
72. Understanding a client's product lifecycle is crucial for providing appropriate strategic advice.
73. Consultants should use storytelling to make their analyses and recommendations more relatable.
74. Facilitating workshops can help clients generate creative solutions and foster team alignment.
75. Consultants should advise clients on effective leadership practices for organizational success.
76. Agile methodologies can increase flexibility and responsiveness in client projects and processes.
77. Understanding fiscal policies and regulations is important for consultants advising on financial matters.
78. Consultants should be open to feedback and continuously seek to improve their service delivery.
79. Digital marketing strategies can enhance a client's reach and target audience engagement.
80. Effective crisis management plans can protect a client's reputation and minimize business disruption.
81. Regularly reviewing a client's business strategy ensures alignment with changing market conditions.
82. Consultants should advocate for ethical business practices to strengthen client reputation and compliance.
83. Incorporating feedback loops within processes enhances client responsiveness to change.
84. Consultants should foster a culture of continuous learning and improvement within client organizations.
85. Strategic partnerships can provide clients with competitive advantage through collaboration.
86. Effective project management ensures on-time delivery of consulting deliverables and client satisfaction.
87. Consultants should advise clients on aligning their talent management strategies with business goals.
88. Stakeholder analysis helps clients understand the interests and influence of individuals involved in a project.
89. Process automation can lead to increased efficiency and consistency in business operations.
90. Consultants should guide clients in developing effective customer loyalty programs.
91. Political, economic, social, and technological factors can significantly impact a client's business environment.
92. Innovation workshops can inspire ideas for new products, services, or process improvements.
93. Consultants should ensure they understand the specific goals and constraints of each client situation.
94. Risk management strategies are essential for minimizing the impact of unforeseen events.
95. Consultants should encourage clients to invest in employee development to enhance productivity and retention.
96. Understanding a client's regulatory requirements is critical for ensuring compliance and avoiding penalties.
97. Effective leadership development programs can prepare future leaders within client organizations.
98. Consultants should help clients develop brand positioning strategies that differentiate them in the market.
99. Mergers and acquisitions can drive growth, but require careful planning and execution.
100. Consultants should emphasize the importance of digital literacy for all employees in client organizations.
101. Advanced analytics can provide deeper insights into client data, identifying trends and opportunities.
102. Consultants should recommend data protection best practices to secure client information.
103. Understanding the full customer journey can help consultants enhance the client’s customer experience.
104. Consultants should advise clients to prioritize corporate social responsibility initiatives for sustainability.
105. Solid stakeholder relationships are crucial for the successful implementation of strategic initiatives.
106. Consultants need to be proficient in project management tools to track progress and ensure accountability.
107. A client-centric approach can lead to higher customer satisfaction and loyalty.
108. Consultants should encourage clients to develop contingency plans for high-risk projects.
109. Continuous feedback mechanisms help clients adjust strategies to meet changing needs.
110. Consultants should assess a client's operational risk to minimize potential business disruptions.
111. Quantitative analysis can help clients make informed financial and strategic decisions.
112. Consultants should advocate for effective workplace communication practices to enhance collaboration.
113. Understanding the client's decision-making hierarchy can streamline approval processes.
114. Consultants should monitor client competition to identify emerging threats and opportunities.
115. Strategic portfolio management can help clients align projects with business objectives.
116. Consultants should encourage clients to leverage innovation to keep pace with market developments.
117. Building a strong organizational culture can lead to improved employee engagement and productivity.
118. Consultants should guide clients in balancing innovation with risk management.
119. Effective supply chain management can enhance a client’s operational efficiency and cost control.
120. Predictive analytics can help clients anticipate market trends and customer behaviors.
121. Consultants should assist clients in developing robust cybersecurity practices to protect data assets.
122. Understanding consumer sentiment analysis helps clients tailor their marketing and product development.
123. Consultants should advise on strategic use of artificial intelligence to improve business processes.
124. Training programs can enhance a client's workforce skills and adaptability.
125. Consultants should emphasize the importance of aligning IT strategy with business goals.
126. Automation in finance functions can lead to greater accuracy and efficiency in reporting.
127. Consultants need to identify the most impactful metrics for clients to track their strategic progress.
128. Effective presentation of complex solutions in simple terms helps clients with decision-making.
129. Consultants should help clients foster a customer-first mindset across their organization.
130. Identifying potential catalysts for change can guide strategic planning and execution.
131. Consultants should promote resilience thinking to help clients manage and adapt to change.
132. A strong feedback culture within organizations can drive innovation and continuous improvement.
133. Effective communication of value propositions helps consultants differentiate their services.
134. Emerging markets may offer growth opportunities for clients looking to expand internationally.
135. Building an effective performance review process can aid in tracking employee progress and development.
136. Consultants should guide clients in making data-informed decisions to mitigate business risks.
137. Digital content strategies can enhance a client's customer engagement and brand loyalty.
138. Consultants should advise on ways to improve organizational agility to adapt to market changes.
139. Market segmentation allows clients to tailor offerings to specific customer needs and preferences.
140. Consultants should help clients utilize collaborative tools to enhance team communication and productivity.
141. Change champions within organizations can influence and support transitions effectively.
142. Cybersecurity awareness training can prevent data breaches and protect sensitive client information.
143. Consultants should encourage leaders to model desired behaviors for culture transformation.
144. Managing a diversified investment portfolio can help clients reduce financial risk.
145. Emotional branding can differentiate a client's products or services by establishing strong customer connections.
146. Consultants should facilitate strategic workshops to foster alignment and consensus among stakeholders.
147. A client’s success in global markets hinges on effective market entry strategies.
148. Consultants should assist in developing business intelligence systems for data-driven decision-making.
149. Branding consistency across channels builds trust and recognition for a client's organization.
150. Consultants need to assess the socio-economic impact of client projects for responsible consulting.
151. Effective pricing strategies are crucial for client profitability and competitive positioning.
152. Customer journey mapping can help clients improve touchpoints and overall experience.
153. Consultants should advise on optimizing resource allocation to maximize project outcomes.
154. Employee retention strategies can lead to cost savings and improved client service delivery.
155. Strategic alliances can expand a client's capabilities and market reach through shared resources.
156. Consultants should assess the scalability of business models to support client growth objectives.
157. Good governance practices instill confidence and help mitigate client stakeholder risks.
158. Consultants need to develop skills in virtual tools to facilitate remote consulting engagements.
159. Effective internal communication supports engagement and keeps client personnel informed.
160. Risk mitigation strategies can help clients protect their assets and ensure business continuity.
161. Understanding the competitive landscape is essential for strategic positioning in the market.
162. Consultants should promote transparency in budgeting processes to build client trust.
163. Scaling strategies are crucial for clients aiming to grow their operations organically.
164. Consultants should guide clients in talent acquisition strategies to attract top-tier candidates.
165. Benchmarking against industry best practices can expose gaps and opportunities for improvement.
166. Consultants should encourage clients to conduct regular employee engagement surveys.
167. Emerging tech trends should be closely monitored to remain relevant in client advisement.
168. A focus on customer satisfaction is key to client reputation and long-term success.
169. Consultants should facilitate alignment between corporate strategy and functional objectives.
170. Effective crisis communication plans prevent misinformation and protect a client's credibility.
171. Cost-benefit analysis is important when deciding on significant client investments or projects.
172. Consultants should guide clients in nurturing relationships with key accounts and partners.
173. Encouraging innovation can make clients more competitive in an ever-evolving market landscape.
174. Consultants need to maintain industry certifications to showcase proficiency and credibility.
175. Effective retention marketing strategies can increase a client's repeat customer rates.
176. Consultants should assist in developing a flexible workplace strategy to attract diverse talent.
177. Engaging visual aids in presentations can enhance client understanding and retention.
178. Consultants should help clients streamline their supply chain to reduce costs and improve delivery times.
179. Understanding local regulations is essential for clients operating in multiple jurisdictions.
180. Consultants should enable a mindset shift from focusing on transactions to building relationships.
181. Utilizing cloud computing solutions can enhance a client’s data accessibility and collaboration.
182. Consultants should assess the potential social impact of strategic client decisions.
183. Efficient document management systems improve client accessibility and reduce information silos.
184. Consultants should guide clients in prioritizing digital skills development for future readiness.
185. Minimal viable products can help clients test market acceptance before full-scale launches.
186. Consultants should recommend integrating predictive maintenance to reduce client operational costs.
187. Sustainable and ethical sourcing can improve client supply chain reliability and reputation.
188. Cross-selling and upselling strategies can increase a client's revenue from existing customers.
189. Consultants should advise on workplace diversity initiatives for inclusive company culture.
190. Green business models can lead to long-term client sustainability and brand advantage.
191. Effective collaboration tools can support remote operations and enhance teamwork.
192. Consultants should help clients establish a vision that aligns with their core values and objectives.
193. Strategic foresight can assist clients in navigating potential future challenges and disruptions.
194. Consultants should facilitate workshops that bring diverse perspectives to develop creative solutions.
195. Analyzing customer feedback is crucial for understanding market needs and enhancing satisfaction.
196. Consultants need to promote resilience by advocating for adaptable client strategies.
197. Effective brand storytelling can create emotional connections and differentiate client offerings.
198. Consultants should engage in scenario planning to prepare for various future market conditions.
199. A consultative sales approach focuses on understanding and solving client needs rather than pushing a product.
200. Consultants should remain agile to adapt to dynamic client requirements and industry changes.
201. A holistic view of the value chain can help clients optimize operations and improve profitability.
202. Consultants should advise on corporate governance best practices to enhance client accountability.
203. Leveraging analytics can help clients personalize customer experiences and predict behavior.
204. Transparent reporting enhances trust and credibility in client-stakeholder communication.
205. Consultants should advocate for integrating environmental, social, and governance (ESG) criteria into client strategies.
206. Transformation roadmaps provide clear paths for clients undertaking digital or organizational changes.
207. Assessing a client's core competencies can guide strategic positioning and differentiation.
208. Consultants should assist in developing agile methodologies to boost client project execution.
209. Understanding consumer privacy and data protection regulations is critical for consultants advising on client compliance.
