Interview-Informed Generative Agents for Product Discovery: A Validation Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zichao, Siu, Alexa
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910090077929472
author Wang, Zichao
Siu, Alexa
author_facet Wang, Zichao
Siu, Alexa
contents Large language models (LLMs) have shown strong performance on standardized social science instruments, but their value for product discovery remains unclear. We investigate whether interview-informed generative agents can simulate user responses in concept testing scenarios. Using in-depth workflow interviews with knowledge workers, we created personalized agents and compared their evaluations of novel AI concepts against the same participants' responses. Our results show that agents are distribution-calibrated but identity-imprecise: they fail to replicate the specific individual they are grounded in, yet approximate population-level response distributions. These findings highlight both the potential and the limits of LLM simulation in design research. While unsuitable as a substitute for individual-level insights, simulation may provide value for early-stage concept screening and iteration, where distributional accuracy suffices. We discuss implications for integrating simulation responsibly into product development workflows.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29890
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Interview-Informed Generative Agents for Product Discovery: A Validation Study
Wang, Zichao
Siu, Alexa
Human-Computer Interaction
Artificial Intelligence
Large language models (LLMs) have shown strong performance on standardized social science instruments, but their value for product discovery remains unclear. We investigate whether interview-informed generative agents can simulate user responses in concept testing scenarios. Using in-depth workflow interviews with knowledge workers, we created personalized agents and compared their evaluations of novel AI concepts against the same participants' responses. Our results show that agents are distribution-calibrated but identity-imprecise: they fail to replicate the specific individual they are grounded in, yet approximate population-level response distributions. These findings highlight both the potential and the limits of LLM simulation in design research. While unsuitable as a substitute for individual-level insights, simulation may provide value for early-stage concept screening and iteration, where distributional accuracy suffices. We discuss implications for integrating simulation responsibly into product development workflows.
title Interview-Informed Generative Agents for Product Discovery: A Validation Study
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2603.29890