QuestionPunkQuestionPunk
Start free

Synthetic testing with AI personas

Create AI-generated respondent personas and run them through your survey before launch.

Synthetic testing lets you create AI personas with specific demographics, attitudes, and backgrounds, then run them through your survey to pressure-test question flow, logic, and quality before real respondents see it.

testingqualityaisynthetic10-20 minutesIntermediateResearchersSurvey designersQA teams

Steps

  1. Start a synthetic test
    In the survey editor Build tab, click the Test with AI button to run a fast synthetic test. Choose how many respondents to run, then pick a respondent source: auto-generated diverse personas, an audience, custom targeting (describe who you want), panel-based personas, or digital twins of real respondents. You can also manage reusable personas on the AI Personas page and run them against any survey.
    Start a synthetic test
  2. Create personas
    Create personas in three ways: AI Generate (describe the persona and AI fills in details), from a template (pre-built demographic profiles), or Manual (specify every detail yourself). Personas are saved on the AI Personas page for reuse across surveys.
  3. Configure and run
    Pick a Respondent source (for example, auto-generated diverse personas or a saved list), set the Number of respondents (3, 5, or 10, or a custom number up to 500), and start the test. Under Advanced, turn on Diverse responses for more varied answers, or set Target marginals to steer multiple-choice answer shares. You can also run tests through different AI models to compare output quality. Before you start, the dialog shows an estimated credit cost (or "Free") that updates as you change the model, respondent count and run options, and a progress banner shows the estimated time while the run is in progress.
  4. Review synthetic responses
    Synthetic responses appear in the Results tab with a "synthetic" label. Compare how different personas answered to identify question issues, biased wording, or logic problems.

Synthetic testing is like a dress rehearsal for your survey. AI personas simulate real respondents, helping you catch issues before launch.

Personas can be created with AI assistance: just describe "a 35-year-old marketing manager who is skeptical of new tools" and the AI generates a complete persona profile.

Pre-built persona templates cover common demographics and archetypes, making it easy to test with a diverse set of simulated respondents.

Personas are stored on the AI Personas page and can be reused across multiple surveys, saving setup time for recurring studies.

Target marginals let you set the answer percentages you expect on multiple-choice questions (for example, from census figures), and Diverse responses samples each persona's answers from estimated probabilities so runs don't all answer alike.

Multi-model testing lets you run the same personas through different AI models to compare response quality and behavior. In Results > AI Runs, Structural audit (advanced) shows side-by-side results across models.

Fidelity reports compare synthetic responses against real human responses to measure how well AI personas mirror actual respondent behavior. The Human vs. Synthetic comparison view highlights where synthetic and real distributions align or diverge.

Run history tracks all synthetic test runs, so you can compare results across iterations as you refine your survey.