Synthetic users
Also called AI users, simulated users, AI personas
Synthetic users are AI agents given a persona (a background, goals and constraints) that stand in for real users in research or testing.
There are two kinds, and the difference is the whole argument. One kind is a language model asked to answer as a persona: it describes what it would do. The other drives a real browser through the real product: it does the thing, and you see the result.
The first is quick for an early read on a message or a name. The second is what you need to find the step where a flow breaks, because it produces something you can check.
Where Stunt Double fits
Stunt Double calls its synthetic users actors. Each has a persona, knowledge and an inbox, and each run returns what the actor did with a screenshot of every step.
Related terms
- AI user testingAI user testing sends AI agents with defined personas through a product in place of recruited participants, and reports what each one did and where it got stuck.
- Synthetic researchSynthetic 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.
- 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.
- 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.