Reverb
Start a study

What your customer thinks, before you build it.

Reverb gives you a fast, honest read on a product concept — first from Echoes, synthetic respondents that react like your target customer, then from verified humans when you need ground truth. Here's how it actually works.

The approach

Two kinds of panel, one workflow

Most research forces a choice: fast and cheap, or rigorous and slow. Reverb makes it a sequence. Screen broadly with Echoes in minutes; validate the survivors with real, verified people. The same brief, the same questions, one continuous flow.

Echoes

Screen for breadth

Synthetic respondents, each briefed to react as a specific slice of your market. Test twenty concepts, sweep a price, interrogate any reaction — for the cost of a few cents and a couple of minutes. A directional read that finds the risks fast.

Minutes 12–500 respondents
Verified humans

Validate for depth

When a decision is high-stakes, confirm the read with real, identity-verified people sourced to ESOMAR-grade standards. You get a side-by-side delta against the Echo prediction — and a calibration score that says exactly how close the synthetic layer was.

Identity-verified Days, not weeks
Screen with Echoes validate the winners with humans
The science of an Echo

The trick isn't the persona — it's how we ask

Ask a language model to rate a concept “1 to 5” and it does something useless: it hugs the middle, almost never commits to a strong yes or no, and produces ratings no real market would ever give. So we don't ask for a number.

1

Brief the respondent

Each Echo is conditioned on a real slice of your market — defined by category usage and buying behaviour, the attributes that actually shape a purchase decision. It reacts in character: its priorities, its scepticism, its budget.

2

Elicit a genuine reaction

Instead of a rating, we collect what the respondent would actually say — an honest, in-their- words reaction to your concept, plus what draws them in and what holds them back. No scale to game, no middle to hide in.

3

Map words to a rating distribution

We then translate each reaction into a purchase-intent distribution by measuring how closely it resembles a set of calibrated reference points — the meaning of the words, not a number the model invented. Aggregate across the panel and you get a realistic spread of intent, not a flat “everyone says 3.”

Grounded in peer-reviewed research

This isn't a clever demo. It's a published method.

The approach behind Echoes — eliciting language and mapping it to ratings by semantic similarity — was validated by researchers at PyMC Labs and Colgate-Palmolive against thousands of real consumer responses. On head-to-head tests it reproduced human purchase intent strikingly well.

~90%
of human test–retest reliability recovered on purchase intent
9,300
real human responses across 57 consumer surveys used to validate it
Matched
response distributions closely tracked the real human ones, not just the averages

Maier et al. (2025), “LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings.” arXiv:2510.08338. We build on this method and extend it with our own calibration layer.

Honest by design

We tell you what an Echo can't do

Synthetic respondents are a powerful instrument with real limits. The fastest way to lose your trust would be to pretend otherwise — so every Echo report says exactly how far to trust it.

What Echoes are great at

  • Surfacing the risks and objections in a concept, fast — before you spend on fieldwork.
  • Ranking variants, claims and price points against each other.
  • Realistic distributions of intent in categories the model knows well.
  • Letting you interrogate any reaction and rerun counterfactuals at near-zero cost.

What we won't claim

  • Echoes are a directional screen, not ground truth — for absolute numbers, validate with humans.
  • They're weaker in unfamiliar categories and non-Western markets — we flag those reports as uncalibrated.
  • We never cut synthetic results by gender or ethnicity — those are persona colour, not statistical signal.
  • Every report ships with a plain-English methods and limitations note. No black box.
What makes it better over time

The calibration loop

Most synthetic-research tools ask you to take their accuracy on faith. We'd rather show you.

Every human study teaches the Echoes

When you validate a finding with verified humans, we measure exactly how close the Echo prediction was and feed that back in. Over time the synthetic layer gets measurably sharper in your categories — and you see the score, per category, on every report.

Verified humans, actually verified

When you go to humans, they're sourced to professional (ESOMAR-grade) standards and can be confirmed as real, unique people through privacy-preserving identity verification — no personal data stored, each person counted once. The quiet fix for an industry with a real panel-fraud problem.

See what your market thinks — in the next five minutes.

Run your first Echo panel free. No fieldwork, no waiting, no black box.

Start a study