Sign inCreate account

How a study works.From start to finish.

Test with evidence-backed cohorts before the budget commits.

See what you define, how a study runs on behavior we recorded, and how every result traces back to the question behind it, including the questions it will refuse.

You defineSteps 1–2

Set the conditions. Simulate what comes after.

Start with the decision and what success means. Choose the audiences who can affect it, then write the questions that test each option. Four question shapes cover most of what people bring.
  • Creative

    “Will this ad stop the scroll?”

    What comes back

    Stop rate · split by cohort · the reasons, in each audience's voice

  • Positioning

    “Which of these three lines lands, and with whom?”

    What comes back

    Per-version split · a winner only when it is earned · too close called honestly

  • Risk

    “Who will read this the wrong way?”

    What comes back

    Objections by cohort · how backlash could spread · what to change

  • Audience

    “Who is engaging with this space?”

    What comes back

    Audience profiles · what they engage with · who they are

Inside a runSteps 3–4

Audiences built from behavior answer from their own evidence.

The step that separates this from prompting a model with a demographic description: each audience answers from a brief of what its members actually did, and says how they would split, not what one imagined person would say.

Each audience loads its brief: who its members are, what they engage with and how they write. It then states how its members would split across your options. Where audiences are linked, later rounds see how their neighbors reacted, the way a message travels through a real feed.

rounds 2…n · opinions carry forwardBrief
message + audience, in plain language
Match
audiences drawn from the catalog
Answer
each audience states its split
Spread
reactions pass between linked audiences
Report
recommendation, split, reasons
Enforced at every stepNo cohort below 100 real accounts · no individual ever addressable · every share carries its range
Figure 2 · One study, end to end. Steps three and four repeat: where audiences are linked, one answering in a later round has already seen how its neighbors reacted, the way a message travels through a real feed.

The comparison against what you already use. It decides whether the rest of this page is relevant to you, and nothing in the fast half of the chart replaces a panel.

slower ← turnaround → fasterindicative ← evidential weight → defensibleSurvey paneldays–weeksFocus groupweeksDesk researchdaysSynthetic personasminutesMimiminutes
Figure 1 · Where each method sits. Nothing in the fast half replaces a panel for a claim that has to survive scrutiny. The gap this fills is the weeks of guessing that happen before anyone can justify commissioning one.
MethodStrongest atTurnaroundReach for it when
Survey panelReal humans; defensible for regulated claimsDays–weeksThe number must survive legal or procurement
Focus groupDepth, follow-ups, genuine surpriseWeeksYou do not yet know what to ask
Synthetic personasInstant and cheapMinutesNothing is riding on the answer
MimiDirection and disagreement, grounded in recorded behaviorMinutesYou need to choose before you can justify fielding
What returnsStep 5

A recommendation with its evidence, never one confident sentence.

What to do and how sure it is; every option with its share and range; the split by cohort; where the cohorts disagree; and the reasons, written in each audience’s own voice.
Would stop scrolling41%Would keep scrolling34%Would comment16%a range, not a pointshareBy cohortwhere the headlinehides a disagreementUS · beauty commentary58%US · fitness & routine37%Global · food creators22%cohort gap36 pts
Figure 3 · Anatomy of a result. The headline is an average of audiences that may disagree, so the per-cohort split and the gap between the most different cohorts sit beside it. Where two options’ ranges overlap, the report calls them too close rather than ranking noise.

  • A recommendation

    What to do, how sure the result is, and what is working and what is not. It is marked high confidence only when a validated verdict backs it.

  • Shares with ranges

    Every option with its share and range. Where ranges overlap, the report says too close to call rather than ranking noise.

  • The split by cohort

    The headline is usually an average of audiences that disagree. Each cohort is shown separately, and the widest gaps are flagged.

  • Objections and backlash

    Who would object, what they would object to, how it could spread, and a specific change for each audience.

  • Follow-ups

    Ask the audiences why. Each answers in the way its members write. Answers explain a result; they never change it.

  • Stated limits

    Which audiences were thin, what the evidence does not cover, and what to test next with real people.

Audiences
4,021
you can test today
People
62M
observed, not invented
Per audience
≥100
real people, by construction
Median run
34s
most finish within a minute
What it will not tell youStated plainly

A buyer surprised in month three is worse than one who declines today.

These are construction limits, not small print. Each one is enforced by the platform itself. A study that hits one says so on the result rather than guessing past it.

Absolute forecasts

Direction and relative gaps hold up far better than a predicted percentage. Treat the numbers as a ranking, not a projection.

Audiences outside the catalog

If a brief matches thin cohorts, the platform says so rather than substituting neighbors.

Anything about an individual

Every cohort is an aggregate of at least 100 accounts, by construction. There is no individual to address.

Reactions to breaking events

Evidence carries a capture latency. A cohort does not know what happened yesterday.

Bring the question you were going to guess at.

Create account The platform underneath