assets/example-outputs/personas.md
Output: Personas
When: the goal is segments/personas from a series of interviews. You need ≥5 interviews, otherwise a persona = a stereotype. Input: nuggets (with role/segment) → clustering by segment, not by theme.
Grounding rule
A persona is not fiction, but an aggregate. Every persona attribute rests on ≥k different interviews with a verified quote.
One vivid respondent ≠ a persona. Mark [weak: n<k] if data is thin.
Persona format
## Persona: [archetype, not a name] — [segment]
Based on: N interviews (roles/segment)
Goals: [what they want] — «quote» (Interview, Lxx)
Behavior: [what they actually do, past facts] — «quote» (Lxx)
Pains: [pains, ranked] — «quote» (Lxx)
Barriers: structural vs operational
Triggers/motivators: [what drives them]
Difference from other personas: [how they differ]
Confidence: high/medium/low
Rules
- An attribute without ≥k confirmations → not into the persona, but into "hypotheses".
- Don't invent demographics that aren't in the data.
- Personas must DIFFER (if two are nearly identical — it's one).
- Record tensions between segments separately (more important than averaging).