Model how real voters respond to policy positions.
Simulate town halls, constituent meetings, and policy rollouts with demographically accurate, personality-driven participants — before you go public.
Request Early AccessThe blind spots in political research
Polling tells you positions. It doesn’t tell you how voters reason, what moves them, or how a message lands when challenged by competing views. And real constituent events are high-stakes, one-shot opportunities.
Example scenario: Ballot measure simulation
Step 1 — Generate profiles: 60 participants · Guidance: “likely voters in a swing suburban district, mixed income, family-oriented, homeowners and renters”
Step 2 — Run simulation: Topic: “Measure J: 15% inclusionary zoning requirement for new developments over 10 units” · Duration: 90 min · Export: JSON
Output includes vote breakdown (Support / Oppose / Undecided) with representative statements organized by demographic group. Results are most reliable as directional signals — identifying where a message is vulnerable, which frames attract opposition, and what arguments move persuadable voters. Treat subgroup breakdowns as hypotheses to validate, not statistically precise predictions.
Research validation
Controlled research on AI-assisted persuasion dynamics has produced significant findings:
A note on responsible use
AnthroSim is a research and stress-testing tool. Results represent synthetic population behavior and should inform — not replace — real constituent engagement. Simulation outputs are directional; subgroup-level breakdowns are hypothesis-generating, not statistically definitive.
Research has established that AI-powered persuasion can be remarkably potent — which makes this technology valuable for pre-deployment message testing and a serious responsibility to handle carefully. Improbability Engineers, LLC does not support use of this platform for deceptive political operations, automated influence campaigns, or the targeting of real individuals.
Request Early Access
We're onboarding a first cohort of researchers and industry teams — academic and applied researchers, market research firms, enterprise AI and product teams, and policy organizations.
Early access participants receive preferred rates and priority onboarding.