210. Regular competitive audits can keep clients informed on their positioning and market dynamics.
211. Consultants should encourage regular strategy reviews to ensure alignment with organizational goals.
212. Effective team leadership is key for successful project delivery in client engagements.
213. Consultants should guide clients in communicating strategic direction clearly across teams.
214. Enhancing customer service capabilities can lead to higher satisfaction and brand loyalty.
215. Consultants should promote data-driven insights for better strategic dialogue with clients.
216. Investing in leadership capabilities prepares clients for future organizational challenges.
217. Consultants should encourage a culture of feedback to enhance employee engagement and performance.
218. Strategic diversification can minimize client risk exposure and capitalize on new opportunities.
219. Consultants should support the adoption of technology solutions that align with client goals.
220. Incorporating predictive analytics helps forecast future trends and client market behavior.
221. Consultants should advise on structuring strategic alliances to boost competitive advantage.
222. Providing clients with a road map ensures clear steps and milestones for achieving goals.
223. Consultants should advocate for a strong legal framework to protect client intellectual property.
224. Effective product lifecycle management can increase a client's market responsiveness.
225. Consultants should focus on helping clients create a compelling customer value proposition.
226. Sustainability initiatives can enhance client brand perception and reduce environmental impact.
227. Consultants should encourage clients to align tech investments with business strategy for ROI.
228. Organizing cross-functional teams can bring diverse expertise to solve client problems.
229. Consultants should guide clients in strategic risk assessment to anticipate potential setbacks.
230. Leveraging digital ecosystems can expand client business models and market reach.
231. Consultants should ensure that clients develop robust strategies for digital customer engagement.
232. Change management is crucial for ensuring client transitions are well-received by employees.
233. Strategic agility can increase a client's ability to respond rapidly to market changes.
234. Consultants should promote the use of OKRs (Objectives and Key Results) to align teams.
235. Fostering a strong company culture can significantly impact client employee satisfaction.
236. Consultants should facilitate knowledge sharing to encourage collaboration and innovation.
237. Regular workforce analysis can aid in identifying skill gaps and future talent needs.
238. Consultants should advocate for clear succession planning to ensure leadership continuity.
239. Applying behavioral economics can help clients better understand customer decision processes.
240. Consultants should encourage long-term thinking for sustainable client business success.
241. Advanced insights from big data can drive better strategic decision-making for clients.
242. A focus on continuous improvement can enhance client competitiveness and efficiency.
243. Consultants should recommend tools and processes that enhance client work-life balance.
244. Encouraging open communication among teams fosters collaboration and innovation for clients.
245. Strategic foresight aligns a client’s actions with anticipated challenges and disruptions.
246. Consultants should promote integrated reporting for a holistic view of client business performance.
247. Effective use of KPIs can help track client progress toward strategic objectives.
248. Consultants should counsel on mergers and acquisitions to aid in strategic client growth.
249. Encouraging cognitive diversity in client teams can drive novel solutions and ideas.
250. Creating an inclusive workplace culture can benefit client employee engagement and performance.
251. Consultants should ensure that clients have robust customer relationship management (CRM) systems.
252. Agile HR practices can make client organizations more adaptable to rapid changes.
253. Consultants need to balance risk and innovation for clients to maintain competitive advantage.
254. Resilient supply chains can withstand disruptions and support client business continuity.
255. Consultants should consider the life cycle cost of client investment decisions for long-term value.
256. Engaging employees in strategic development processes drives alignment and ownership.
257. Consultants should identify potential new market segments for client business expansion.
258. Effective resource planning ensures that clients maximize efficiency and minimize waste.
259. Consultants should help clients navigate regulatory environments to maintain compliance.
260. Employing a user-centric design approach can enhance client product and service usability.
261. Tracking client competitors' benchmarks informs better strategic decision-making.
262. Consultants should guide clients in creating value networks to deliver enhanced solutions.
263. Collaborative innovation can enable clients to harness collective expertise and breakthroughs.
264. Consultants need to advocate for clear internal branding to support client engagement and loyalty.
265. Effective contingency planning helps clients prepare for and mitigate potential crises.
266. Consultants should facilitate workshops that focus on building strategic alignment across departments.
267. Providing frameworks for decision-making empowers clients to act with confidence and clarity.
268. Understanding the client's customer personas ensures more precise targeting and engagement.
269. Consultants should advocate for the strategic deployment of machine learning to enhance operations.
270. Structuring client operations for lean efficiency can reduce costs and improve productivity.
271. Consultants should promote narrative-driven reporting to make findings more compelling and memorable.
272. Visibility in client supply chains aids in the identification of potential bottlenecks and inefficiencies.
273. Consultants should encourage scenario modeling to prepare for diverse business conditions.
274. Employee value propositions help attract and retain top talent for clients.
275. Consultants should guide client strategic communications to align with brand vision and objectives.
276. Knowledge management systems can enhance client learning and resource-sharing opportunities.
277. Strategic outsourcing can help clients focus on core competencies while gaining external expertise.
278. Facilitating strategy sessions encourages diverse client inputs and fosters innovative solutions.
279. Consultants should promote process reengineering to streamline client workflows and improve outcomes.
280. Building resilient organizational frameworks can help clients withstand economic uncertainty.
281. Consultants should guide clients in resource risk analysis to optimize and safeguard operations.
282. Understanding generational diversity in the workforce can improve client recruitment and retention.
283. Consulting on boundary-spanning leadership can enhance client collaboration and capability building.
284. Effective governance structures ensure that clients maintain alignment with strategic goals.
285. Consultants should emphasize the value of mentoring and coaching for client employee development.
286. Leve
gitextract_rb6ph2t1/ ├── .gitattributes ├── .github/ │ ├── copilot-instructions.md │ ├── project-copilot-instructions.md │ ├── prompts/ │ │ ├── improve.prompt.md │ │ ├── open-ended_ideas.prompt.md │ │ └── write_tests.prompt.md │ └── workflows/ │ ├── bandit.yml │ └── codeql.yml ├── .gitignore ├── CODE_OF_CONDUCT.md ├── LICENSE ├── MANIFEST.in ├── README.md ├── RESPONSIBLE_AI_FAQ.md ├── SECURITY.md ├── SUPPORT.md ├── build_and_install_package_from_repo.bat ├── build_package.bat ├── config.ini ├── data/ │ ├── empirical/ │ │ ├── 07.17.2025 - Market Research - AI-enabled story telling device or app - Raw Data.csv │ │ └── 07.19.2025 - Market Research - Bottled Gazpacho - Raw Data.csv │ ├── extractions/ │ │ ├── appartment_rent_ad.extraction.json │ │ ├── appartment_rent_ad_1.extraction.json │ │ ├── synthetic_data_generation.out.csv │ │ └── wordprocessor/ │ │ └── Document/ │ │ ├── Lisa Carter - Resume.Lisa Carter.docx │ │ ├── Lisa Carter - Resume.Lisa Carter.json │ │ ├── Lisa Carter - Resume.Lisa Carter.md │ │ ├── Resume of Lisa Carter.Lisa Carter.docx │ │ ├── Resume of Lisa Carter.Lisa Carter.json │ │ ├── Resume of Lisa Carter.Lisa Carter.md │ │ ├── Resume of Lisa.Lisa.docx │ │ ├── Resume of Lisa.Lisa.json │ │ ├── Resume of Lisa.Lisa.md │ │ └── Resume.Lisa.docx │ ├── facts/ │ │ └── business-facts.synthetic.txt │ └── grounding_examples/ │ ├── grounding_examples_1/ │ │ ├── don_quijote_project_gutenberg.txt │ │ └── marus_aurelius_meditations_by_project_gutenberg.txt │ └── grounding_microsoft/ │ ├── 2023_Microsoft_Annual_Report.docx │ └── 2024_Annual_Report.docx ├── docs/ │ ├── api/ │ │ └── tinytroupe/ │ │ ├── agent/ │ │ │ ├── action_generator.html │ │ │ ├── grounding.html │ │ │ ├── index.html │ │ │ ├── memory.html │ │ │ ├── mental_faculty.html │ │ │ └── tiny_person.html │ │ ├── clients/ │ │ │ ├── azure_client.html │ │ │ ├── index.html │ │ │ ├── ollama_client.html │ │ │ └── openai_client.html │ │ ├── control.html │ │ ├── enrichment/ │ │ │ ├── index.html │ │ │ ├── tiny_enricher.html │ │ │ └── tiny_styler.html │ │ ├── environment/ │ │ │ ├── index.html │ │ │ ├── tiny_social_network.html │ │ │ └── tiny_world.html │ │ ├── examples/ │ │ │ ├── agents.html │ │ │ ├── index.html │ │ │ └── loaders.html │ │ ├── experimentation/ │ │ │ ├── in_place_experiment_runner.html │ │ │ ├── index.html │ │ │ ├── proposition.html │ │ │ ├── randomization.html │ │ │ └── statistical_tests.html │ │ ├── extraction/ │ │ │ ├── artifact_exporter.html │ │ │ ├── index.html │ │ │ ├── normalizer.html │ │ │ ├── results_extractor.html │ │ │ ├── results_reducer.html │ │ │ └── results_reporter.html │ │ ├── factory/ │ │ │ ├── index.html │ │ │ ├── tiny_factory.html │ │ │ └── tiny_person_factory.html │ │ ├── index.html │ │ ├── profiling.html │ │ ├── steering/ │ │ │ ├── index.html │ │ │ ├── intervention.html │ │ │ └── tiny_story.html │ │ ├── tools/ │ │ │ ├── index.html │ │ │ ├── tiny_calendar.html │ │ │ ├── tiny_tool.html │ │ │ └── tiny_word_processor.html │ │ ├── ui/ │ │ │ ├── index.html │ │ │ └── jupyter_widgets.html │ │ ├── utils/ │ │ │ ├── behavior.html │ │ │ ├── concurrency.html │ │ │ ├── config.html │ │ │ ├── index.html │ │ │ ├── json.html │ │ │ ├── llm.html │ │ │ ├── misc.html │ │ │ ├── parallel.html │ │ │ ├── rendering.html │ │ │ ├── semantics.html │ │ │ └── validation.html │ │ └── validation/ │ │ ├── index.html │ │ ├── propositions.html │ │ ├── simulation_validator.html │ │ ├── tiny_person_validator.html │ │ └── validation_chamber.html │ ├── guides/ │ │ └── ollama.md │ └── index.html ├── examples/ │ ├── AI-enabled Children Story Telling Market Research 2.ipynb │ ├── AI-enabled Children Story Telling Market Research.ipynb │ ├── Advertisement for TV.ipynb │ ├── Bottled Gazpacho Market Research 2.archival.ipynb │ ├── Bottled Gazpacho Market Research 3.archival.ipynb │ ├── Bottled Gazpacho Market Research 4.archival.ipynb │ ├── Bottled Gazpacho Market Research 4b.archival.ipynb │ ├── Bottled Gazpacho Market Research 5 (with behavior correction).ipynb │ ├── Bottled Gazpacho Market Research 5.ipynb │ ├── Bottled Gazpacho Market Research 5b.ipynb │ ├── Bottled Gazpacho Market Research 5c.ipynb │ ├── Bottled Gazpacho Market Research.archival.ipynb │ ├── Create Ad for Apartment.ipynb │ ├── Creating and Validating Agents.ipynb │ ├── Interview with Customer.ipynb │ ├── Investment Firm.ipynb │ ├── Online Advertisement for Travel.ipynb │ ├── Political Compass (customizing agents with fragments).ipynb │ ├── Product Brainstorming (with behavior correction).ipynb │ ├── Product Brainstorming.ipynb │ ├── Simple Chat.ipynb │ ├── Story telling (long narratives).ipynb │ ├── Synthetic Data Generation 1.ipynb │ ├── Synthetic Data Generation 2 (tool usage).ipynb │ ├── Synthetic Data Generation.ipynb │ ├── Travel Product Market Research.ipynb │ ├── Word Processor Tool Usage.ipynb │ ├── agents/ │ │ ├── Friedrich_Wolf.agent.json │ │ ├── Lila.agent.json │ │ ├── Lisa.agent.json │ │ ├── Marcos.agent.json │ │ ├── Oscar.agent.json │ │ ├── Paulo_Salem.agent.json │ │ └── Sophie_Lefevre.agent.json │ ├── archive/ │ │ ├── AI-enabled Children Story Telling Market Research.ipynb │ │ ├── Bottled Gazpacho Market Research 2.archival.ipynb │ │ ├── Bottled Gazpacho Market Research 3.archival.ipynb │ │ ├── Bottled Gazpacho Market Research 4.archival.ipynb │ │ ├── Bottled Gazpacho Market Research 4b.archival.ipynb │ │ ├── Bottled Gazpacho Market Research 5b.ipynb │ │ ├── Bottled Gazpacho Market Research 5c.ipynb │ │ └── Bottled Gazpacho Market Research.archival.ipynb │ ├── config.ini │ ├── extractions/ │ │ └── synthetic_data_example_3/ │ │ └── Document/ │ │ ├── MultiLever Rapid Response Report- Stabilizing Demand under High Inflation.Lisa Carter.docx │ │ ├── MultiLever Rapid Response Report- Stabilizing Demand under High Inflation.Lisa Carter.json │ │ ├── MultiLever Rapid Response Report- Stabilizing Demand under High Inflation.Lisa Carter.md │ │ ├── MultiLever — Initial Rapid Diagnostic & Recommendations (Client Brief).Lisa Carter.docx │ │ ├── MultiLever — Initial Rapid Diagnostic & Recommendations (Client Brief).Lisa Carter.json │ │ ├── MultiLever — Initial Rapid Diagnostic & Recommendations (Client Brief).Lisa Carter.md │ │ ├── MultiLever — Rapid Diagnostic & Recommendations.Lisa Carter.docx │ │ ├── MultiLever — Rapid Diagnostic & Recommendations.Lisa Carter.json │ │ ├── MultiLever — Rapid Diagnostic & Recommendations.Lisa Carter.md │ │ ├── Port Aurora u0007 Rapid Flood Resilience Plan u0007 Initial Report and Recommended Next Steps.Lisa Carter.docx │ │ ├── Port Aurora u0007 Rapid Flood Resilience Plan u0007 Initial Report and Recommended Next Steps.Lisa Carter.json │ │ ├── Port Aurora u0007 Rapid Flood Resilience Plan u0007 Initial Report and Recommended Next Steps.Lisa Carter.md │ │ ├── Rapid Delivery Plan- Phase 1 FEMA-compliant Procurement and Upgrade Path.Lisa Carter.docx │ │ ├── Rapid Delivery Plan- Phase 1 FEMA-compliant Procurement and Upgrade Path.Lisa Carter.json │ │ └── Rapid Delivery Plan- Phase 1 FEMA-compliant Procurement and Upgrade Path.Lisa Carter.md │ ├── fragments/ │ │ ├── aggressive_debater.fragment.json │ │ ├── authoritarian.agent.fragment.json │ │ ├── genuine.agent.fragment.json │ │ ├── leftwing.agent.fragment.json │ │ ├── libertarian.agent.fragment.json │ │ ├── loving_parent.agent.fragment.json │ │ ├── picky_customer.agent.fragment.json │ │ ├── rightwing.agent.fragment.json │ │ └── travel_enthusiast.agent.fragment.json │ ├── information/ │ │ └── populations/ │ │ ├── brazil.json │ │ ├── spain.json │ │ └── usa.json │ ├── ollama/ │ │ ├── Simple Chat.ipynb │ │ └── config.ini │ └── scratch/ │ ├── Advertisement for TV.ipynb │ ├── Simulation Experiment Empirical Validation Example.ipynb │ ├── config.ini │ └── tool_usage.ipynb ├── generate_api_documentation.bat ├── install_package_from_repo.bat ├── publications/ │ ├── README.md │ ├── paper_artifacts_june-2025/ │ │ ├── Brainstorming and Focus Group Quantitative Experimentation 1 - treatment