Synthetic survey respondents from real census data, with a calibration score

Every digital respondent is drawn from real age, sex, education and income structure. No panels. No wait. No guessing in the dark.

We don’t invent personas. We sample real, weighted respondent profiles from public microdata, condition a language model on each one, and aggregate the answers the way a real survey would.

Personas drawn from US Census microdata and World Bank population structure — real age, sex, education and income, weighted to the population.

A language model is conditioned on each individual respondent and answers your question in character — single choice, 1–5 scale or open text.

Weighted distribution, segment breakdowns, margin of error — plus a back-test against real data so you know the accuracy on your topic.

Synthetic respondents are a powerful shortcut — but they’re a model, not a mirror. Everyone else asks you to take it on faith. We measure the gap for you.

Lower is better — 0 = matches reality exactly, 20 = far off. Our best benchmark lands 2 points in; the average across six is 10. The bar isn’t meant to fill.

off the real 2020 US presidential vote — 86% of individual respondents predicted correctly.

average error across 6 public-opinion benchmarks — several within 1–7 points.

real respondents (Cooperative Election Study, public domain) used to validate.

Feed in a real labelled poll and calibrate mode simulates every real respondent, then reports how closely the prediction matches reality — mean error, total variation, per segment. You launch knowing whether this is a confident read or a loose hypothesis.

Pre-screen taglines, product concepts, packaging and naming across segments in minutes.

See how willingness and preference shift by age, income and market before you commit.

Directional reads on how different populations lean — with explicit confidence, not false precision.

Dry-run a questionnaire, spot dead questions and sharpen options before you field for real.

Simulated responses are directional. They can under-represent minority and extreme views. For high-stakes calls, calibrate first and validate with real fielding. We build that caution into every report — because a number you can trust beats a number that sounds confident.

Start free in the studio, go Pro for unlimited studies and the calibration score, or run the engine on Apify.