Synthetic research
Also called synthetic user research, AI-led user research
Synthetic research is user research run with AI participants instead of recruited people: interviews, usability tasks and studies where the participants are personas played by AI agents.
A study looks the same as a human one on paper. There is a discussion guide, a set of tasks and a group of participants, and at the end a report groups what they did into themes.
What it changes is the time. A recruited round takes weeks to book, run and write up, and a re-test after a fix starts over. A synthetic round runs the same afternoon, and runs again after every change.
It works best as the first pass: it covers the ground so that sessions with real people go on the questions only people can answer, such as whether they would pay.
Where Stunt Double fits
Stunt Double runs interviews with persona participants who use the real product during the session, then writes a report with the evidence attached. Humans validate; actors go first.
Related terms
- Synthetic usersSynthetic users are AI agents given a persona (a background, goals and constraints) that stand in for real users in research or testing.
- Sycophancy in synthetic researchSycophancy is the tendency of language models to tell the person asking what they seem to want to hear. In synthetic research it shows up as simulated users who like every concept they are shown.
- Usability testingUsability testing watches people attempt real tasks in a product to find where they hesitate, make mistakes or give up.
- User personaA user persona is a profile of a type of person a product serves: who they are, what they are trying to do, what they know already and what gets in their way.