run.ipynb │ │ ├── Brainstorming and Focus Group Quantitative Experimentation 1.ipynb │ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.1 - treatment run.ipynb │ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.1.ipynb │ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.2 - treatment run.ipynb │ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.2.ipynb │ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.3 - treatment run.ipynb │ │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.3.ipynb │ │ ├── Debating Quantitative Experimentation 1 - treatment run.ipynb │ │ ├── Debating Quantitative Experimentation 1.ipynb │ │ ├── Food Products Ideas Brainstorming.ipynb │ │ ├── Market Research Quantitative Experimentation 1.ipynb │ │ ├── Market Research Quantitative Experimentation 2.ipynb │ │ ├── Opinion Poll Quantitative Experimentation.ipynb │ │ ├── Political Compass (customizing agents with fragments).ipynb │ │ ├── Populations creation.ipynb │ │ ├── Spicy Food Market Research.ipynb │ │ ├── Synthetic Data Generation.ipynb │ │ ├── Travel Product Market Research (with behavior correction).ipynb │ │ ├── Travel Product Market Research.ipynb │ │ ├── brainstorming_and_focus_group_quantitative_experimentation_1c.json │ │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.1c.json │ │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.2b.json │ │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.3.json │ │ ├── common_utils.py │ │ ├── config.ini │ │ ├── debating_quantitative_experimentation_1c.json │ │ ├── extractions/ │ │ │ ├── synthetic_data_example_1/ │ │ │ │ └── Document/ │ │ │ │ ├── Report for AquaPure Solutions- Strategies for Modernizing Water Purification Systems.Lisa Carter.docx │ │ │ │ ├── Report for AquaPure Solutions- Strategies for Modernizing Water Purification Systems.Lisa Carter.json │ │ │ │ ├── Report for AquaPure Solutions- Strategies for Modernizing Water Purification Systems.Lisa Carter.md │ │ │ │ ├── Report for BioSphere Innovations- Feasibility Study for Waste-to-Energy Solution.Lisa Carter.docx │ │ │ │ ├── Report for BioSphere Innovations- Feasibility Study for Waste-to-Energy Solution.Lisa Carter.json │ │ │ │ ├── Report for BioSphere Innovations- Feasibility Study for Waste-to-Energy Solution.Lisa Carter.md │ │ │ │ ├── Report for BrightPath Industries- Strategies for Enhancing Supply Chain Resilience.Lisa Carter.docx │ │ │ │ ├── Report for BrightPath Industries- Strategies for Enhancing Supply Chain Resilience.Lisa Carter.json │ │ │ │ ├── Report for BrightPath Industries- Strategies for Enhancing Supply Chain Resilience.Lisa Carter.md │ │ │ │ ├── Report for CleanFuture Corp- Strategies for Reshaping Public Image and Sustainability Practices.Lisa Carter.docx │ │ │ │ ├── Report for CleanFuture Corp- Strategies for Reshaping Public Image and Sustainability Practices.Lisa Carter.json │ │ │ │ ├── Report for CleanFuture Corp- Strategies for Reshaping Public Image and Sustainability Practices.Lisa Carter.md │ │ │ │ ├── Report for EcoFuture Enterprises- Strategies for Sourcing Sustainable Materials.Lisa Carter.docx │ │ │ │ ├── Report for EcoFuture Enterprises- Strategies for Sourcing Sustainable Materials.Lisa Carter.json │ │ │ │ ├── Report for EcoFuture Enterprises- Strategies for Sourcing Sustainable Materials.Lisa Carter.md │ │ │ │ ├── Report for EcoTech Solutions- Strategies for Enhancing Product Appeal and Market Presence.Lisa Carter.docx │ │ │ │ ├── Report for EcoTech Solutions- Strategies for Enhancing Product Appeal and Market Presence.Lisa Carter.json │ │ │ │ ├── Report for EcoTech Solutions- Strategies for Enhancing Product Appeal and Market Presence.Lisa Carter.md │ │ │ │ ├── Report for GreenWave Innovations- Strategies for Reducing Waste and Enhancing Sustainability.Lisa Carter.docx │ │ │ │ ├── Report for GreenWave Innovations- Strategies for Reducing Waste and Enhancing Sustainability.Lisa Carter.json │ │ │ │ ├── Report for GreenWave Innovations- Strategies for Reducing Waste and Enhancing Sustainability.Lisa Carter.md │ │ │ │ ├── Report for MultiLever- Strategies for Addressing Inflation and Enhancing Consumer Demand.Lisa Carter.docx │ │ │ │ ├── Report for MultiLever- Strategies for Addressing Inflation and Enhancing Consumer Demand.Lisa Carter.json │ │ │ │ ├── Report for MultiLever- Strategies for Addressing Inflation and Enhancing Consumer Demand.Lisa Carter.md │ │ │ │ ├── Report for SolarWave Technologies- Strategies for Securing Funding for Solar Panel Project.Lisa Carter.docx │ │ │ │ ├── Report for SolarWave Technologies- Strategies for Securing Funding for Solar Panel Project.Lisa Carter.json │ │ │ │ ├── Report for SolarWave Technologies- Strategies for Securing Funding for Solar Panel Project.Lisa Carter.md │ │ │ │ ├── Report for TerraBuild- Strategies for Reducing Carbon Footprint and Improving Public Image.Lisa Carter.docx │ │ │ │ ├── Report for TerraBuild- Strategies for Reducing Carbon Footprint and Improving Public Image.Lisa Carter.json │ │ │ │ ├── Report for TerraBuild- Strategies for Reducing Carbon Footprint and Improving Public Image.Lisa Carter.md │ │ │ │ ├── Report for UrbanGreen- Strategies for Sustainable Urban Development Projects.Lisa Carter.docx │ │ │ │ ├── Report for UrbanGreen- Strategies for Sustainable Urban Development Projects.Lisa Carter.json │ │ │ │ └── Report for UrbanGreen- Strategies for Sustainable Urban Development Projects.Lisa Carter.md │ │ │ └── synthetic_data_example_2/ │ │ │ └── Document/ │ │ │ ├── Report for AquaPure- Sustainable Funding Model and Operational Efficiency Improvement.Lisa Carter.docx │ │ │ ├── Report for AquaPure- Sustainable Funding Model and Operational Efficiency Improvement.Lisa Carter.json │ │ │ ├── Report for AquaPure- Sustainable Funding Model and Operational Efficiency Improvement.Lisa Carter.md │ │ │ ├── Report for EcoTech Innovations- Strategies for Improving Visibility and Consumer Engagement.Lisa Carter.docx │ │ │ ├── Report for EcoTech Innovations- Strategies for Improving Visibility and Consumer Engagement.Lisa Carter.json │ │ │ ├── Report for EcoTech Innovations- Strategies for Improving Visibility and Consumer Engagement.Lisa Carter.md │ │ │ ├── Report for FinTech Nexus- Strategies for Competitive Advantage and Compliance Navigation.Lisa Carter.docx │ │ │ ├── Report for FinTech Nexus- Strategies for Competitive Advantage and Compliance Navigation.Lisa Carter.json │ │ │ ├── Report for FinTech Nexus- Strategies for Competitive Advantage and Compliance Navigation.Lisa Carter.md │ │ │ ├── Report for GreenWave Logistics- Sustainable Logistics Model Development.Lisa Carter.docx │ │ │ ├── Report for GreenWave Logistics- Sustainable Logistics Model Development.Lisa Carter.json │ │ │ ├── Report for GreenWave Logistics- Sustainable Logistics Model Development.Lisa Carter.md │ │ │ ├── Report for MedTech Solutions- Strategies for Regulatory Compliance and Market Penetration.Lisa Carter.docx │ │ │ ├── Report for MedTech Solutions- Strategies for Regulatory Compliance and Market Penetration.Lisa Carter.json │ │ │ ├── Report for MedTech Solutions- Strategies for Regulatory Compliance and Market Penetration.Lisa Carter.md │ │ │ ├── Report for MultiLever- Strategies to Address Inflation and Decreased Consumer Demand.Lisa Carter.docx │ │ │ ├── Report for MultiLever- Strategies to Address Inflation and Decreased Consumer Demand.Lisa Carter.json │ │ │ ├── Report for MultiLever- Strategies to Address Inflation and Decreased Consumer Demand.Lisa Carter.md │ │ │ ├── Report for SafeHaven- Strategies for Streamlining Claims Processing and Improving Communication.Lisa Carter.docx │ │ │ ├── Report for SafeHaven- Strategies for Streamlining Claims Processing and Improving Communication.Lisa Carter.json │ │ │ ├── Report for SafeHaven- Strategies for Streamlining Claims Processing and Improving Communication.Lisa Carter.md │ │ │ ├── Report for StellarTech- Streamlining Operations and Navigating Regulatory Compliance.Lisa Carter.docx │ │ │ ├── Report for StellarTech- Streamlining Operations and Navigating Regulatory Compliance.Lisa Carter.json │ │ │ ├── Report for StellarTech- Streamlining Operations and Navigating Regulatory Compliance.Lisa Carter.md │ │ │ ├── Report for TechSphere- Crisis Management and Cybersecurity Enhancement Strategies.Lisa Carter.docx │ │ │ ├── Report for TechSphere- Crisis Management and Cybersecurity Enhancement Strategies.Lisa Carter.json │ │ │ ├── Report for TechSphere- Crisis Management and Cybersecurity Enhancement Strategies.Lisa Carter.md │ │ │ ├── Report for UrbanGrow- Strategies for Addressing Climate Change and Supply Chain Disruptions.Lisa Carter.docx │ │ │ ├── Report for UrbanGrow- Strategies for Addressing Climate Change and Supply Chain Disruptions.Lisa Carter.json │ │ │ ├── Report for UrbanGrow- Strategies for Addressing Climate Change and Supply Chain Disruptions.Lisa Carter.md │ │ │ ├── Report for UrbanHealth- Comprehensive Outreach Strategy and Funding Proposal.Lisa Carter.docx │ │ │ ├── Report for UrbanHealth- Comprehensive Outreach Strategy and Funding Proposal.Lisa Carter.json │ │ │ └── Report for UrbanHealth- Comprehensive Outreach Strategy and Funding Proposal.Lisa Carter.md │ │ ├── food_products_brainstorming_2.json │ │ ├── fragments/ │ │ │ ├── aggressive_debater.fragment.json │ │ │ ├── authoritarian.agent.fragment.json │ │ │ ├── difficult_person.agent.fragment.json │ │ │ ├── leftwing.agent.fragment.json │ │ │ ├── libertarian.agent.fragment.json │ │ │ ├── loving_parent.agent.fragment.json │ │ │ ├── picky_customer.agent.fragment copy.json │ │ │ ├── picky_customer.agent.fragment.json │ │ │ └── rightwing.agent.fragment.json │ │ ├── information/ │ │ │ └── populations/ │ │ │ ├── brazil.json │ │ │ ├── china.json │ │ │ ├── india.json │ │ │ ├── mexico.json │ │ │ ├── norway.json │ │ │ ├── scandinavia.json │ │ │ └── usa.json │ │ ├── market_research_quantitative_experimentation_1.json │ │ ├── market_research_quantitative_experimentation_2.json │ │ ├── market_research_utils.py │ │ ├── opinion_poll_quantitative_experimentation_1.json │ │ ├── population/ │ │ │ ├── difficult_people/ │ │ │ │ ├── Benjamin Carter.agent.json │ │ │ │ ├── Benjamin Hall.agent.json │ │ │ │ ├── Chloe Turner.agent.json │ │ │ │ ├── Clara Johnson.agent.json │ │ │ │ ├── Clara White.agent.json │ │ │ │ ├── Ella Johnson.agent.json │ │ │ │ ├── Gabriel White.agent.json │ │ │ │ ├── Gavin Lewis.agent.json │ │ │ │ ├── Henry White.agent.json │ │ │ │ ├── Isaac Anderson.agent.json │ │ │ │ ├── Isaac Brooks.agent.json │ │ │ │ ├── Isaac Turner.agent.json │ │ │ │ ├── Jasmine Brooks.agent.json │ │ │ │ ├── Katherine Hall.agent.json │ │ │ │ ├── Liam Foster.agent.json │ │ │ │ ├── Nora Adams.agent.json │ │ │ │ ├── Nora Mitchell.agent.json │ │ │ │ ├── Sophie Johnson.agent.json │ │ │ │ ├── Victoria Hall.agent.json │ │ │ │ └── Zoe Mitchell.agent.json │ │ │ ├── global_general/ │ │ │ │ ├── Amelia Scott.agent.json │ │ │ │ ├── Ava Patel.agent.json │ │ │ │ ├── Benjamin Taylor.agent.json │ │ │ │ ├── Charlotte Nguyen.agent.json │ │ │ │ ├── Daniel Clark.agent.json │ │ │ │ ├── Daniel Evans.agent.json │ │ │ │ ├── Ella Lewis.agent.json │ │ │ │ ├── Emily Foster.agent.json │ │ │ │ ├── Emma Thompson.agent.json │ │ │ │ ├── Ethan Singh.agent.json │ │ │ │ ├── Grace Harris.agent.json │ │ │ │ ├── Isabella Martinez.agent.json │ │ │ │ ├── James Rodriguez.agent.json │ │ │ │ ├── Liam Chen.agent.json │ │ │ │ ├── Lily Carter.agent.json │ │ │ │ ├── Lucas Wilson.agent.json │ │ │ │ ├── Mason Brown.agent.json │ │ │ │ ├── Matthew Young.agent.json │ │ │ │ ├── Noah Kim.agent.json │ │ │ │ └── Samuel Turner.agent.json │ │ │ ├── mexico_general/ │ │ │ │ ├── Ana Maria Herrera.agent.json │ │ │ │ ├── Ana Maria Salazar.agent.json │ │ │ │ ├── Camila Rojas.agent.json │ │ │ │ ├── Camila Salazar.agent.json │ │ │ │ ├── Camila Torres.agent.json │ │ │ │ ├── Carlos Herrera.agent.json │ │ │ │ ├── Carlos Mendoza.agent.json │ │ │ │ ├── Diego Mendoza.agent.json │ │ │ │ ├── Diego Morales.agent.json │ │ │ │ ├── Diego Salazar.agent.json │ │ │ │ ├── Fernando Ramirez.agent.json │ │ │ │ ├── Isabel Gonzalez.agent.json │ │ │ │ ├── Isabel Rojas.agent.json │ │ │ │ ├── Isabella Rojas.agent.json │ │ │ │ ├── Lucia Morales.agent.json │ │ │ │ ├── Santiago Jimenez.agent.json │ │ │ │ ├── Santiago Rojas.agent.json │ │ │ │ ├── Valeria Jimenez.agent.json │ │ │ │ ├── Valeria Morales.agent.json │ │ │ │ └── Valeria Torres.agent.json │ │ │ ├── misc/ │ │ │ │ ├── Daniel Harris (Market Researcher).agent.json │ │ │ │ └── Oscar.agent.json │ │ │ ├── norway_general/ │ │ │ │ ├── Astrid Johansen.agent.json │ │ │ │ ├── Astrid Nilsen.agent.json │ │ │ │ ├── Astrid Sørensen.agent.json │ │ │ │ ├── Emil Bergstrom.agent.json │ │ │ │ ├── Emil Knudsen.agent.json │ │ │ │ ├── Freja Eriksen.agent.json │ │ │ │ ├── Freja Johansen.agent.json │ │ │ │ ├── Henrik Berg.agent.json │ │ │ │ ├── Henrik Eriksen.agent.json │ │ │ │ ├── Ingrid Knudsen.agent.json │ │ │ │ ├── Ingrid Lund.agent.json │ │ │ │ ├── Ingrid Madsen.agent.json │ │ │ │ ├── Ingrid Sørensen.agent.json │ │ │ │ ├── Kari Madsen.agent.json │ │ │ │ ├── Lars Nilsen.agent.json │ │ │ │ ├── Magnus Knudsen.agent.json │ │ │ │ ├── Magnus Sørensen.agent.json │ │ │ │ ├── Oskar Berg.agent.json │ │ │ │ ├── Sofie Lundgren.agent.json │ │ │ │ └── Sofie Sørensen.agent.json │ │ │ ├── political_compass/ │ │ │ │ ├── Aiden Lewis.agent.json │ │ │ │ ├── Benjamin Carter.agent.json │ │ │ │ ├── Chloe Mitchell.agent.json │ │ │ │ ├── Chloe White.agent.json │ │ │ │ ├── Ethan Brooks.agent.json │ │ │ │ ├── Ethan Rivera.agent.json │ │ │ │ ├── Ethan Young.agent.json │ │ │ │ ├── Evelyn Carter.agent.json │ │ │ │ ├── Grace Adams.agent.json │ │ │ │ ├── Henry Johnson.agent.json │ │ │ │ ├── Isabella Martinez.agent.json │ │ │ │ ├── Jessica Martinez.agent.json │ │ │ │ ├── Natalie Brown.agent.json │ │ │ │ ├── Noah Anderson.agent.json │ │ │ │ ├── Noah Davis.agent.json │ │ │ │ ├── Olivia Foster.agent.json │ │ │ │ ├── Olivia Harris.agent.json │ │ │ │ ├── Samuel Reed.agent.json │ │ │ │ ├── Sophia Lewis.agent.json │ │ │ │ └── Sophia Turner.agent.json │ │ │ ├── usa_couples/ │ │ │ │ ├── Aiden Garcia.agent.json │ │ │ │ ├── Aiden Lee.agent.json │ │ │ │ ├── Aiden Martinez.agent.json │ │ │ │ ├── Aiden Thompson.agent.json │ │ │ │ ├── Chloe Adams.agent.json │ │ │ │ ├── Chloe Garcia.agent.json │ │ │ │ ├── Chloe Kim.agent.json │ │ │ │ ├── David Kim.agent.json │ │ │ │ ├── David Nguyen.agent.json │ │ │ │ ├── David Patel.agent.json │ │ │ │ ├── David Wilson.agent.json │ │ │ │ ├── Ella Adams.agent.json │ │ │ │ ├── Ella Brown.agent.json │ │ │ │ ├── Ella Garcia.agent.json │ │ │ │ ├── Ella Johnson.agent.json │ │ │ │ ├── Ella Rodriguez.agent.json │ │ │ │ ├── Emily Chen.agent.json │ │ │ │ ├── Emily Rodriguez.agent.json │ │ │ │ ├── Grace Adams.agent.json │ │ │ │ ├── Grace Johnson.agent.json │ │ │ │ ├── Grace Nguyen.agent.json │ │ │ │ ├── Grace Patel.agent.json │ │ │ │ ├── Isabella Garcia.agent.json │ │ │ │ ├── Isabella Lee.agent.json │ │ │ │ ├── Isabella White.agent.json │ │ │ │ ├── James Brown.agent.json │ │ │ │ ├── James Nguyen.agent.json │ │ │ │ ├── James Patel.agent.json │ │ │ │ ├── James Thompson.agent.json │ │ │ │ ├── Lucas Kim.agent.json │ │ │ │ ├── Mia Carter.agent.json │ │ │ │ ├── Mia Garcia.agent.json │ │ │ │ ├── Mia Rodriguez.agent.json │ │ │ │ ├── Oliver Garcia.agent.json │ │ │ │ ├── Oliver Kim.agent.json │ │ │ │ ├── Oliver Thompson.agent.json │ │ │ │ ├── Sofia Johnson.agent.json │ │ │ │ ├── Sofia