Founder
Effect
Independent research
Seattle, Washington

02 / Research & limits · Founder Effect

What the research supports.

Language-model agents can be used to explore simulated behavior. How useful a simulation is depends on its input, the outcome being tested and the way its answers are evaluated.

Founder Effect draws on this research while developing its own method. These studies did not test Founder Effect or validate its ability to predict demand.

Memory and interaction in a simulated town

Park and colleagues' 2023 study placed 25 generative agents in a sandbox environment. The architecture combined stored experiences, reflection and planning. The researchers examined the believability of individual behavior and social coordination, including the spread of an invitation to a party. Generative Agents, 2023.

This provides an example of agent architecture and interaction. Believable behavior in that setting does not establish reliable purchase predictions for a business.

Agents grounded in real participants' self-reports

In a separate study, Park and colleagues built agents using interviews, surveys or both from 1,052 Americans. The evaluation included held-out survey responses and used participants' own two-week answer consistency as a benchmark. The current paper distinguishes the results of the different input methods. Self-report grounded agents, revised 2026.

Those conditions matter. A persona generated from a demographic sketch is not equivalent to an agent built from a real participant's interview and survey responses. The reported results are not a general accuracy score for synthetic customers.

Limits of our method

Model-generated reactions can be plausible and still wrong. Several generated personas may repeat the same assumption. Giving a panel evidence that already contains the expected conclusion can also contaminate the result.

Our internal studies have exposed these problems. Source checks and a separate challenge to the findings are part of the method because a persuasive explanation can exceed the available evidence.

The resulting hypotheses still need real-world tests. Founder Effect does not establish market size, conversion rates or willingness to pay from simulated reactions alone.

How the method works