Pattern #22 · Research methods

Use synthetic users to prepare research, not to replace it

The AI participant will love your concept. That is the whole problem.

Track Aux researchsynthetic usersevidencesycophancystudy design

Do

Pilot a discussion guide, pressure test a screener, sketch a proto persona you plan to throw away.

Don't

Validate a concept. It will love the idea, and so will everyone you show the transcript to.

The rule. Synthetic users can shape a study before it runs; only real participants can be evidence inside it.

Why. Arora, Chakraborty, and Nishimura (2025) found that LLM simulated respondents reproduce the direction of human effects while missing their magnitude and their variability, which is exactly where effect sizes and edge cases live. The strongest result in the literature is also narrower than the category's marketing: Park et al. (2024) built agents from two hour interviews with 1,052 people, and those agents matched their own participant's General Social Survey answers at 83 percent of that person's two week test retest consistency, against 74 percent for a demographics only model. That is a decent replica of someone you already interviewed, not a stand in for someone you have not. Rosala and Moran (2024) name the failure mode teams actually hit: synthetic users are agreeable, greet new concepts as a game changer, and go vague under probing.

Seen in the wild. Synthetic Users, one of the better known products in the category, headlines its site "User research, without" and then concedes in its own FAQ that real user research "stays essential for validation and edge-case work" (verified as of August 31, 2026).

References

  1. 01

    Arora, N., Chakraborty, I., & Nishimura, Y. (2025). AI-human hybrids for marketing research: Leveraging large language models (LLMs) as collaborators. Journal of Marketing, 89(2), 43-70. https://doi.org/10.1177/00222429241276529

    https://doi.org/10.1177/00222429241276529
  2. 02

    Budiu, R. (2025, August 15). Evaluating AI-simulated behavior: Insights from three studies on digital twins and synthetic users. Nielsen Norman Group. https://www.nngroup.com/articles/ai-simulations-studies/

    https://www.nngroup.com/articles/ai-simulations-studies/
  3. 03

    Park, J. S., Zou, C. Q., Kamphorst, J., Egan, N., Shaw, A., Hill, B. M., Cai, C., Morris, M. R., Liang, P., Willer, R., & Bernstein, M. S. (2024). LLM agents grounded in self-reports enable general-purpose simulation of individuals. arXiv. https://arxiv.org/abs/2411.10109

    https://arxiv.org/abs/2411.10109
  4. 04

    Rosala, M., & Moran, K. (2024, June 21). Synthetic users: If, when, and how to use AI-generated research. Nielsen Norman Group. https://www.nngroup.com/articles/synthetic-users/

    https://www.nngroup.com/articles/synthetic-users/