Kim.agent.json │ │ │ │ ├── Sofia Lee.agent.json │ │ │ │ └── Sofia Martinez.agent.json │ │ │ ├── usa_couples_2/ │ │ │ │ ├── Ava Carter-Moore.agent.json │ │ │ │ ├── Chloe Lee-Williams.agent.json │ │ │ │ ├── Chloe Nguyen-Smith.agent.json │ │ │ │ ├── Elena Carter-Jones.agent.json │ │ │ │ ├── Elena Martinez-Garcia.agent.json │ │ │ │ ├── Elena Martinez-Jones.agent.json │ │ │ │ ├── Elena Rodriguez.agent.json │ │ │ │ ├── Elijah Carter-Jones.agent.json │ │ │ │ ├── Gabriel Lee-Roberts.agent.json │ │ │ │ ├── Gabriel Lee-Smith.agent.json │ │ │ │ ├── Gabriel Lee-Williams.agent.json │ │ │ │ ├── Gabriel Martinez-Smith.agent.json │ │ │ │ ├── Isabella Carter-Jones.agent.json │ │ │ │ ├── Isabella Carter.agent.json │ │ │ │ ├── Isabella Kimball-Wong.agent.json │ │ │ │ ├── Isaiah Carter.agent.json │ │ │ │ ├── Isaiah Johnson-Smith.agent.json │ │ │ │ ├── Isaiah Patel-Garcia.agent.json │ │ │ │ ├── Jasper Lee-Roberts.agent.json │ │ │ │ ├── Jasper Nguyen-Williams.agent.json │ │ │ │ ├── Jasper Nguyen.agent.json │ │ │ │ ├── Liam Patel-Smith.agent.json │ │ │ │ ├── Liam Torres-Brown.agent.json │ │ │ │ ├── Liam Torres-Garcia.agent.json │ │ │ │ ├── Liam Torres-Moore.agent.json │ │ │ │ ├── Liam Torres-Smith.agent.json │ │ │ │ ├── Nina Hayes-Roberts.agent.json │ │ │ │ ├── Nina Johnson-Rivera.agent.json │ │ │ │ ├── Nina Robinson-Smith.agent.json │ │ │ │ ├── Nina Torres-Smith.agent.json │ │ │ │ ├── Oliver Hayes-Kim.agent.json │ │ │ │ ├── Oliver Hayes-Smith.agent.json │ │ │ │ ├── Oliver Martinez-Jones.agent.json │ │ │ │ ├── Samuel Lee-Patel.agent.json │ │ │ │ ├── Sofia Adams-Williams.agent.json │ │ │ │ ├── Sofia Johnson-Brown.agent.json │ │ │ │ ├── Sofia Patel-Jones.agent.json │ │ │ │ ├── Sofia Patel-Roberts.agent.json │ │ │ │ ├── Sofia Patel-Williams.agent.json │ │ │ │ ├── Victoria Adams-Garcia.agent.json │ │ │ │ ├── Victoria Adams-Kim.agent.json │ │ │ │ ├── Victoria Nguyen.agent.json │ │ │ │ ├── Zara Johnson-Kim.agent.json │ │ │ │ └── Zara Johnson-Smith.agent.json │ │ │ ├── usa_families/ │ │ │ │ ├── Aiden Brown.agent.json │ │ │ │ ├── Aiden Johnson.agent.json │ │ │ │ ├── Aiden Smith.agent.json │ │ │ │ ├── Benjamin Clark.agent.json │ │ │ │ ├── Benjamin Lee.agent.json │ │ │ │ ├── Benjamin Lewis.agent.json │ │ │ │ ├── Benjamin Scott.agent.json │ │ │ │ ├── Chloe Davis.agent.json │ │ │ │ ├── Chloe Harris.agent.json │ │ │ │ ├── Chloe Taylor.agent.json │ │ │ │ ├── Chloe White.agent.json │ │ │ │ ├── Chloe Wilson.agent.json │ │ │ │ ├── Ella Thompson.agent.json │ │ │ │ ├── Ella Wilson.agent.json │ │ │ │ ├── Emily Davis.agent.json │ │ │ │ ├── Emily Smith.agent.json │ │ │ │ ├── Emily Taylor.agent.json │ │ │ │ ├── Emily Wilson.agent.json │ │ │ │ ├── Ethan Smith.agent.json │ │ │ │ ├── Ethan Taylor.agent.json │ │ │ │ ├── Ethan Wilson.agent.json │ │ │ │ ├── Grace Martinez.agent.json │ │ │ │ ├── Grace Taylor.agent.json │ │ │ │ ├── Grace Wilson.agent.json │ │ │ │ ├── Jackson Lee.agent.json │ │ │ │ ├── Jackson White.agent.json │ │ │ │ ├── James Anderson.agent.json │ │ │ │ ├── James Taylor.agent.json │ │ │ │ ├── Lucas Anderson.agent.json │ │ │ │ ├── Lucas Brown.agent.json │ │ │ │ ├── Lucas Davis.agent.json │ │ │ │ ├── Lucas Martinez.agent.json │ │ │ │ ├── Lucas Taylor.agent.json │ │ │ │ ├── Lucas White.agent.json │ │ │ │ ├── Mia Anderson.agent.json │ │ │ │ ├── Mia Johnson.agent.json │ │ │ │ ├── Mia Thompson.agent.json │ │ │ │ ├── Oliver Davis.agent.json │ │ │ │ ├── Oliver Johnson.agent.json │ │ │ │ ├── Oliver Smith.agent.json │ │ │ │ ├── Sofia Anderson.agent.json │ │ │ │ ├── Sofia Brown.agent.json │ │ │ │ ├── Sofia Clark.agent.json │ │ │ │ ├── Sofia Davis.agent.json │ │ │ │ └── Sofia White.agent.json │ │ │ ├── usa_families_2/ │ │ │ │ ├── Avery Martinez.agent.json │ │ │ │ ├── Chloe White.agent.json │ │ │ │ ├── Dante Brooks.agent.json │ │ │ │ ├── Dante Hayes.agent.json │ │ │ │ ├── Dante Kim.agent.json │ │ │ │ ├── Elena Garcia.agent.json │ │ │ │ ├── Elena Martinez-Williams.agent.json │ │ │ │ ├── Elena Martinez.agent.json │ │ │ │ ├── Elijah Carter-Williams.agent.json │ │ │ │ ├── Elijah Johnson.agent.json │ │ │ │ ├── Ethan Brooks.agent.json │ │ │ │ ├── Ethan Carter.agent.json │ │ │ │ ├── Ethan Ramirez.agent.json │ │ │ │ ├── Gabriel Lee-Moore.agent.json │ │ │ │ ├── Gabriel Martinez.agent.json │ │ │ │ ├── Gabriel Torres-Moore.agent.json │ │ │ │ ├── Gabriel Torres.agent.json │ │ │ │ ├── Isabella Martinez-Garcia.agent.json │ │ │ │ ├── Isabella Martinez.agent.json │ │ │ │ ├── Isaiah Ramirez.agent.json │ │ │ │ ├── Jasper Martinez.agent.json │ │ │ │ ├── Julian Hayes-Smith.agent.json │ │ │ │ ├── Liam Carter-Smith.agent.json │ │ │ │ ├── Liam Carter.agent.json │ │ │ │ ├── Liam Harris.agent.json │ │ │ │ ├── Liam Rivera-Sanchez.agent.json │ │ │ │ ├── Liam Rivera.agent.json │ │ │ │ ├── Lucas Thompson.agent.json │ │ │ │ ├── Mason Brown.agent.json │ │ │ │ ├── Mason Carter.agent.json │ │ │ │ ├── Maya Johnson-Smith.agent.json │ │ │ │ ├── Nina Foster.agent.json │ │ │ │ ├── Nina Patel.agent.json │ │ │ │ ├── Nina Robinson.agent.json │ │ │ │ ├── Nina Torres-Garcia.agent.json │ │ │ │ ├── Nina Torres.agent.json │ │ │ │ ├── Rafael Adams.agent.json │ │ │ │ ├── Rafael Torres.agent.json │ │ │ │ ├── Samuel White-Blackwell.agent.json │ │ │ │ ├── Sofia Adams.agent.json │ │ │ │ ├── Sofia Bennett.agent.json │ │ │ │ ├── Sofia Johnson.agent.json │ │ │ │ ├── Sophia Brown.agent.json │ │ │ │ ├── Talia Brooks.agent.json │ │ │ │ ├── Talia Hayes.agent.json │ │ │ │ ├── Talia Robinson.agent.json │ │ │ │ ├── Victoria Adams-Brown.agent.json │ │ │ │ ├── Victoria Torres.agent.json │ │ │ │ ├── Zara Patel.agent.json │ │ │ │ ├── Zara Thompson-Jones.agent.json │ │ │ │ └── Zara Thompson.agent.json │ │ │ ├── usa_general/ │ │ │ │ ├── Aiden Brooks.agent.json │ │ │ │ ├── Ashley Wilson.agent.json │ │ │ │ ├── Charlotte Cooper.agent.json │ │ │ │ ├── Christopher Lee.agent.json │ │ │ │ ├── David Anderson.agent.json │ │ │ │ ├── Ethan Foster.agent.json │ │ │ │ ├── Ethan Scott.agent.json │ │ │ │ ├── Henry Murphy.agent.json │ │ │ │ ├── Isabella Young.agent.json │ │ │ │ ├── Jackson Ward.agent.json │ │ │ │ ├── James Carter.agent.json │ │ │ │ ├── Jessica Martinez.agent.json │ │ │ │ ├── Lucas Carter.agent.json │ │ │ │ ├── Lucas Hall.agent.json │ │ │ │ ├── Matthew Robinson.agent.json │ │ │ │ ├── Michael Thompson.agent.json │ │ │ │ ├── Olivia Bennett.agent.json │ │ │ │ ├── Olivia Harris.agent.json │ │ │ │ ├── Sarah Brown.agent.json │ │ │ │ └── Zoe Rivera.agent.json │ │ │ ├── usa_picky/ │ │ │ │ ├── Amelia Lewis.agent.json │ │ │ │ ├── Benjamin Young.agent.json │ │ │ │ ├── Charlotte Clark.agent.json │ │ │ │ ├── Chloe Anderson.agent.json │ │ │ │ ├── Ella Martin.agent.json │ │ │ │ ├── Emily Johnson.agent.json │ │ │ │ ├── Ethan Wilson.agent.json │ │ │ │ ├── Grace Allen.agent.json │ │ │ │ ├── Grace White.agent.json │ │ │ │ ├── Henry Walker.agent.json │ │ │ │ ├── James Williams.agent.json │ │ │ │ ├── Lucas Thompson.agent.json │ │ │ │ ├── Lucas Young.agent.json │ │ │ │ ├── Mason Taylor.agent.json │ │ │ │ ├── Noah Rodriguez.agent.json │ │ │ │ ├── Oliver Harris.agent.json │ │ │ │ ├── Olivia Jones.agent.json │ │ │ │ ├── Scarlett Hall.agent.json │ │ │ │ ├── Victoria King.agent.json │ │ │ │ └── Zoe King.agent.json │ │ │ ├── usa_singles/ │ │ │ │ ├── Aiden Foster.agent.json │ │ │ │ ├── Ashley Brown.agent.json │ │ │ │ ├── Ava Cooper.agent.json │ │ │ │ ├── Ava Patel.agent.json │ │ │ │ ├── Ava Scott.agent.json │ │ │ │ ├── Chloe Nguyen.agent.json │ │ │ │ ├── Chloe Ramirez.agent.json │ │ │ │ ├── Chloe Reed.agent.json │ │ │ │ ├── Christopher Garcia.agent.json │ │ │ │ ├── Daniel Anderson.agent.json │ │ │ │ ├── David Lee.agent.json │ │ │ │ ├── Ella Murphy.agent.json │ │ │ │ ├── Emily Johnson.agent.json │ │ │ │ ├── Ethan Brooks.agent.json │ │ │ │ ├── Ethan Clark.agent.json │ │ │ │ ├── Ethan Ramirez.agent.json │ │ │ │ ├── Isabella Brooks.agent.json │ │ │ │ ├── Isabella Foster.agent.json │ │ │ │ ├── Isabella Green.agent.json │ │ │ │ ├── Isabella Patel.agent.json │ │ │ │ ├── Isabella Turner.agent.json │ │ │ │ ├── Jackson Green.agent.json │ │ │ │ ├── James Wilson.agent.json │ │ │ │ ├── Jessica Martinez.agent.json │ │ │ │ ├── Laura White.agent.json │ │ │ │ ├── Liam Carter.agent.json │ │ │ │ ├── Liam Foster.agent.json │ │ │ │ ├── Liam Patel.agent.json │ │ │ │ ├── Liam Young.agent.json │ │ │ │ ├── Lucas Harris.agent.json │ │ │ │ ├── Lucas Wright.agent.json │ │ │ │ ├── Mason Lee.agent.json │ │ │ │ ├── Mason Reed.agent.json │ │ │ │ ├── Mason Rivera.agent.json │ │ │ │ ├── Michael Thompson.agent.json │ │ │ │ ├── Noah Brooks.agent.json │ │ │ │ ├── Noah Carter.agent.json │ │ │ │ ├── Noah King.agent.json │ │ │ │ ├── Olivia Harris.agent.json │ │ │ │ ├── Sarah Robinson.agent.json │ │ │ │ ├── Sophia Lewis.agent.json │ │ │ │ ├── Sophia Turner.agent.json │ │ │ │ ├── Zoe Cooper.agent.json │ │ │ │ ├── Zoe Thompson.agent.json │ │ │ │ └── Zoe Turner.agent.json │ │ │ └── usa_singles_2/ │ │ │ ├── Amelia Foster.agent.json │ │ │ ├── Amelia Torres.agent.json │ │ │ ├── Ava Martinez.agent.json │ │ │ ├── Charlotte Evans.agent.json │ │ │ ├── Charlotte Nguyen.agent.json │ │ │ ├── Chloe Bennett.agent.json │ │ │ ├── Chloe Martinez.agent.json │ │ │ ├── Chloe Nguyen.agent.json │ │ │ ├── Chloe Ramirez.agent.json │ │ │ ├── Daniel Foster.agent.json │ │ │ ├── David Lee.agent.json │ │ │ ├── Emily Chen.agent.json │ │ │ ├── Ethan Kim.agent.json │ │ │ ├── Evelyn Brooks-Johnson.agent.json │ │ │ ├── Evelyn Brooks.agent.json │ │ │ ├── Evelyn Martinez.agent.json │ │ │ ├── Gabriel Scott.agent.json │ │ │ ├── Grace Mitchell.agent.json │ │ │ ├── Grace Nguyen.agent.json │ │ │ ├── Henry Adams.agent.json │ │ │ ├── Henry Mitchell.agent.json │ │ │ ├── Isaac Johnson.agent.json │ │ │ ├── Isabella Garcia.agent.json │ │ │ ├── Isabella Wright.agent.json │ │ │ ├── Isaiah Patel.agent.json │ │ │ ├── Jackson Wright.agent.json │ │ │ ├── James Anderson.agent.json │ │ │ ├── Jaxon Rivera.agent.json │ │ │ ├── Julian Grant.agent.json │ │ │ ├── Julian Hayes.agent.json │ │ │ ├── Liam Johnson.agent.json │ │ │ ├── Lily Carter.agent.json │ │ │ ├── Lily Foster.agent.json │ │ │ ├── Lily Nguyen.agent.json │ │ │ ├── Lucas Ramirez.agent.json │ │ │ ├── Luna Hayes.agent.json │ │ │ ├── Madison Reed.agent.json │ │ │ ├── Madison Torres.agent.json │ │ │ ├── Mason Reed.agent.json │ │ │ ├── Mia Robinson.agent.json │ │ │ ├── Michael Thompson.agent.json │ │ │ ├── Natalie Torres.agent.json │ │ │ ├── Nathaniel Scott.agent.json │ │ │ ├── Noah Lewis.agent.json │ │ │ ├── Nora Kim.agent.json │ │ │ ├── Oliver Brooks.agent.json │ │ │ ├── Olivia Garcia.agent.json │ │ │ ├── Olivia Turner.agent.json │ │ │ ├── Olivia Walker.agent.json │ │ │ ├── Samantha Lee.agent.json │ │ │ ├── Samantha Reed.agent.json │ │ │ ├── Scarlett Nguyen.agent.json │ │ │ ├── Sofia Martinez.agent.json │ │ │ ├── Sophia Carter.agent.json │ │ │ └── Sophia Patel.agent.json │ │ └── spicy_product_market_research.json │ └── paper_artifacts_october-2025/ │ ├── Brainstorming and Focus Group Quantitative Experimentation 1 (Treatment run).ipynb │ ├── Brainstorming and Focus Group Quantitative Experimentation 1.ipynb │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.1 (Treatment run).ipynb │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.1.ipynb │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.2 (Treatment run).ipynb │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.2.ipynb │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.3 (Treatment run).ipynb │ ├── Brainstorming and Focus Group Quantitative Experimentation 2.3.ipynb │ ├── Food Products Ideas Brainstorming.ipynb │ ├── Paper Charts and Plots.ipynb │ ├── Political Compass (customizing agents with fragments).ipynb │ ├── Populations creation.ipynb │ ├── Synthetic Data Generation.ipynb │ ├── Travel Product Market Research (with behavior correction).ipynb │ ├── Travel Product Market Research 2.ipynb │ ├── Travel Product Market Research 2b (with behavior correction).ipynb │ ├── Travel Product Market Research 2b.ipynb │ ├── Travel Product Market Research 2c (with behavior correction).ipynb │ ├── Travel Product Market Research.ipynb │ ├── action_correction_example.txt │ ├── brainstorming_and_focus_group_quantitative_experimentation_1.json │ ├── brainstorming_and_focus_group_quantitative_experimentation_1b.json │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.1c.json │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.1d.json │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.1e.json │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.1f.json │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.2b.json │ ├── brainstorming_and_focus_group_quantitative_experimentation_2.3.json │ ├── common_utils.py │ ├── config.ini │ ├── debating_quantitative_experimentation_1c.json │ ├── extractions/ │ │ └── synthetic_data_example_3/ │ │ └── Document/ │ │ ├── Asteria Conservatory — Emergency Response Report & 10‑Day Action Plan.Lisa Carter.docx │ │ ├── Asteria Conservatory — Emergency Response Report & 10‑Day Action Plan.Lisa Carter.json │ │ ├── Asteria Conservatory — Emergency Response Report & 10‑Day Action Plan.Lisa Carter.md │ │ ├── BlueHarbor – Rapid Scoping Report- Microgrid Options, Immediate Asks & 6-week Plan.Lisa Carter.docx │ │ ├── BlueHarbor – Rapid Scoping Report- Microgrid Options, Immediate Asks & 6-week Plan.Lisa Carter.json │ │ ├── BlueHarbor – Rapid Scoping Report- Microgrid Options, Immediate Asks & 6-week Plan.Lisa Carter.md │ │ ├── GreenRiver Rapid-Response Report — 48h Needs Assessment & Pilot Plan (Draft).Lisa Carter.docx │ │ ├── GreenRiver Rapid-Response Report — 48h Needs Assessment & Pilot Plan (Draft).Lisa Carter.json │ │ ├── GreenRiver Rapid-Response Report — 48h Needs Assessment & Pilot Plan (Draft).Lisa Carter.md │ │ ├── Halcyon Air — Initial Recovery & Regulator-Lender Outreach Report (Draft).Lisa Carter.docx │ │ ├── Halcyon Air — Initial Recovery & Regulator-Lender Outreach Report (Draft).Lisa Carter.json │ │ ├── Halcyon Air — Initial Recovery & Regulator-Lender Outreach Report (Draft).Lisa Carter.md │ │ ├── Highland Coffee Cooperative — Recovery & Traceability Plan (Draft).Lisa Carter.docx │ │ ├── Highland Coffee Cooperative — Recovery & Traceability Plan (Draft).Lisa Carter.json │ │ ├── Highland Coffee Cooperative — Recovery & Traceability Plan (Draft).Lisa Carter.md │ │ ├── IronCliff Emergency Stabilisation & Community Protection Plan — Draft Short Report.Lisa Carter.docx │ │ ├── IronCliff Emergency Stabilisation & Community Protection Plan — Draft Short Report.Lisa Carter.json │ │ ├── IronCliff Emergency Stabilisation & Community Protection Plan — Draft Short Report.Lisa Carter.md │ │ ├── MultiLever Rapid Diagnostic & Action Plan.Lisa Carter.docx │ │ ├── MultiLever Rapid Diagnostic & Action Plan.Lisa Carter.json │ │ ├── MultiLever Rapid Diagnostic & Action Plan.Lisa Carter.md │ │ ├── MultiLever — Rapid Diagnostic & Action Plan (Inflation & Demand Shock).Lisa Carter.docx │ │ ├── MultiLever — Rapid Diagnostic & Action Plan (Inflation & Demand Shock).Lisa Carter.json │ │ ├── MultiLever — Rapid Diagnostic & Action Plan (Inflation & Demand Shock).Lisa Carter.md │ │ ├── MultiLever — Rapid Diagnostic & Action Plan for Demand Shortfall.Lisa Carter, Wild Advice Partners.docx │ │ ├── MultiLever — Rapid Diagnostic & Action Plan for Demand Shortfall.Lisa Carter, Wild Advice Partners.json │ │ ├── MultiLever — Rapid Diagnostic & Action Plan for Demand Shortfall.Lisa Carter, Wild Advice Partners.md │ │ ├── MultiLever- Rapid Diagnostic & Action Plan for Demand