Method note · Solutions
Asking a real audience, before the budget commits
What a study answers, how one runs, what comes back, and where this sits against the alternatives you already use.
In short
A study puts one message in front of cohorts compiled from accounts that already posted, already followed and already reacted, and returns a distribution with confidence intervals — never a single confident answer. It is a triage instrument: it tells you which direction to take and which audience disagrees, in the time it takes to brief an agency. It is not a replacement for a panel when a number has to survive procurement, and it does not forecast absolute outcomes.
- Cohorts
- 485
- each ≥100 accounts
- Accounts
- 265K
- resolved, not sampled
- Reactions
- 311K
- observed, not inferred
- Voice samples
- 9.9K
- indexed for tone
01Where this sits against what you already use
The honest comparison first, because it decides whether the rest of the page is relevant to you. Nothing in the fast half of this chart replaces a panel.
| Method | Strongest at | Turnaround | Reach for it when |
|---|---|---|---|
| Survey panel | Real humans; defensible for regulated claims | Days–weeks | The number must survive legal or procurement |
| Focus group | Depth, follow-ups, genuine surprise | Weeks | You do not yet know what to ask |
| Synthetic personas | Instant and cheap | Minutes | Nothing is riding on the answer |
| Project SIMS | Direction and divergence, grounded in recorded behaviour | Minutes | You need to choose before you can justify fielding |
02What a study answers
Four question shapes cover most of what people bring. Each returns the same structure: a distribution, the split by cohort, and the quotes behind it.
| Use | The question, as people ask it | What comes back |
|---|---|---|
| Creative | “Will this ad stop the scroll?” | Stop rate · split by cohort · representative comments |
| Positioning | “Which of these three lines lands, and with whom?” | Per-variant distribution · pairwise gaps · ties called honestly |
| Risk | “Who will read this the wrong way?” | Divergence by cohort · the dissenting quotes |
| Audience | “Who is actually engaging with this space?” | Cohort profiles · observed topics · reach percentiles |
03How a study runs
The step that separates this from prompting a model with a demographic description is the fourth. Reactions move along ties that were recorded, so a message entering a dense community behaves differently from one entering the periphery — because it does.
04What comes back
| Element | What it is for |
|---|---|
| Distribution, not a verdict | Every option with its share and a 95% interval. Overlapping intervals are reported as tied. |
| The split by cohort | The headline is usually an average of audiences that disagree. Each cohort is shown separately, with its own sample size. |
| Divergence score | One number for how far apart the cohorts are. High means the average is hiding the finding. |
| Representative quotes | Drawn from the cohort's indexed voice, so tone is retrieved from what members actually wrote rather than invented. |
| Stated limits | Which cohorts were thin, what the evidence does not cover, and the run's own parameters. |
05What a study will not tell you
Stated plainly, because a buyer who is surprised in month three is a worse outcome than one who declines today.
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 catalogue
If a brief matches thin cohorts, the platform says so rather than substituting neighbours.
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.