About SpareBrain

In short

SpareBrain runs your idea — copy, a pricing page, a screenshot — past a group of fifteen simulated people, each dealt their own mood, money worries, and patience by chance, so you see where they’d agree and where they’d argue. It’s built for founders and small teams who want a gut-check before they spend real research budget. The honest caveat: it’s a starting point for sharpening what to ask real people next, not a replacement for talking to them.

Most “LLM as user” tools ask one model to play a persona and report back. The answer sounds reasonable — and collapses the variability of real people into a single confident voice. SpareBrain runs a cohort instead: simulated users whose underlying conditions are rolled by seeded dice outside the model, so the model embodies variance rather than inventing it.

Why cohorts, not personas

Each cohort member gets a starting hand of traits — mood, financial pressure, prior frustrations, expertise, attention, age, place — dealt per member by randomness outside the model, across six layers. Persona templates shape the probabilities, never the outcome: no combination is impossible, so the affluent-but-anxious and the skeptic-who-signs-up still occur, the way they do in real samples. The model’s job is to inhabit the hand it’s dealt.

This is measured, not assumed: against a conventional persona-only baseline on the same stimulus and model, nine of fifteen baseline responses opened with the identical sentence; the dice-dealt cohort produced fifteen distinct openers and roughly three times the length variance.

How to read a study

Splits carry the signal.Every generalisation must name its numbers (“9 of 15”). A summary that smooths disagreement into consensus is rejected and regenerated automatically.
The dissenting voice is verbatim. It is checked character-for-character against a real cohort response — never a paraphrase.
Strong consensus replicates; mid-range counts wobble. In same-seed replication tests, findings held by 12+ of 15 members were stable, split magnitudes moved by ±2, and counts of spontaneously mentioned themes swung widely. Read those as “this objection exists,” not “this many hold it.”
Trust is earned, not assumed. Until a use case has been checked against real research, every output stays exploratory — a hypothesis generator, not a finding.

What it refuses to do — until it’s earned trust

Purchase-intent prediction, willingness-to-pay, and conversion forecasting are structurally refused. Not because synthetic prediction is impossible — published work shows it can correlatewith human panels in specific, carefully controlled settings — but because those numbers don’t transfer: not across products, not across audiences, and never from a cohort that hasn’t earned that trust. A number that looks like a forecast will be treated as one, so until a use case has earned trust against your real data, none is produced. The refusal runs deep: even inside legitimate studies, a built-in check strips intent tallies (“11 of 15 would subscribe”) out of the summary and demands the objections and reasons instead.

Reproducibility

Every study records its seed. The same seed re-deals the identical cohort — same starting traits, ages, and locations — so duplicating a study and changing one thing (the copy, the model, the template) is a controlled comparison, not a vibe check. Randomness enters once, at study creation, and never inside the model.