Recovery.Lisa Carter.docx │ │ ├── MultiLever- Rapid Diagnostic & Action Plan for Demand Recovery.Lisa Carter.json │ │ ├── MultiLever- Rapid Diagnostic & Action Plan for Demand Recovery.Lisa Carter.md │ │ ├── ZephyrPay — AML Remediation & Model Audit- 3-week plan.Lisa Carter.docx │ │ ├── ZephyrPay — AML Remediation & Model Audit- 3-week plan.Lisa Carter.json │ │ └── ZephyrPay — AML Remediation & Model Audit- 3-week plan.Lisa Carter.md │ ├── food_products_brainstorming_2.json │ ├── fragments/ │ │ ├── aggressive_debater.fragment.json │ │ ├── authoritarian.agent.fragment.json │ │ ├── difficult_person.agent.fragment.json │ │ ├── leftwing.agent.fragment.json │ │ ├── libertarian.agent.fragment.json │ │ ├── loving_parent.agent.fragment.json │ │ ├── picky_customer.agent.fragment copy.json │ │ ├── picky_customer.agent.fragment.json │ │ └── rightwing.agent.fragment.json │ ├── information/ │ │ └── populations/ │ │ ├── brazil.json │ │ ├── china.json │ │ ├── india.json │ │ ├── mexico.json │ │ ├── norway.json │ │ ├── scandinavia.json │ │ └── usa.json │ ├── market_research_utils.py │ ├── population/ │ │ ├── company_2/ │ │ │ ├── Alan Merrick.agent.json │ │ │ ├── Anthony Russo.agent.json │ │ │ ├── Anya Calder-Mori.agent.json │ │ │ ├── Barbara Jean Pratt.agent.json │ │ │ ├── Colin Arthur Matthews.agent.json │ │ │ ├── Colin Murray.agent.json │ │ │ ├── Connor Walsh.agent.json │ │ │ ├── Darren McCall.agent.json │ │ │ ├── Dean Bartlett.agent.json │ │ │ ├── Declan Blackwell.agent.json │ │ │ ├── Edgar Milton Crane.agent.json │ │ │ ├── Leonard Victor Hale.agent.json │ │ │ ├── Mildred Agnes Hargreaves.agent.json │ │ │ ├── Ruby Mae Thornton.agent.json │ │ │ ├── Rupert Langley-Smythe.agent.json │ │ │ ├── Sloane Amaya Bexley.agent.json │ │ │ ├── Stanley Burke.agent.json │ │ │ ├── Tyler James Banks.agent.json │ │ │ ├── Tyrell Hayes.agent.json │ │ │ └── Vivian Hyejin Hwang.agent.json │ │ ├── difficult_people_2/ │ │ │ ├── Alan Merrick.agent.json │ │ │ ├── Anthony Russo.agent.json │ │ │ ├── Anya Calder-Mori.agent.json │ │ │ ├── Barbara Jean Pratt.agent.json │ │ │ ├── Colin Arthur Matthews.agent.json │ │ │ ├── Colin Murray.agent.json │ │ │ ├── Connor Walsh.agent.json │ │ │ ├── Darren McCall.agent.json │ │ │ ├── Dean Bartlett.agent.json │ │ │ ├── Declan Blackwell.agent.json │ │ │ ├── Edgar Milton Crane.agent.json │ │ │ ├── Leonard Victor Hale.agent.json │ │ │ ├── Mildred Agnes Hargreaves.agent.json │ │ │ ├── Ruby Mae Thornton.agent.json │ │ │ ├── Rupert Langley-Smythe.agent.json │ │ │ ├── Sloane Amaya Bexley.agent.json │ │ │ ├── Stanley Burke.agent.json │ │ │ ├── Tyler James Banks.agent.json │ │ │ ├── Tyrell Hayes.agent.json │ │ │ └── Vivian Hyejin Hwang.agent.json │ │ ├── global_general_2/ │ │ │ ├── Adam Kamara.agent.json │ │ │ ├── Ahmet Demir.agent.json │ │ │ ├── Alex Cruz.agent.json │ │ │ ├── Alexander Beaumont.agent.json │ │ │ ├── Aman Mehra.agent.json │ │ │ ├── Asha Okoye.agent.json │ │ │ ├── Diego Chen López.agent.json │ │ │ ├── Hikaru Sato.agent.json │ │ │ ├── Hinewai Te Rangi.agent.json │ │ │ ├── Isabela Rivera.agent.json │ │ │ ├── Jordan Navarro.agent.json │ │ │ ├── Khadija Diallo.agent.json │ │ │ ├── Kiran Ndlovu.agent.json │ │ │ ├── Mariama Diallo.agent.json │ │ │ ├── Mariana Chen.agent.json │ │ │ ├── Meera Sharma.agent.json │ │ │ ├── Morgan Schmidt.agent.json │ │ │ ├── Riley Ajani.agent.json │ │ │ ├── Sunita Devi.agent.json │ │ │ └── Taylor Novak.agent.json │ │ ├── mexico_general_2/ │ │ │ ├── Alexis Romero Aguilar.agent.json │ │ │ ├── Camila Fernanda Santillán Méndez.agent.json │ │ │ ├── Carlos Alberto Navarro López.agent.json │ │ │ ├── Claudia Murillo Aguilar.agent.json │ │ │ ├── Dominga Chilón Gómez.agent.json │ │ │ ├── Federico Treviño Sada.agent.json │ │ │ ├── Fernando Alejandro Salas Ortega.agent.json │ │ │ ├── Gael Emiliano Zamora.agent.json │ │ │ ├── Jorge Luis Nájera Morales.agent.json │ │ │ ├── José Guadalupe Martínez Cruz.agent.json │ │ │ ├── María Concepción Téllez Zapata.agent.json │ │ │ ├── María Elena Sandoval Cruz.agent.json │ │ │ ├── María Guadalupe López Juárez.agent.json │ │ │ ├── María Soledad López.agent.json │ │ │ ├── María de la Luz Pacheco Ramos.agent.json │ │ │ ├── María del Rosario Ríos Valencia.agent.json │ │ │ ├── Raúl Alejandro Paredes López.agent.json │ │ │ ├── Raúl Enrique Velázquez Cruz.agent.json │ │ │ ├── Renata Lucero Montes.agent.json │ │ │ └── Rosa Elena Méndez.agent.json │ │ ├── norway_general_2/ │ │ │ ├── Anna Nowak.agent.json │ │ │ ├── Bjørn Arvid Lunde.agent.json │ │ │ ├── Einar Folke Brekke.agent.json │ │ │ ├── Emilie Solheim.agent.json │ │ │ ├── Helga Kristoffersen.agent.json │ │ │ ├── Ingrid Elise Berg.agent.json │ │ │ ├── Ingrid Olsen.agent.json │ │ │ ├── Kari Karlsen.agent.json │ │ │ ├── Kristian Solbakken.agent.json │ │ │ ├── Line Marie Hansen.agent.json │ │ │ ├── Marek Kowalski.agent.json │ │ │ ├── Mika Nguyen-Berg.agent.json │ │ │ ├── Noah Henrik Berg.agent.json │ │ │ ├── Odin Holmvik.agent.json │ │ │ ├── Oskar Haugland.agent.json │ │ │ ├── Per Harald Kristiansen.agent.json │ │ │ ├── Piotr Nowak.agent.json │ │ │ ├── Ragnhild Hansen.agent.json │ │ │ ├── Sigrid Margrethe Nilsen.agent.json │ │ │ └── Sofie Haugen.agent.json │ │ ├── political_compass_2/ │ │ │ ├── Adelaida Vargas.agent.json │ │ │ ├── Aiko Rivera-Nakano.agent.json │ │ │ ├── Alex Malinowski.agent.json │ │ │ ├── Caleb Reynolds.agent.json │ │ │ ├── Casey Buchanan.agent.json │ │ │ ├── Etta June Harper.agent.json │ │ │ ├── Grant Emerson Caldwell.agent.json │ │ │ ├── Harold Eugene Thompson.agent.json │ │ │ ├── Harrison Cole.agent.json │ │ │ ├── Isabella Cruz-Nguyen.agent.json │ │ │ ├── Isla Moreno-Grant.agent.json │ │ │ ├── Malcolm Andre Whitaker.agent.json │ │ │ ├── Malia Begay.agent.json │ │ │ ├── Maya Park-Sullivan.agent.json │ │ │ ├── Nina Morales.agent.json │ │ │ ├── Quinn Langford.agent.json │ │ │ ├── Samir Ali Haddad.agent.json │ │ │ ├── Spencer Caldwell.agent.json │ │ │ ├── Tamsin Reid.agent.json │ │ │ └── Taylor Cruz.agent.json │ │ ├── usa_couples_2/ │ │ │ ├── Alex Larson.agent.json │ │ │ ├── Andrew Maxwell Porter.agent.json │ │ │ ├── Ava Carter-Moore.agent.json │ │ │ ├── Beatrice Lorraine Grant.agent.json │ │ │ ├── Bernice Henderson.agent.json │ │ │ ├── Blair Wentworth.agent.json │ │ │ ├── Caroline Margaret Bennett.agent.json │ │ │ ├── Catherine Langford.agent.json │ │ │ ├── Chloe Lee-Williams.agent.json │ │ │ ├── Chloe Nguyen-Smith.agent.json │ │ │ ├── Daniel Park.agent.json │ │ │ ├── Daniel Wei Liu.agent.json │ │ │ ├── Derek Malone.agent.json │ │ │ ├── Eleanor June Bennett.agent.json │ │ │ ├── Eleanor Whitman.agent.json │ │ │ ├── Elena Carter-Jones.agent.json │ │ │ ├── Elena Marquez.agent.json │ │ │ ├── Elena Martinez-Garcia.agent.json │ │ │ ├── Elena Martinez-Jones.agent.json │ │ │ ├── Elena Rodriguez.agent.json │ │ │ ├── Elijah Carter-Jones.agent.json │ │ │ ├── Eric Thompson.agent.json │ │ │ ├── Gabriel Lee-Roberts.agent.json │ │ │ ├── Gabriel Lee-Smith.agent.json │ │ │ ├── Gabriel Lee-Williams.agent.json │ │ │ ├── Gabriel Martinez-Smith.agent.json │ │ │ ├── Gregory Miles Anderson.agent.json │ │ │ ├── Harper Lin.agent.json │ │ │ ├── Isabel Valenzuela.agent.json │ │ │ ├── Isabella Carter-Jones.agent.json │ │ │ ├── Isabella Carter.agent.json │ │ │ ├── Isabella Kimball-Wong.agent.json │ │ │ ├── Isaiah Carter.agent.json │ │ │ ├── Isaiah Johnson-Smith.agent.json │ │ │ ├── Isaiah Patel-Garcia.agent.json │ │ │ ├── Janet Holden.agent.json │ │ │ ├── Janice Foley.agent.json │ │ │ ├── Jason Chen.agent.json │ │ │ ├── Jasper Lee-Roberts.agent.json │ │ │ ├── Jasper Nguyen-Williams.agent.json │ │ │ ├── Jasper Nguyen.agent.json │ │ │ ├── José Emilio Muñoz.agent.json │ │ │ ├── Leroy Anthony Booker.agent.json │ │ │ ├── Levi Nelson.agent.json │ │ │ ├── Liam Patel-Smith.agent.json │ │ │ ├── Liam Torres-Brown.agent.json │ │ │ ├── Liam Torres-Garcia.agent.json │ │ │ ├── Liam Torres-Moore.agent.json │ │ │ ├── Liam Torres-Smith.agent.json │ │ │ ├── Lucas Park.agent.json │ │ │ ├── Lucia Morales.agent.json │ │ │ ├── Luis Alejandro Perez.agent.json │ │ │ ├── Manuel Gonzalez.agent.json │ │ │ ├── Mariana Alvarez.agent.json │ │ │ ├── Marjorie Claire Ellis.agent.json │ │ │ ├── Mark Weber.agent.json │ │ │ ├── Mateo Javier Ramos.agent.json │ │ │ ├── Mateo Santiago Ortega.agent.json │ │ │ ├── Monica Patrice Grant.agent.json │ │ │ ├── Nina Hayes-Roberts.agent.json │ │ │ ├── Nina Johnson-Rivera.agent.json │ │ │ ├── Nina Robinson-Smith.agent.json │ │ │ ├── Nina Torres-Smith.agent.json │ │ │ ├── Oliver Hayes-Kim.agent.json │ │ │ ├── Oliver Hayes-Smith.agent.json │ │ │ ├── Oliver Martinez-Jones.agent.json │ │ │ ├── Owen Larson.agent.json │ │ │ ├── Paloma Sofia Ruiz.agent.json │ │ │ ├── Reese Choi-Walker.agent.json │ │ │ ├── Rohan Patel.agent.json │ │ │ ├── Samuel Lee-Patel.agent.json │ │ │ ├── Sofia Adams-Williams.agent.json │ │ │ ├── Sofia Johnson-Brown.agent.json │ │ │ ├── Sofia Patel-Jones.agent.json │ │ │ ├── Sofia Patel-Roberts.agent.json │ │ │ ├── Sofia Patel-Williams.agent.json │ │ │ ├── Victoria Adams-Garcia.agent.json │ │ │ ├── Victoria Adams-Kim.agent.json │ │ │ ├── Victoria Nguyen.agent.json │ │ │ ├── Walter Eugene Brooks.agent.json │ │ │ ├── William Otis Jones.agent.json │ │ │ ├── Yvonne Harris.agent.json │ │ │ ├── Zara Johnson-Kim.agent.json │ │ │ └── Zara Johnson-Smith.agent.json │ │ ├── usa_families_2/ │ │ │ ├── Agnes Lorraine Hughes.agent.json │ │ │ ├── Amara Hollingsworth.agent.json │ │ │ ├── Amari Sullivan.agent.json │ │ │ ├── Arden Brooks.agent.json │ │ │ ├── Ari Delgado.agent.json │ │ │ ├── Avery Martinez.agent.json │ │ │ ├── Carlos Rivera.agent.json │ │ │ ├── Cecilia Hartmann.agent.json │ │ │ ├── Celeste Rutherford.agent.json │ │ │ ├── Chloe White.agent.json │ │ │ ├── Clara Westwood.agent.json │ │ │ ├── Dante Brooks.agent.json │ │ │ ├── Dante Hayes.agent.json │ │ │ ├── Dante Kim.agent.json │ │ │ ├── Darla Jean McKenzie.agent.json │ │ │ ├── Darlene Whitcomb.agent.json │ │ │ ├── Diane Ruth Whitaker.agent.json │ │ │ ├── Earlene Mae Donovan.agent.json │ │ │ ├── Eden Morales.agent.json │ │ │ ├── Eleanor Hayes.agent.json │ │ │ ├── Elena Garcia.agent.json │ │ │ ├── Elena Martinez-Williams.agent.json │ │ │ ├── Elena Martinez.agent.json │ │ │ ├── Eleni Parker.agent.json │ │ │ ├── Elijah Carter-Williams.agent.json │ │ │ ├── Elijah Johnson.agent.json │ │ │ ├── Ellis Davenport.agent.json │ │ │ ├── Emerson Tran.agent.json │ │ │ ├── Erica Santos.agent.json │ │ │ ├── Ethan Brooks.agent.json │ │ │ ├── Ethan Carter.agent.json │ │ │ ├── Ethan Ramirez.agent.json │ │ │ ├── Evelyn Moreno.agent.json │ │ │ ├── Gabriel Lee-Moore.agent.json │ │ │ ├── Gabriel Martinez.agent.json │ │ │ ├── Gabriel Torres-Moore.agent.json │ │ │ ├── Gabriel Torres.agent.json │ │ │ ├── Isabella Martinez-Garcia.agent.json │ │ │ ├── Isabella Martinez.agent.json │ │ │ ├── Isaiah Ramirez.agent.json │ │ │ ├── Jada Moreno.agent.json │ │ │ ├── Jasper Martinez.agent.json │ │ │ ├── Jordan Blake.agent.json │ │ │ ├── Julian Hayes-Smith.agent.json │ │ │ ├── Leah Baxter.agent.json │ │ │ ├── Liam Carter-Smith.agent.json │ │ │ ├── Liam Carter.agent.json │ │ │ ├── Liam Harris.agent.json │ │ │ ├── Liam Rivera-Sanchez.agent.json │ │ │ ├── Liam Rivera.agent.json │ │ │ ├── Linda Mae Thompson.agent.json │ │ │ ├── Lucas Thompson.agent.json │ │ │ ├── Lydia Mercer.agent.json │ │ │ ├── Mabel Jean Hawkins.agent.json │ │ │ ├── Mason Brown.agent.json │ │ │ ├── Mason Carter.agent.json │ │ │ ├── Maya Johnson-Smith.agent.json │ │ │ ├── Mildred Louise Hargrove.agent.json │ │ │ ├── Morgan Hayes.agent.json │ │ │ ├── Nina Foster.agent.json │ │ │ ├── Nina Patel.agent.json │ │ │ ├── Nina Robinson.agent.json │ │ │ ├── Nina Torres-Garcia.agent.json │ │ │ ├── Nina Torres.agent.json │ │ │ ├── Norma Jean Carmichael.agent.json │ │ │ ├── Norman Lee Carter.agent.json │ │ │ ├── Olivia Kensington.agent.json │ │ │ ├── Rafael Adams.agent.json │ │ │ ├── Rafael Torres.agent.json │ │ │ ├── Remy Alvarez.agent.json │ │ │ ├── Riya Desai.agent.json │ │ │ ├── Rowan Ellis.agent.json │ │ │ ├── Rowan Sinclair.agent.json │ │ │ ├── Sammy Jo Carter.agent.json │ │ │ ├── Samuel White-Blackwell.agent.json │ │ │ ├── Sharon Ellis.agent.json │ │ │ ├── Skyler Nguyen-Pham.agent.json │ │ │ ├── Sofia Adams.agent.json │ │ │ ├── Sofia Bennett.agent.json │ │ │ ├── Sofia Johnson.agent.json │ │ │ ├── Sophia Brown.agent.json │ │ │ ├── Talia Brooks.agent.json │ │ │ ├── Talia Hayes.agent.json │ │ │ ├── Talia Robinson.agent.json │ │ │ ├── Tanvi Kapoor.agent.json │ │ │ ├── Victoria Adams-Brown.agent.json │ │ │ ├── Victoria Torres.agent.json │ │ │ ├── Zara Linh Nguyen.agent.json │ │ │ ├── Zara Patel.agent.json │ │ │ ├── Zara Thompson-Jones.agent.json │ │ │ └── Zara Thompson.agent.json │ │ ├── usa_families_2b/ │ │ │ ├── Aaliyah Rosario Rodríguez.agent.json │ │ │ ├── Adriana Beatriz Flores-Medina.agent.json │ │ │ ├── Aiden Miguel Santos.agent.json │ │ │ ├── Amara Lin Dawson.agent.json │ │ │ ├── Ana Lucía Mendoza.agent.json │ │ │ ├── Arjun Vikram Desai.agent.json │ │ │ ├── Avery Linh Svensson.agent.json │ │ │ ├── Camila Rosario Johnson.agent.json │ │ │ ├── Carmen Lucía Navarro.agent.json │ │ │ ├── Christopher Hiro Tanaka-Wells.agent.json │ │ │ ├── Claire Alexandra Sinclair.agent.json │ │ │ ├── Clara Maeve Lockwood.agent.json │ │ │ ├── Daniel Everett Brooks.agent.json │ │ │ ├── Dorothy Ann Carlson.agent.json │ │ │ ├── Earl Benjamin Crockett.agent.json │ │ │ ├── Eleanor Ruth Winslow.agent.json │ │ │ ├── Emily Grace Walker.agent.json │ │ │ ├── Erin Sora Park-Harrington.agent.json │ │ │ ├── Gabriela Marisol Ortega.agent.json │ │ │ ├── Greta Marianne Olsen.agent.json │ │ │ ├── Harper Noelle Santiago.agent.json │ │ │ ├── James Earl Hensley.agent.json │ │ │ ├── Joan Elizabeth Gallagher.agent.json │ │ │ ├── Jonathan Pierce Aldridge.agent.json │ │ │ ├── Juan Pablo Castillo.agent.json │ │ │ ├── Karina Maribel Gómez Ruiz.agent.json │ │ │ ├── Latoya Simone Parker.agent.json │ │ │ ├── Laura Jean Thompson.agent.json │ │ │ ├── Lucas Orion Hayes.agent.json │ │ │ ├── Mariana Elena Torres.agent.json │ │ │ ├── Marilyn Josephine Peterson.agent.json │ │ │ ├── Marisa Redbird.agent.json │ │ │ ├── Maritza Elena Rios.agent.json │ │ │ ├── Mark Allen Hargrove.agent.json │ │ │ ├── Matthew Kenji Fairchild.agent.json │ │ │ ├── Maya Celeste Bennett.agent.json │ │ │ ├── Meredith Claire Hargreaves.agent.json │ │ │ ├── Monique Patrice Johnson.agent.json │ │ │ ├── Nora Keiko Sullivan.agent.json │ │ │ ├── Nova Mei Holmgren.agent.json │ │ │ ├── Radhika Meera Kapoor.agent.json │ │ │ ├── Robert Lee McClain.agent.json │ │ │ ├── Rowan Micah Ellwood.agent.json │ │ │ ├── Sharon Louise Keller.agent.json │ │ │ ├── Sofia Elena Morales.agent.json │ │ │ ├── Tanya Michelle Brown.agent.json │ │ │ ├── Timothy Dale Kirkland.agent.json │ │ │ ├── Travis Allen Finley.agent.json │ │ │ ├── William Ray Tucker.agent.json │ │ │ └── Yadira Noemi Cruz-López.agent.json │ │ ├── usa_families_2c/ │ │ │ ├── Amaya Linh Rosario-Keller.agent.json │ │ │ ├── Arjun Vikram Patel.agent.json │ │ │ ├── Arturo Luis Peña.agent.json │ │ │ ├── Asha Meera Iyer.agent.json │ │ │ ├── Benjamin Carter Langley.agent.json │ │ │ ├── Caleb Mitchell Davenport.agent.json │ │ │ ├── Carlos Alejandro Valdez.agent.json │ │ │ ├── Caroline Bethany Wallace.agent.json │ │ │ ├── Casey Rivera-Lin.agent.json │ │ │ ├── Claire Meredith Langford.agent.json │ │ │ ├── Diego Alejandro Navarro.agent.json │ │ │ ├── Eleanor Grace Sullivan.agent.json │ │ │ ├── Elliot Sinclair.agent.json │ │ │ ├── Emiliano Javier Ramos.agent.json │ │ │ ├── Ethan Marshall Reed.agent.json │ │ │ ├── Evan Mateo Alvarez.agent.json │ │ │ ├── Evelyn Jean Parker.agent.json │ │ │ ├── Garrett Wayne Collins.agent.json │ │ │ ├── Jeffrey Mark Lawson.agent.json │ │ │ ├── Jordan Parker Whitman.agent.json │ │ │ ├── Katherine Mae Whitaker.agent.json │ │ │ ├── Leo Alexander Bennett.agent.json │ │ │ ├── Lucas Manuel Hernández.agent.json │ │ │ ├── Lucia Isabel Garcia.agent.json │ │ │ ├── Marcus Elijah Brooks.agent.json │ │ │ ├── Maria Elena Sanchez.agent.json │ │ │ ├── Mark Alan Peterson.agent.json │ │ │ ├── Marquis Anthony Jackson.agent.json │ │ │ ├── Mateo Daniel González.agent.json │ │ │ ├── Maya Anjali Carter.agent.json │ │ │ ├── Miguel Ángel Torres-García.agent.json │ │ │ ├── Morgan Ellis Caldwell.agent.json │ │ │ ├── Natalie Claire Kensington.agent.json │ │ │ ├── Nathaniel Grant Hawthorne.agent.json │ │ │ ├── Neela Patel-Wright.agent.json │ │ │ ├── Noah Elias Cruz.agent.json │ │ │ ├── Oliver James Carson.agent.json │ │ │ ├── Quinn Emerson.agent.json │ │ │ ├── Rafael Julian Crowe.agent.json │ │ │ ├── Riley Mateo Santiago.agent.json │ │ │ ├── Roger Allen Kessler.agent.json │ │ │ ├── Rohan Kiran Li-Desai.agent.json │ │ │ ├── Ruben Arturo Morales.agent.json │ │ │ ├── Ruby Mae Johnson.agent.json │ │ │ ├── Samantha Aiyana TallBear.agent.json │ │ │ ├── Sebastian Kai Mendoza.agent.json │ │ │ ├── Tameka Renée Bryant.agent.json │ │ │ ├── Taylor Emerson Clarke.agent.json │ │ │ ├── Yadira Marisol Valenzuela.agent.json │ │ │ └── Yesenia Maribel Flores.agent.json │ │ ├── usa_general_2/ │ │ │ ├── Ariana Martinez-Brown.agent.json │ │ │ ├── Ava Sinclair.agent.json │ │ │ ├── Benjamin Hartley.agent.json │ │ │ ├── Carmen Alvarez-Johnson.agent.json │ │ │ ├── Carolyn Whitman.agent.json │ │ │ ├── Charlotte Mercer.agent.json │ │ │ ├── Elliot James Prescott.agent.json │ │ │ ├── Eloise Gardner.agent.json │ │ │ ├── Ethan Nakamura.agent.json │ │ │ ├── Evelyn Bradford.agent.json │ │ │ ├── Gloria Rosario.agent.json │ │ │ ├── Harper Sullivan.agent.json │ │ │ ├── Janet Marie Carlson.agent.json │ │ │ ├── Juanita Delgado.agent.json │ │ │ ├── Julian Harrington.agent.json │ │ │ ├── Keisha Alvarez.agent.json │ │ │ ├── Liana Torres-Kim.agent.json │ │ │ ├── Margaret Elaine Miller.agent.json │ │ │ ├── Patricia Ann Baker.agent.json │ │ │ └── Valentina Marisol Torres.agent.json │ │ ├── usa_picky_2/ │ │ │ ├── Anika Mei Chen-Rao.agent.json │ │ │ ├── Betty Lou Hensley.agent.json │ │ │ ├── Declan Rossetti.agent.json │ │ │ ├── Dorothy Mae Whitaker.agent.json │ │ │ ├── Dustin Lee Hargrove.agent.json │ │ │ ├── Gabriela Ortega.agent.json │ │ │ ├── Grace O'Malley-Fischer.agent.json │ │ │ ├── Isha Chen-Patel.agent.json │ │ │ ├── Latasha Renee McClain.agent.json │ │ │ ├── Laura Brennan.agent.json │ │ │ ├── Logan McCarthy.agent.json │ │ │ ├── Luna Hernández.agent.json │ │ │ ├── Monique Latrice Carter.agent.json │ │ │ ├── Noah Delgado.agent.json │ │ │ ├── Rachel Donnelly.agent.json │ │ │ ├── Sarah Gallagher.agent.json │ │ │ ├── Shane Lee McCoy.agent.json │ │ │ ├── Siobhan Lombardi.agent.json │ │ │ ├── Susan Davenport.agent.json │ │ │ └── Ximena Alvarez-Ruiz.agent.json │ │ └── usa_singles_2/ │ │ ├── Amelia Foster.agent.json │ │ ├── Amelia Torres.agent.json │ │ ├── Ananya Mehta.agent.json │ │ ├── Arthur Lee McBride.agent.json │ │ ├── Ava Martinez.agent.json │ │ ├── Cameron Ellis.agent.json │ │ ├── Casey Rivera.agent.json │ │ ├── Charles Vernon Whitaker.agent.json │ │ ├── Charlotte Evans.agent.json │ │ ├── Charlotte Nguyen.agent.json │ │ ├── Chloe Bennett.agent.json │ │ ├── Chloe Martinez.agent.json │ │ ├── Chloe Nguyen.agent.json │ │ ├── Chloe Ramirez.agent.json │ │ ├── Clarence Walker.agent.json │ │ ├── Daniel Callahan.agent.json │ │ ├── Daniel Foster.agent.json │ │ ├── David Alan Porter.agent.json │ │ ├── David Lee.agent.json │ │ ├── Diego Manuel Herrera.agent.json │ │ ├── Emily Chen.agent.json │ │ ├── Erin Palmer.agent.json │ │ ├── Ethan Kim.agent.json │ │ ├── Evan Chen-Parker.agent.json │ │ ├── Evelyn Brooks-Johnson.agent.json │ │ ├── Evelyn Brooks.agent.json │ │ ├── Evelyn Crawford.agent.json │ │ ├── Evelyn Martinez.agent.json │ │ ├── Gabriel Scott.agent.json │ │ ├── Gary Rhodes.agent.json │ │ ├── Grace Mitchell.agent.json │ │ ├── Grace Nguyen.agent.json │ │ ├── Harold Dean Fletcher.agent.json │ │ ├── Henry Adams.agent.json │ │ ├── Henry Mitchell.agent.json │ │ ├── Isaac Johnson.agent.json │ │ ├── Isabella Garcia.agent.json │ │ ├── Isabella Wright.agent.json │ │ ├── Isaiah Patel.agent.json │ │ ├── Jackson Wright.agent.json │ │ ├── James Anderson.agent.json │ │ ├── Jamie Lee Carter.agent.json │ │ ├── Jaxon Rivera.agent.json │ │ ├── Jordan Alvarez-Kim.agent.json │ │ ├── Jordan Kim-Rodriguez.agent.json │ │ ├── Jordan Park.agent.json │ │ ├── José Antonio Vega.agent.json │ │ ├── Julian Grant.agent.json │ │ ├── Julian Hayes.agent.json │ │ ├── Kai Mendoza.agent.json │ │ ├── Kaya Yazzie-Kelekolio.agent.json │ │ ├── Leilani Begay.agent.json │ │ ├── Liam Johnson.agent.json │ │ ├── Lillian Porter.agent.json │ │ ├── Lily Carter.agent.json │ │ ├── Lily Foster.agent.json │ │ ├── Lily Nguyen.agent.json │ │ ├── Loretta Jean Sanders.agent.json │ │ ├── Lucas Ramirez.agent.json │ │ ├── Luna Hayes.agent.json │ │ ├── Madison Reed.agent.json │ │ ├── Madison Torres.agent.json │ │ ├── Makana Begay.agent.json │ │ ├── Maria Elena Dominguez.agent.json │ │ ├── Marissa Tanaka.agent.json │ │ ├── Maritza Soto.agent.json │ │ ├── Mason Reed.agent.json │ │ ├── Mia Robinson.agent.json │ │ ├── Michael Thompson.agent.json │ │ ├── Miriam Langford.agent.json │ │ ├── Natalie Torres.agent.json │ │ ├── Nathaniel Scott.agent.json │ │ ├── Noah Lewis.agent.json │ │ ├── Noelani Benally.agent.json │ │ ├── Nora Kim.agent.json │ │ ├── Oliver Brooks.agent.json │ │ ├── Olivia Garcia.agent.json │ │ ├── Olivia Turner.agent.json │ │ ├── Olivia Walker.agent.json │ │ ├── Quinn Garcia.agent.json │ │ ├── Raymond Lee Carter.agent.json │ │ ├── Rowan Park-Bennett.agent.json │ │ ├── Samantha Lee.agent.json │ │ ├── Samantha Reed.agent.json │ │ ├── Sarah Mitchell.agent.json │ │ ├── Sasha Morales.agent.json │ │ ├── Scarlett Nguyen.agent.json │ │ ├── Shanice Marie Washington.agent.json │ │ ├── Sofia Martinez.agent.json │ │ ├── Sophia Carter.agent.json │ │ ├── Sophia Patel.agent.json │ │ ├── Tamika Grace Brown.agent.json │ │ ├── Taylor Nguyen-Santos.agent.json │ │ ├── Taylor Rivera.agent.json │ │ └── Thomas Earl Davis.agent.json │ └── run_experiments.py ├── pyproject.toml ├── reinstall_package_from_repo.bat ├── test-report.html ├── test-results.xml ├── test.bat ├── test_comparison.txt ├── test_core_with_cache.bat ├── test_exports/ │ └── Document/ │ ├── Architectural Proposal & Preliminary Cost Analysis — [Project Name - TBC].Oscar.docx │ ├── Architectural Proposal & Preliminary Cost Analysis — [Project Name - TBC].Oscar.json │ ├── Architectural Proposal & Preliminary Cost Analysis — [Project Name - TBC].Oscar.md │ ├── Architectural Proposal for Standard Apartment Building Configuration.Oscar.docx │ ├── Architectural Proposal for Standard Apartment Building Configuration.Oscar.json │ ├── Architectural Proposal for Standard Apartment Building Configuration.Oscar.md │ ├── Architectural Proposal for Standard Apartment Building Elements.Oscar.docx │ ├── Architectural Proposal for Standard Apartment Building Elements.Oscar.json │ ├── Architectural Proposal for Standard Apartment Building Elements.Oscar.md │ ├── Architectural Proposal for Standard Apartment Configurations at Awesome Inc..Oscar.docx │ ├── Architectural Proposal for Standard Apartment Configurations at Awesome Inc..Oscar.json │ ├── Architectural Proposal for Standard Apartment Configurations at Awesome Inc..Oscar.md │ ├── Architectural Proposal for Sustainable Modular Apartment Building.Oscar.docx │ ├── Architectural Proposal for Sustainable Modular Apartment Building.Oscar.json │ ├── Architectural Proposal for Sustainable Modular Apartment Building.Oscar.md │ ├── Architectural Proposal for Sustainable Modular Housing.Oscar.docx │ ├── Architectural Proposal for Sustainable Modular Housing.Oscar.json │ ├── Architectural Proposal for Sustainable Modular Housing.Oscar.md │ ├── Architectural Proposal — Standardized Apartment Building & Cost Analysis.Oscar.docx │ ├── Architectural Proposal — Standardized Apartment Building & Cost Analysis.Oscar.json │ ├── Architectural Proposal — Standardized Apartment Building & Cost Analysis.Oscar.md │ ├── Architectural Proposal- Modular Apartment Building — Standard Apartment Configurations & Cost Analysis.Oscar (Architect, Awesome Inc.).docx │ ├── Architectural Proposal- Modular Apartment Building — Standard Apartment Configurations & Cost Analysis.Oscar (Architect, Awesome Inc.).json │ ├── Architectural Proposal- Modular Apartment Building — Standard Apartment Configurations & Cost Analysis.Oscar (Architect, Awesome Inc.).md │ ├── Detailed Building Cost Analysis for Standard Apartment Elements.Oscar.docx │ ├── Detailed Building Cost Analysis for Standard Apartment Elements.Oscar.json │ ├── Detailed Building Cost Analysis for Standard Apartment Elements.Oscar.md │ ├── Standardized Apartment Configuration Proposal — Awesome Inc..Oscar.docx │ ├── Standardized Apartment Configuration Proposal — Awesome Inc..Oscar.json │ └── Standardized Apartment Configuration Proposal — Awesome Inc..Oscar.md ├── test_gpt41mini_with_cache.bat ├── test_output.txt ├── test_with_cache_without_slow.bat ├── test_without_slow.bat ├── tests/ │ ├── README.md │ ├── conftest.py │ ├── non_functional/ │ │ └── test_security.py │ ├── scenarios/ │ │ ├── test_advertisement_scenarios.py │ │ ├── test_basic_scenarios.py │ │ ├── test_brainstorming_scenarios.py │ │ ├── test_extended_scenarios.py │ │ ├── test_gpt41mini_scenarios.py │ │ └── test_jupyter_examples.py │ ├── testing_utils.py │ └── unit/ │ ├── test-report.html │ ├── test-results.xml │ ├── test_action_generator.py │ ├── test_api_cache.py │ ├── test_api_cache_integration.py │ ├── test_config.py │ ├── test_control.py │ ├── test_cost_tracking.py │ ├── test_enrichment.py │ ├── test_experimentation.py │ ├── test_exports/ │ │ ├── Document/ │ │ │ ├── Architectural Proposal — Modular Sustainable Standard Apartments.Oscar, Architect — Awesome Inc..docx │ │ │ ├── Architectural Proposal — Modular Sustainable Standard Apartments.Oscar, Architect — Awesome Inc..json │ │ │ ├── Architectural Proposal — Modular Sustainable Standard Apartments.Oscar, Architect — Awesome Inc..md │ │ │ └── test_artifact.docx │ │ ├── record/ │ │ │ └── test_artifact.json │ │ └── text/ │ │ └── test_artifact.txt │ ├── test_extraction.py │ ├── test_factory.py │ ├── test_grounding.py │ ├── test_in_place_experiment_runner.py │ ├── test_intervention.py │ ├── test_llm_chat.py │ ├── test_memory.py │ ├── test_normalizer.py │ ├── test_profiling.py │ ├── test_results_extractor.py │ ├── test_results_reducer.py │ ├── test_results_reporter.py │ ├── test_simulation_validator.py │ ├── test_statistical_tests.py │ ├── test_story.py │ ├── test_tiny_calendar.py │ ├── test_tiny_social_network.py │ ├── test_tiny_styler.py │ ├── test_tiny_tool.py │ ├── test_tinyperson.py │ ├── test_tinyperson_extended.py │ ├── test_tinyworld.py │ ├── test_utils.py │ └── test_validation.py ├── tinytroupe/ │ ├── __init__.py │ ├── agent/ │ │ ├── __init__.py │ │ ├── action_generator.py │ │ ├── grounding.py │ │ ├── memory.py │ │ ├── mental_faculty.py │ │ ├── prompts/ │ │ │ ├── tiny_person.mustache │ │ │ └── tiny_person.v2.mustache │ │ └── tiny_person.py │ ├── clients/ │ │ ├── __init__.py │ │ ├── azure_client.py │ │ ├── ollama_client.py │ │ └── openai_client.py │ ├── config.ini │ ├── control.py │ ├── enrichment/ │ │ ├── __init__.py │ │ ├── prompts/ │ │ │ ├── enricher.system.mustache │ │ │ ├── enricher.user.mustache │ │ │ ├── styler.system.mustache │ │ │ └── styler.user.mustache │ │ ├── tiny_enricher.py │ │ └── tiny_styler.py │ ├── environment/ │ │ ├── __init__.py │ │ ├── tiny_social_network.py │ │ └── tiny_world.py │ ├── examples/ │ │ ├── __init__.py │ │ ├── agents/ │ │ │ ├── Friedrich_Wolf.agent.json │ │ │ ├── Lila.agent.json │ │ │ ├── Lisa.agent.json │ │ │ ├── Marcos.agent.json │ │ │ ├── Oscar.agent.json │ │ │ └── Sophie_Lefevre.agent.json │ │ ├── agents.py │ │ ├── fragments/ │ │ │ ├── authoritarian.agent.fragment.json │ │ │ ├── leftwing.agent.fragment.json │ │ │ ├── libertarian.agent.fragment.json │ │ │ └── rightwing.agent.fragment.json │ │ └── loaders.py │ ├── experimentation/ │ │ ├── __init__.py │ │ ├── in_place_experiment_runner.py │ │ ├── proposition.py │ │ ├── randomization.py │ │ └── statistical_tests.py │ ├── extraction/ │ │ ├── __init__.py │ │ ├── artifact_exporter.py │ │ ├── normalizer.py │ │ ├── prompts/ │ │ │ ├── interaction_results_extractor.mustache │ │ │ ├── normalizer.applier.system.mustache │ │ │ ├── normalizer.applier.user.mustache │ │ │ ├── normalizer.system.mustache │ │ │ └── normalizer.user.mustache │ │ ├── results_extractor.py │ │ ├── results_reducer.py │ │ └── results_reporter.py │ ├── factory/ │ │ ├── __init__.py │ │ ├── prompts/ │ │ │ ├── generate_person.mustache │ │ │ └── generate_person_factory.md │ │ ├── tiny_factory.py │ │ └── tiny_person_factory.py │ ├── profiling.py │ ├── steering/ │ │ ├── __init__.py │ │ ├── intervention.py │ │ ├── prompts/ │ │ │ ├── intervention.mustache │ │ │ ├── story.continuation.system.mustache │ │ │ ├── story.continuation.user.mustache │ │ │ ├── story.start.system.mustache │ │ │ └── story.start.user.mustache │ │ └── tiny_story.py │ ├── tools/ │ │ ├── __init__.py │ │ ├── tiny_calendar.py │ │ ├── tiny_tool.py │ │ └── tiny_word_processor.py │ ├── ui/ │ │ ├── __init__.py │ │ └── jupyter_widgets.py │ ├── utils/ │ │ ├── __init__.py │ │ ├── behavior.py │ │ ├── concurrency.py │ │ ├── config.py │ │ ├── json.py │ │ ├── llm.py │ │ ├── misc.py │ │ ├── parallel.py │ │ ├── prompts/ │ │ │ ├── rai_copyright_infringement_prevention.md │ │ │ └── rai_harmful_content_prevention.md │ │ ├── rendering.py │ │ ├── semantics.py │ │ └── validation.py │ └── validation/ │ ├── __init__.py │ ├── prompts/ │ │ └── check_person.mustache │ ├── propositions.py │ ├── simulation_validator.py │ ├── tiny_person_validator.py │ └── validation_chamber.py └── uninstall_package.bat
SYMBOL INDEX (9 symbols across 3 files) FILE: publications/paper_artifacts_june-2025/common_utils.py function compute_average_scores (line 7) | def compute_average_scores(scores): function plot_scores (line 17) | def plot_scores(propositions_scores): function merge_dicts_of_lists (line 30) | def merge_dicts_of_lists(source_dict, target_dict): FILE: publications/paper_artifacts_june-2025/market_research_utils.py function is_there_a_good_market (line 17) | def is_there_a_good_market(df, yes_threshold=0.1, no_threshold=0.5): function extract_and_analyze_results (line 50) | def extract_and_analyze_results(people, title): function plot_combined_responses (line 62) | def plot_combined_responses(title, name_to_df): FILE: publications/paper_artifacts_october-2025/common_utils.py function compute_average_scores (line 7) | def compute_average_scores(scores): function plot_scores (line 17) | def plot_scores(propositions_scores): function merge_dicts_of_lists (line 30) | def merge_dicts_of_lists(source_dict, target_dict):
Copy disabled (too large)
Download .json
Condensed preview — 1516 files, each showing path, character count, and a content snippet. Download the .json file for the full structured content (110,707K chars).
