Prompt library
Draft evidence-based customer personas
Personas rot when they are demographic fiction; anchoring every attribute to cited evidence and quarantining assumptions keeps them empirical. The decision-it-changes test is the filter that separates working personas from slide decoration.
Last reviewed July 17, 2026
The prompt
Build customer personas from the evidence below. Do not invent demographic decoration.
Evidence: {{evidence}}
Method:
1. Cluster the evidence by observed behavior and situation (trigger, alternative considered, buying constraint), not by age or job title alone.
2. Produce 2-4 personas. For each: the situation they are in, the trigger that starts their search, the alternatives they weigh (including doing nothing), their decision criteria in priority order, the objection that stalls them, and the exact vocabulary they use (quote from evidence).
3. For every attribute, cite which piece of evidence supports it. Attributes with no evidence go in an "assumed, needs validation" list per persona.
4. End with the marketing decision each persona changes: channel, message, or offer. A persona that changes no decision gets cut.
State how confident the clustering is given the evidence volume.Run in idaptOpens a new chat with the prompt prefilled. Nothing sends until you press send.
Fill in the variables
| Variable | What it is | Example |
|---|---|---|
| {{evidence}} | Interviews, survey results, support tickets, reviews | [paste interview notes, survey exports, review excerpts] |