Plain-English, honest about the limits

Guides to synthetic audiences

What a synthetic audience is, how silicon sampling works, when to use a synthetic survey versus a real one, and how accurate the method actually is — written straight, with the caveats included.

What is a synthetic audience?

A synthetic audience is a set of AI respondents grounded in real population data, used to simulate a survey in minutes. Here is how it works, what it is good for, and where it breaks.

Read →

Synthetic survey vs real survey: when to use which

Synthetic and real surveys solve different problems. A practical guide to when a synthetic survey is the right first read and when you must field a real one.

Read →

What is silicon sampling?

Silicon sampling is the research technique behind synthetic audiences: conditioning a language model on real respondent profiles to simulate survey answers. Here is the idea and its limits.

Read →

How to test a concept before you pay for a panel

A step-by-step way to pre-screen taglines, concepts and pricing with a synthetic audience, so you only field a real panel on the ideas that survive.

Read →

How accurate are synthetic respondents?

An honest look at synthetic respondent accuracy: what the back-tests show, where the method is strong and weak, and why a calibration score matters more than a marketing claim.

Read →

How to run a Van Westendorp pricing study

The Van Westendorp Price Sensitivity Meter finds what a market will bear from four simple questions. Here is how it works, how to read the curves, and how to run one in minutes on a synthetic audience.

Read →

Attitudinal segmentation, explained

Attitudinal segmentation groups people by what they believe and value, not just their demographics. Here is how it works, why it beats age-and-gender buckets, and how to run it on a synthetic audience.

Read →
Try it

Poll a whole population in a coffee break.

Start free in the studio, with the calibration score that tells you how far to trust the result.