[
{
"path": ".gitattributes",
"chars": 49,
"preview": "*.cache.json filter=lfs diff=lfs merge=lfs -text\n"
},
{
"path": ".github/copilot-instructions.md",
"chars": 8023,
"preview": "---\napplyTo: \"**\"\n---\n# Guidelines for Code Generation in TinyTroupe\n\nThis document provides the primary guidelines for "
},
{
"path": ".github/project-copilot-instructions.md",
"chars": 644,
"preview": "# TinyTroupe Project Programming Guidelines \n\nThis document provides the TinyTroupe-specific guidelines for generating p"
},
{
"path": ".github/prompts/improve.prompt.md",
"chars": 1541,
"preview": "---\nmode: 'agent'\ndescription: 'Examines the current selected context and suggests improvements.'\n---\n\nExamine the attac"
},
{
"path": ".github/prompts/open-ended_ideas.prompt.md",
"chars": 869,
"preview": "---\nmode: 'agent'\ndescription: 'Generate open-ended ideas for the project.'\n---\n\nExamine the attached files in order to "
},
{
"path": ".github/prompts/write_tests.prompt.md",
"chars": 323,
"preview": "---\nmode: 'agent'\ndescription: 'Generate tests for the specified function or selected section of program.'\n---\n\nPlease w"
},
{
"path": ".github/workflows/bandit.yml",
"chars": 2542,
"preview": "# This workflow uses actions that are not certified by GitHub.\n# They are provided by a third-party and are governed by\n"
},
{
"path": ".github/workflows/codeql.yml",
"chars": 4294,
"preview": "# For most projects, this workflow file will not need changing; you simply need\n# to commit it to your repository.\n#\n# Y"
},
{
"path": ".gitignore",
"chars": 3319,
"preview": "#other\n*.pickle\n.llmapi.bin\n*.cache.*\ntests_cache.pickle\n*.local.*\n.VSCodeCounter/\n.vscode/\n\noutputs/\n\n# Byte-compiled /"
},
{
"path": "CODE_OF_CONDUCT.md",
"chars": 444,
"preview": "# Microsoft Open Source Code of Conduct\n\nThis project has adopted the [Microsoft Open Source Code of Conduct](https://op"
},
{
"path": "LICENSE",
"chars": 1141,
"preview": " MIT License\n\n Copyright (c) Microsoft Corporation.\n\n Permission is hereby granted, free of charge, to any pers"
},
{
"path": "MANIFEST.in",
"chars": 149,
"preview": "recursive-include tinytroupe *.ini\nrecursive-include tinytroupe *.py\nrecursive-include tinytroupe *.md *.mustache\nrecurs"
},
{
"path": "README.md",
"chars": 50678,
"preview": "# TinyTroupe 🤠🤓🥸🧐\n*LLM-powered multiagent persona simulation for imagination enhancement and business insights.*\n\n<p ali"
},
{
"path": "RESPONSIBLE_AI_FAQ.md",
"chars": 5224,
"preview": "# TinyTroupe: Responsible AI FAQ\n\n## What is TinyTroupe?\n\n*TinyTroupe* is an experimental Python library that allows us "
},
{
"path": "SECURITY.md",
"chars": 2656,
"preview": "<!-- BEGIN MICROSOFT SECURITY.MD V0.0.9 BLOCK -->\n\n## Security\n\nMicrosoft takes the security of our software products an"
},
{
"path": "SUPPORT.md",
"chars": 510,
"preview": "# Support\r\n\r\n## How to file issues and get help \r\n\r\nThis project uses GitHub Issues to track bugs and feature requests."
},
{
"path": "build_and_install_package_from_repo.bat",
"chars": 79,
"preview": "pip install build\nCALL .\\build_package.bat\nCALL .\\install_package_from_repo.bat"
},
{
"path": "build_package.bat",
"chars": 33,
"preview": "pip install build\npython -m build"
},
{
"path": "config.ini",
"chars": 654,
"preview": "[OpenAI]\n\nAPI_TYPE=openai\n\n# Check Azure's documentation for updates here:\n# https://learn.microsoft.com/en-us/azure/ai-"
},
{
"path": "data/empirical/07.17.2025 - Market Research - AI-enabled story telling device or app - Raw Data.csv",
"chars": 16725,
"preview": "Responder #,Vote,Explanation,Age Range,Gender Identity,Kids Toy Buying Frequency,Hobbies And Interests,Age Of Kids,Paren"
},
{
"path": "data/empirical/07.19.2025 - Market Research - Bottled Gazpacho - Raw Data.csv",
"chars": 9148,
"preview": "Responder #,Vote,Explanation,Age Range,Gender Identity,Political Affiliation,Racial Or Ethnic Identity\n1,4,Yes because i"
},
{
"path": "data/extractions/appartment_rent_ad.extraction.json",
"chars": 878,
"preview": "{\n \"agent_extractions\": {},\n \"world_extraction\": {\n \"Focus group\": {\n \"ad_copy\": \"Discover a spa"
},
{
"path": "data/extractions/appartment_rent_ad_1.extraction.json",
"chars": 4504,
"preview": "{\n \"agent_extractions\": {\n \"Lisa\": [\n {\n \"main_point\": \"To advertise Paulo's apartme"
},
{
"path": "data/extractions/synthetic_data_generation.out.csv",
"chars": 8703,
"preview": "author,content\nUSER,\"Get some work done together, help each other.\"\nMarina Ellsworth,\"Sounds good — I’m up for a focused"
},
{
"path": "data/extractions/wordprocessor/Document/Lisa Carter - Resume.Lisa Carter.json",
"chars": 10705,
"preview": "{\n \"title\": \"Lisa Carter - Resume\",\n \"content\": \"# Lisa Carter\\n\\n---\\n\\n## Contact Information\\n\\n- **Location:**"
},
{
"path": "data/extractions/wordprocessor/Document/Lisa Carter - Resume.Lisa Carter.md",
"chars": 10401,
"preview": "# Lisa Carter\n\n---\n\n## Contact Information\n\n- **Location:** United States of America (USA) \n- **Nationality:** Canadian"
},
{
"path": "data/extractions/wordprocessor/Document/Resume of Lisa Carter.Lisa Carter.json",
"chars": 6195,
"preview": "{\n \"title\": \"Resume of Lisa Carter\",\n \"content\": \"```\\n# Lisa Carter\\n\\n## Contact Information\\n- **Email:** lisa."
},
{
"path": "data/extractions/wordprocessor/Document/Resume of Lisa Carter.Lisa Carter.md",
"chars": 6006,
"preview": "```\n# Lisa Carter\n\n## Contact Information\n- **Email:** lisa.carter@example.com\n- **Phone:** (123) 456-7890\n- **LinkedIn:"
},
{
"path": "data/extractions/wordprocessor/Document/Resume of Lisa.Lisa.json",
"chars": 5301,
"preview": "{\n \"title\": \"Resume of Lisa\",\n \"content\": \"```\\n# Lisa's Resume\\n\\n## Contact Information\\n- **Name:** Lisa Johnso"
},
{
"path": "data/extractions/wordprocessor/Document/Resume of Lisa.Lisa.md",
"chars": 5123,
"preview": "```\n# Lisa's Resume\n\n## Contact Information\n- **Name:** Lisa Johnson\n- **Age:** 28\n- **Nationality:** Canadian\n- **Locat"
},
{
"path": "data/facts/business-facts.synthetic.txt",
"chars": 49341,
"preview": "1. Effective communication is a crucial skill for business consultants to develop trust and rapport with clients.\n2. Und"
},
{
"path": "data/grounding_examples/grounding_examples_1/don_quijote_project_gutenberg.txt",
"chars": 2129975,
"preview": "The Project Gutenberg eBook of Don Quijote\n \nThis ebook is for the use of anyone anywhere in the United States and\nm"
},
{
"path": "data/grounding_examples/grounding_examples_1/marus_aurelius_meditations_by_project_gutenberg.txt",
"chars": 417417,
"preview": "The Project Gutenberg eBook of Meditations\n \nThis ebook is for the use of anyone anywhere in the United States and\nm"
},
{
"path": "docs/api/tinytroupe/agent/action_generator.html",
"chars": 90808,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/agent/grounding.html",
"chars": 71500,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/agent/index.html",
"chars": 285714,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/agent/memory.html",
"chars": 148628,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/agent/mental_faculty.html",
"chars": 71784,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/agent/tiny_person.html",
"chars": 278482,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/clients/azure_client.html",
"chars": 14083,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/clients/index.html",
"chars": 16724,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/clients/ollama_client.html",
"chars": 35028,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/clients/openai_client.html",
"chars": 78788,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/control.html",
"chars": 109635,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/enrichment/index.html",
"chars": 12421,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/enrichment/tiny_enricher.html",
"chars": 13164,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/enrichment/tiny_styler.html",
"chars": 19818,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/environment/index.html",
"chars": 133261,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/environment/tiny_social_network.html",
"chars": 28716,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/environment/tiny_world.html",
"chars": 163709,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/examples/agents.html",
"chars": 56560,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/examples/index.html",
"chars": 7362,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/examples/loaders.html",
"chars": 12483,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/experimentation/in_place_experiment_runner.html",
"chars": 53096,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/experimentation/index.html",
"chars": 106652,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/experimentation/proposition.html",
"chars": 100283,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/experimentation/randomization.html",
"chars": 21454,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/experimentation/statistical_tests.html",
"chars": 75850,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/extraction/artifact_exporter.html",
"chars": 28513,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/extraction/index.html",
"chars": 113547,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/extraction/normalizer.html",
"chars": 42678,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/extraction/results_extractor.html",
"chars": 44796,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/extraction/results_reducer.html",
"chars": 17394,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/extraction/results_reporter.html",
"chars": 55132,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/factory/index.html",
"chars": 126635,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/factory/tiny_factory.html",
"chars": 20502,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/factory/tiny_person_factory.html",
"chars": 215071,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/index.html",
"chars": 55010,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/profiling.html",
"chars": 197598,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/steering/index.html",
"chars": 42841,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/steering/intervention.html",
"chars": 46953,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/steering/tiny_story.html",
"chars": 24021,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/tools/index.html",
"chars": 39388,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/tools/tiny_calendar.html",
"chars": 20147,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/tools/tiny_tool.html",
"chars": 17839,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/tools/tiny_word_processor.html",
"chars": 24038,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/ui/index.html",
"chars": 45008,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/ui/jupyter_widgets.html",
"chars": 62736,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/utils/behavior.html",
"chars": 12092,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/utils/concurrency.html",
"chars": 12246,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/utils/config.html",
"chars": 36313,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/utils/index.html",
"chars": 9964,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/utils/json.html",
"chars": 53662,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/utils/llm.html",
"chars": 180871,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/utils/misc.html",
"chars": 14559,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/utils/parallel.html",
"chars": 18159,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/utils/rendering.html",
"chars": 23527,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/utils/semantics.html",
"chars": 61688,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/utils/validation.html",
"chars": 14333,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/validation/index.html",
"chars": 8605,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/validation/propositions.html",
"chars": 21395,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/validation/simulation_validator.html",
"chars": 298468,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/validation/tiny_person_validator.html",
"chars": 28933,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/api/tinytroupe/validation/validation_chamber.html",
"chars": 9923,
"preview": "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<meta name=\"viewport\" content=\"width=device-width, initia"
},
{
"path": "docs/guides/ollama.md",
"chars": 1164,
"preview": "# Ollama Support\n\nTinyTroupe now has experimental Ollama support. Yes, even more experimental than the whole experimenta"
},
{
"path": "docs/index.html",
"chars": 14484,
"preview": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"viewport\" content=\"width=device-width"
},
{
"path": "examples/AI-enabled Children Story Telling Market Research 2.ipynb",
"chars": 2989394,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# AI-enabled Children Story Telling"
},
{
"path": "examples/Advertisement for TV.ipynb",
"chars": 857415,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Online Advertisement Evaluation f"
},
{
"path": "examples/Bottled Gazpacho Market Research 2.archival.ipynb",
"chars": 2341049,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/Bottled Gazpacho Market Research 3.archival.ipynb",
"chars": 2290022,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/Bottled Gazpacho Market Research 4.archival.ipynb",
"chars": 1450764,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/Bottled Gazpacho Market Research 4b.archival.ipynb",
"chars": 1521348,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/Bottled Gazpacho Market Research 5 (with behavior correction).ipynb",
"chars": 2431223,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/Bottled Gazpacho Market Research 5.ipynb",
"chars": 2436151,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/Bottled Gazpacho Market Research 5b.ipynb",
"chars": 58151,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/Bottled Gazpacho Market Research 5c.ipynb",
"chars": 60915,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/Bottled Gazpacho Market Research.archival.ipynb",
"chars": 3044858,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research\\"
},
{
"path": "examples/Create Ad for Apartment.ipynb",
"chars": 132938,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Appartment Rent Ad Creation\\n\",\n "
},
{
"path": "examples/Creating and Validating Agents.ipynb",
"chars": 179929,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Creating and Validating Agents\\n\""
},
{
"path": "examples/Interview with Customer.ipynb",
"chars": 105864,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Interview with customers\\n\",\n "
},
{
"path": "examples/Investment Firm.ipynb",
"chars": 351845,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Investment Firm\\n\",\n \"\\n\",\n "
},
{
"path": "examples/Online Advertisement for Travel.ipynb",
"chars": 1051439,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Online Advertisement Evaluation f"
},
{
"path": "examples/Political Compass (customizing agents with fragments).ipynb",
"chars": 349016,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Customizing Agents with Fragments"
},
{
"path": "examples/Product Brainstorming (with behavior correction).ipynb",
"chars": 559530,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Product Brinstorming\\n\",\n \"\\n\""
},
{
"path": "examples/Product Brainstorming.ipynb",
"chars": 562766,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Product Brinstorming\\n\",\n \"\\n\""
},
{
"path": "examples/Simple Chat.ipynb",
"chars": 324403,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Simple Chat\\n\",\n \"\\n\",\n \"A "
},
{
"path": "examples/Story telling (long narratives).ipynb",
"chars": 457484,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Story telling: Zog the alien meet"
},
{
"path": "examples/Synthetic Data Generation 1.ipynb",
"chars": 357977,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Synthetic Data Generation\\n\"\n ]"
},
{
"path": "examples/Synthetic Data Generation 2 (tool usage).ipynb",
"chars": 5450765,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Synthetic Data Generation for Off"
},
{
"path": "examples/Synthetic Data Generation.ipynb",
"chars": 146946,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Synthetic Data Generation\\n\"\n ]"
},
{
"path": "examples/Travel Product Market Research.ipynb",
"chars": 4761188,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Market Research for Various Produ"
},
{
"path": "examples/Word Processor Tool Usage.ipynb",
"chars": 30320,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Wordprocessor usage example\\n\",\n "
},
{
"path": "examples/agents/Friedrich_Wolf.agent.json",
"chars": 8817,
"preview": "{ \"type\": \"TinyPerson\",\n \"persona\": {\n \"name\": \"Friedrich Wolf\",\n \"age\": 35,\n \"gender\": \"Male\""
},
{
"path": "examples/agents/Lila.agent.json",
"chars": 7736,
"preview": "{ \"type\": \"TinyPerson\",\n \"persona\": {\n \"name\": \"Lila\",\n \"age\": 28,\n \"gender\": \"Female\",\n "
},
{
"path": "examples/agents/Lisa.agent.json",
"chars": 7264,
"preview": "{ \"type\": \"TinyPerson\",\n \"persona\": {\n \"name\": \"Lisa Carter\",\n \"age\": 28,\n \"gender\": \"Female\","
},
{
"path": "examples/agents/Marcos.agent.json",
"chars": 8188,
"preview": "{ \"type\": \"TinyPerson\",\n \"persona\": {\n \"name\": \"Marcos Almeida\",\n \"age\": 35,\n \"gender\": \"Male\""
