Validated · Nature Machine Intelligence, 2025
Simulate human populations.
Understand real behavior.
AnthroSim generates demographically diverse AI personas and simulates realistic group conversations — with voting, real-time data, and intelligent moderation. At scale.
Request Early AccessValidated by peer-reviewed research
Nature Machine Intelligence · 2025
A psychometric framework for evaluating and shaping personality traits in large language models
University of Cambridge & Google DeepMind
Larger, instruction-tuned LLMs accurately emulate the full range of human personality traits — and those traits can be reliably shaped through prompts.
Read paper →PNAS · 2025
The potential existential threat of large language models to online survey research
Sean Westwood, Dartmouth College
LLM-powered synthetic respondents replicate human survey responses with high fidelity, evading standard bot-detection systems.
Read paper →Design Science · 2025
Enhancing design concept diversity: multi-persona prompting strategies for large language models
Feng, Hélie & Panchal, Purdue University
LLMs prompted with multiple distinct professional personas — especially using sequential strategies — produce significantly more diverse outputs than single-prompt approaches.
Read paper →What it produces
Concrete, structured output. Not hallucinations.
anthro-profile --count 1 --guidance "policy researcher"
Generated Profile
Dr. Sarah Chen
Age: 34
Occupation: Public Policy Researcher, Brookings Institution
Personality: Analytical, collaborative, evidence-driven
Political stance: Supports evidence-based climate policy; skeptical of partisan framing
Communication: Asks clarifying questions, cites sources, occasionally dry humor
Values: Scientific rigor, institutional trust, pragmatic compromise
anthro-chat --room climate-policy --subject "carbon pricing"
Simulated Conversation
Dr. Sarah Chen
Recent EPA data shows a 23% emissions reduction in states with carbon pricing. The mechanism works when implementation is consistent.
Recent EPA data shows a 23% emissions reduction in states with carbon pricing. The mechanism works when implementation is consistent.
Marcus Webb
That ignores energy poverty effects. My constituents can't absorb another fuel cost increase without direct rebates built in.
That ignores energy poverty effects. My constituents can't absorb another fuel cost increase without direct rebates built in.
Moderator
Bringing in Dr. Okafor, who has studied distributional effects of carbon markets in lower-income regions...
Bringing in Dr. Okafor, who has studied distributional effects of carbon markets in lower-income regions...
47 participants · 83 min · Voting: Support 58% / Oppose 27% / Undecided 15%
Profile Generation
Demographically diverse personas with age, occupation, personality, political stance, values, and AI-generated profile pictures.
Conversation Simulation
LLM-powered participation with real-time Kagi data integration, smart moderation, and meeting timers. 10–100 participants.
Voting & Analytics
Personality-driven voting, context-aware decisions, moderator-announced results, full JSON export.
Request Early Access
Early access participants receive preferred rates and priority onboarding.