},
{
"path": "examples/agents/Oscar.agent.json",
"chars": 7290,
"preview": "{ \"type\": \"TinyPerson\",\n \"persona\": {\n \"name\": \"Oscar\",\n \"age\": 30,\n \"gender\": \"Male\",\n "
},
{
"path": "examples/agents/Paulo_Salem.agent.json",
"chars": 8079,
"preview": "{\n \"type\": \"TinyPerson\",\n \"persona\": {\n \"name\": \"Paulo Salem\",\n \"age\": 42,\n \"gender\": \"Male\",\n \"nationalit"
},
{
"path": "examples/agents/Sophie_Lefevre.agent.json",
"chars": 7060,
"preview": "{ \"type\": \"TinyPerson\",\n \"persona\": {\n \"name\": \"Sophie Lefevre\",\n \"age\": 28,\n \"gender\": \"Femal"
},
{
"path": "examples/archive/Bottled Gazpacho Market Research 2.archival.ipynb",
"chars": 2341049,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/archive/Bottled Gazpacho Market Research 3.archival.ipynb",
"chars": 2290022,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/archive/Bottled Gazpacho Market Research 4.archival.ipynb",
"chars": 1450764,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/archive/Bottled Gazpacho Market Research 4b.archival.ipynb",
"chars": 1521348,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/archive/Bottled Gazpacho Market Research 5b.ipynb",
"chars": 58151,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/archive/Bottled Gazpacho Market Research 5c.ipynb",
"chars": 60915,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research "
},
{
"path": "examples/archive/Bottled Gazpacho Market Research.archival.ipynb",
"chars": 3044858,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Bottled Gazpacho Market Research\\"
},
{
"path": "examples/config.ini",
"chars": 876,
"preview": "[OpenAI]\n#\n# OpenAI or Azure OpenAI Service\n#\n\n# Default options: openai, azure\nAPI_TYPE=openai\n\n# Check Azure's documen"
},
{
"path": "examples/extractions/synthetic_data_example_3/Document/MultiLever Rapid Response Report- Stabilizing Demand under High Inflation.Lisa Carter.json",
"chars": 33862,
"preview": "{\n \"title\": \"MultiLever Rapid Response Report: Stabilizing Demand under High Inflation\",\n \"content\": \"# MultiLever"
},
{
"path": "examples/extractions/synthetic_data_example_3/Document/MultiLever Rapid Response Report- Stabilizing Demand under High Inflation.Lisa Carter.md",
"chars": 32902,
"preview": "# MultiLever — Rapid Response Plan to Demand Contraction and Elevated Inflation\nPrepared by: Wild Advice Partners \nAuth"
},
{
"path": "examples/extractions/synthetic_data_example_3/Document/MultiLever — Initial Rapid Diagnostic & Recommendations (Client Brief).Lisa Carter.json",
"chars": 40882,
"preview": "{\n \"title\": \"MultiLever \\u2014 Initial Rapid Diagnostic & Recommendations (Client Brief)\",\n \"content\": \"# Executiv"
},
{
"path": "examples/extractions/synthetic_data_example_3/Document/MultiLever — Initial Rapid Diagnostic & Recommendations (Client Brief).Lisa Carter.md",
"chars": 39403,
"preview": "# Executive Summary\n\nMultiLever is facing an acute demand shock driven by elevated inflation (~10% year-over-year) and a"
},
{
"path": "examples/extractions/synthetic_data_example_3/Document/MultiLever — Rapid Diagnostic & Recommendations.Lisa Carter.json",
"chars": 33362,
"preview": "{\n \"title\": \"MultiLever \\u2014 Rapid Diagnostic & Recommendations\",\n \"content\": \"# MultiLever \\u2014 Rapid Diagnos"
},
{
"path": "examples/extractions/synthetic_data_example_3/Document/MultiLever — Rapid Diagnostic & Recommendations.Lisa Carter.md",
"chars": 32156,
"preview": "# MultiLever — Rapid Diagnostic & Recommendations\n\nAuthor: Lisa Carter, Data Scientist, Wild Advice Partners \nContact: "
},
{
"path": "examples/extractions/synthetic_data_example_3/Document/Port Aurora u0007 Rapid Flood Resilience Plan u0007 Initial Report and Recommended Next Steps.Lisa Carter.json",
"chars": 33760,
"preview": "{\n \"title\": \"Port Aurora u0007 Rapid Flood Resilience Plan u0007 Initial Report and Recommended Next Steps\",\n \"con"
},
{
"path": "examples/extractions/synthetic_data_example_3/Document/Port Aurora u0007 Rapid Flood Resilience Plan u0007 Initial Report and Recommended Next Steps.Lisa Carter.md",
"chars": 32583,
"preview": "# Port Aurora — Rapid Flood Resilience Plan (Initial Report)\n\nPrepared by: Lisa Carter, Data Scientist, Wild Advice Part"
},
{
"path": "examples/extractions/synthetic_data_example_3/Document/Rapid Delivery Plan- Phase 1 FEMA-compliant Procurement and Upgrade Path.Lisa Carter.json",
"chars": 33524,
"preview": "{\n \"title\": \"Rapid Delivery Plan: Phase 1 FEMA-compliant Procurement and Upgrade Path\",\n \"content\": \"# Executive s"
},
{
"path": "examples/extractions/synthetic_data_example_3/Document/Rapid Delivery Plan- Phase 1 FEMA-compliant Procurement and Upgrade Path.Lisa Carter.md",
"chars": 32568,
"preview": "# Executive summary\n\nWild Advice Partners recommends a phased, procurement-friendly approach to deliver FEMA-eligible Ph"
},
{
"path": "examples/fragments/aggressive_debater.fragment.json",
"chars": 972,
"preview": "{ \"type\": \"Fragment\",\n \"persona\": {\n \"preferences\": {\n \"interests\": [\n \"Debates\"\n "
},
{
"path": "examples/fragments/authoritarian.agent.fragment.json",
"chars": 2204,
"preview": "{ \"type\": \"Fragment\",\n \"persona\": {\n \"preferences\": {\n \"interests\": [\n \"Military h"
},
{
"path": "examples/fragments/genuine.agent.fragment.json",
"chars": 1032,
"preview": "{ \"type\": \"Fragment\",\n \"persona\": {\n \"beliefs\": [\n \"It is very important to speak what I truly be"
},
{
"path": "examples/fragments/leftwing.agent.fragment.json",
"chars": 2617,
"preview": "{ \"type\": \"Fragment\",\n \"persona\": {\n \"preferences\": {\n \"interests\": [\n \"Social jus"
},
{
"path": "examples/fragments/libertarian.agent.fragment.json",
"chars": 2793,
"preview": "{ \"type\": \"Fragment\",\n \"persona\": {\n \"preferences\": {\n \"interests\": [\n \"Debates on"
},
{
"path": "examples/fragments/loving_parent.agent.fragment.json",
"chars": 1668,
"preview": "{ \"type\": \"Fragment\",\n \"persona\": {\n \"preferences\": {\n \"interests\": [\n \"Children\","
},
{
"path": "examples/fragments/picky_customer.agent.fragment.json",
"chars": 3276,
"preview": "{\n \"type\": \"Fragment\",\n \"persona\": {\n \"preferences\": {\n \"interests\": [\n \"Finding "
},
{
"path": "examples/fragments/rightwing.agent.fragment.json",
"chars": 2890,
"preview": "{\n \"type\": \"Fragment\",\n \"persona\": {\n \"preferences\": {\n \"interests\": [\n \"National"
},
{
"path": "examples/fragments/travel_enthusiast.agent.fragment.json",
"chars": 1444,
"preview": "{\n \"type\": \"Fragment\",\n \"persona\": {\n \"preferences\": {\n \"interests\": [\n \"Travelin"
},
{
"path": "examples/information/populations/brazil.json",
"chars": 6818,
"preview": "{\n \"title\": \"Brazil Population Information\",\n \"description\": \"A detailed overview of the population demographics, "
},
{
"path": "examples/information/populations/spain.json",
"chars": 11530,
"preview": "{\n \"title\": \"Spain Population Information\",\n \"description\": \"A detailed overview of the population demographics, t"
},
{
"path": "examples/information/populations/usa.json",
"chars": 14093,
"preview": "{\n \"title\": \"USA Population Information\",\n \"description\": \"A detailed overview of the population demographics, tra"
},
{
"path": "examples/ollama/Simple Chat.ipynb",
"chars": 450577,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Simple Chat\\n\",\n \"\\n\",\n \"A "
},
{
"path": "examples/ollama/config.ini",
"chars": 634,
"preview": "[OpenAI]\n# Using Ollama as the API type\n# Ollama is a local LLM serving tool that allows you to run models on your own h"
},
{
"path": "examples/scratch/Advertisement for TV.ipynb",
"chars": 8524446,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Online Advertisement Evaluation f"
},
{
"path": "examples/scratch/Simulation Experiment Empirical Validation Example.ipynb",
"chars": 51270,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"id\": \"7388fcde\",\n \"metadata\": {},\n \"source\": [\n \"# Simulation E"
},
{
"path": "examples/scratch/config.ini",
"chars": 159,
"preview": "[OpenAI]\n\nMODEL=gpt-4.1-mini\nMAX_TOKENS=32000\nTEMPERATURE=1.5\nFREQ_PENALTY=0.1\nPRESENCE_PENALTY=0.1\n\n\n[Logging]\nLOGLEVEL"
},
{
"path": "examples/scratch/tool_usage.ipynb",
"chars": 69987,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Tool usage\\n\"\n ]\n },\n {\n \"c"
},
{
"path": "generate_api_documentation.bat",
"chars": 44,
"preview": "pdoc --html --output-dir docs/api tinytroupe"
},
{
"path": "install_package_from_repo.bat",
"chars": 28,
"preview": "pip install . --no-cache-dir"
},
{
"path": "publications/README.md",
"chars": 676,
"preview": "# Publications\n\nThis directory contains artifacts related to research publications associated with the TinyTroupe projec"
},
{
"path": "publications/paper_artifacts_june-2025/Brainstorming and Focus Group Quantitative Experimentation 1 - treatment run.ipynb",
"chars": 9448070,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Brainstorming and Focus Group Qua"
},
{
"path": "publications/paper_artifacts_june-2025/Brainstorming and Focus Group Quantitative Experimentation 1.ipynb",
"chars": 93459,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Brainstorming and Focus Group Qua"
},
{
"path": "publications/paper_artifacts_june-2025/Brainstorming and Focus Group Quantitative Experimentation 2.1.ipynb",
"chars": 70046,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Brainstorming and Focus Group Qua"
},
{
"path": "publications/paper_artifacts_june-2025/Brainstorming and Focus Group Quantitative Experimentation 2.2.ipynb",
"chars": 69192,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Brainstorming and Focus Group Qua"
},
{
"path": "publications/paper_artifacts_june-2025/Brainstorming and Focus Group Quantitative Experimentation 2.3 - treatment run.ipynb",
"chars": 1738214,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Brainstorming and Focus Group Qua"
},
{
"path": "publications/paper_artifacts_june-2025/Brainstorming and Focus Group Quantitative Experimentation 2.3.ipynb",
"chars": 96845,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Brainstorming and Focus Group Qua"
},
{
"path": "publications/paper_artifacts_june-2025/Debating Quantitative Experimentation 1.ipynb",
"chars": 74897,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Debating Quantitative Experimenta"
},
{
"path": "publications/paper_artifacts_june-2025/Food Products Ideas Brainstorming.ipynb",
"chars": 1515433,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Product Brinstorming\\n\",\n \"\\n\""
},
{
"path": "publications/paper_artifacts_june-2025/Market Research Quantitative Experimentation 1.ipynb",
"chars": 39681,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Market Research Systematic Quanti"
},
{
"path": "publications/paper_artifacts_june-2025/Market Research Quantitative Experimentation 2.ipynb",
"chars": 1928624,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Market Research Systematic Quanti"
},
{
"path": "publications/paper_artifacts_june-2025/Opinion Poll Quantitative Experimentation.ipynb",
"chars": 36720,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Opinion Poll Quantitative Experim"
},
{
"path": "publications/paper_artifacts_june-2025/Political Compass (customizing agents with fragments).ipynb",
"chars": 179840,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Customizing Agents with Fragments"
},
{
"path": "publications/paper_artifacts_june-2025/Spicy Food Market Research.ipynb",
"chars": 520698,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Travel Product Ideas\\n\",\n \"\\n\""
},
{
"path": "publications/paper_artifacts_june-2025/Synthetic Data Generation.ipynb",
"chars": 2566908,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Synthetic Data Generation for Off"
},
{
"path": "publications/paper_artifacts_june-2025/Travel Product Market Research (with behavior correction).ipynb",
"chars": 1737673,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Travel Product Ideas (with behavi"
},
{
"path": "publications/paper_artifacts_june-2025/Travel Product Market Research.ipynb",
"chars": 1578137,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# Travel Product Ideas\\n\",\n \"\\n\""
},
{
"path": "publications/paper_artifacts_june-2025/brainstorming_and_focus_group_quantitative_experimentation_1c.json",
"chars": 40684,
"preview": "{\n \"experiments\": {\n \"Control\": {\n \"results\": {\n \"Hard Persona Adherence\": [\n "
},
{
"path": "publications/paper_artifacts_june-2025/brainstorming_and_focus_group_quantitative_experimentation_2.1c.json",
"chars": 24133,
"preview": "{\n \"experiments\": {\n \"Control\": {\n \"results\": {\n \"Hard Persona Adherence\": [\n "
},
{
"path": "publications/paper_artifacts_june-2025/brainstorming_and_focus_group_quantitative_experimentation_2.2b.json",
"chars": 24215,
"preview": "{\n \"experiments\": {\n \"Control\": {\n \"results\": {\n \"Persona Adherence\": [\n "
},
{
"path": "publications/paper_artifacts_june-2025/brainstorming_and_focus_group_quantitative_experimentation_2.3.json",
"chars": 41465,
"preview": "{\n \"experiments\": {\n \"Control\": {\n \"results\": {\n \"Hard Persona Adherence\": [\n "
},
{
"path": "publications/paper_artifacts_june-2025/common_utils.py",
"chars": 1488,
"preview": "from pprint import pprint\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom IPython.display import display\n\n# com"
},
{
"path": "publications/paper_artifacts_june-2025/config.ini",
"chars": 1403,
"preview": "[OpenAI]\n#\n# OpenAI or Azure OpenAI Service\n#\n\n# Default options: openai, azure\nAPI_TYPE=openai\n\n# Check Azure's documen"
},
{
"path": "publications/paper_artifacts_june-2025/debating_quantitative_experimentation_1c.json",
"chars": 27564,
"preview": "{\n \"experiments\": {\n \"Control\": {\n \"results\": {\n \"Hard Persona Adherence\": [\n "
},
{
"path": "publications/paper_artifacts_june-2025/extractions/synthetic_data_example_1/Document/Report for AquaPure Solutions- Strategies for Modernizing Water Purification Systems.Lisa Carter.json",
"chars": 7223,
"preview": "{\n \"title\": \"Report for AquaPure Solutions: Strategies for Modernizing Water Purification Systems\",\n \"content\": \"`"
},
{
"path": "publications/paper_artifacts_june-2025/extractions/synthetic_data_example_1/Document/Report for AquaPure Solutions- Strategies for Modernizing Water Purification Systems.Lisa Carter.md",
"chars": 7003,
"preview": "```\n## Executive Summary\nThis comprehensive report outlines the multifaceted challenges faced by AquaPure Solutions in t"
},
{
"path": "publications/paper_artifacts_june-2025/extractions/synthetic_data_example_1/Document/Report for BioSphere Innovations- Feasibility Study for Waste-to-Energy Solution.Lisa Carter.json",
"chars": 9453,
"preview": "{\n \"title\": \"Report for BioSphere Innovations: Feasibility Study for Waste-to-Energy Solution\",\n \"content\": \"```\\n"
},
{
"path": "publications/paper_artifacts_june-2025/extractions/synthetic_data_example_1/Document/Report for BioSphere Innovations- Feasibility Study for Waste-to-Energy Solution.Lisa Carter.md",
"chars": 9208,
"preview": "```\n## Executive Summary\nThis comprehensive report outlines the multifaceted challenges faced by BioSphere Innovations i"
},
{
"path": "publications/paper_artifacts_june-2025/extractions/synthetic_data_example_1/Document/Report for BrightPath Industries- Strategies for Enhancing Supply Chain Resilience.Lisa Carter.json",
"chars": 8308,
"preview": "{\n \"title\": \"Report for BrightPath Industries: Strategies for Enhancing Supply Chain Resilience\",\n \"content\": \"```"
},
{
"path": "publications/paper_artifacts_june-2025/extractions/synthetic_data_example_1/Document/Report for BrightPath Industries- Strategies for Enhancing Supply Chain Resilience.Lisa Carter.md",
"chars": 8070,
"preview": "```\n## Executive Summary\nThis comprehensive report outlines the multifaceted challenges faced by BrightPath Industries d"
},
{
"path": "publications/paper_artifacts_june-2025/extractions/synthetic_data_example_1/Document/Report for CleanFuture Corp- Strategies for Reshaping Public Image and Sustainability Practices.Lisa Carter.json",
"chars": 7828,
"preview": "{\n \"title\": \"Report for CleanFuture Corp: Strategies for Reshaping Public Image and Sustainability Practices\",\n \"c"
},
{
"path": "publications/paper_artifacts_june-2025/extractions/synthetic_data_example_1/Document/Report for CleanFuture Corp- Strategies for Reshaping Public Image and Sustainability Practices.Lisa Carter.md",
"chars": 7563,
"preview": "```\n## Executive Summary\nThis report provides a comprehensive analysis of the challenges currently faced by CleanFuture "
},
{
"path": "publications/paper_artifacts_june-2025/extractions/synthetic_data_example_1/Document/Report for EcoFuture Enterprises- Strategies for Sourcing Sustainable Materials.Lisa Carter.json",
"chars": 7768,
"preview": "{\n \"title\": \"Report for EcoFuture Enterprises: Strategies for Sourcing Sustainable Materials\",\n \"content\": \"```\\n#"
}
]
// ... and 1316 more files (download for full content)
About this extraction
This page contains the full source code of the microsoft/TinyTroupe GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 1516 files (313.6 MB), approximately 26.5M tokens, and a symbol index with 9 extracted functions, classes, methods, constants, and types. Use this with OpenClaw, Claude, ChatGPT, Cursor, Windsurf, or any other AI tool that accepts text input. You can copy the full output to your clipboard or download it as a .txt file.
Extracted by GitExtract — free GitHub repo to text converter for AI. Built by Nikandr Surkov.