Build a one-page persona from the real customer evidence below (transcripts, surveys, support tickets, sales notes - any direct customer voice). Use exactly these 5 sections:
1. Who they are: role, context, demographic shape. Cite the source ('5/8 interviews fit this shape').
2. What they're trying to do: their job-to-be-done in their words. Include a verbatim quote.
3. What's getting in the way: evidence-backed pain. Include a verbatim quote and a count of how many sources mentioned it.
4. Current workaround: what they do today to cope. Often 'do nothing' or 'use a template' - both are valid.
5. What would change for them: if you solved the pain in section 3, what concretely changes in their week.
Do not invent quotes. If you can't find evidence for a section, write 'no direct evidence in input' rather than fabricate.
The evidence:
{{customer_evidence}}
Persona from real evidence
Add to PromptPaste
Download PromptPaste for MacDownload PromptPaste for iPhoneDownload PromptPaste for iPadDownload PromptPaste for Mac & iPhone
the prompt
Example output
Persona: 'Maya, the busy growth PM at a Series B SaaS'
Who she is: 28-34, 2-4 years PM experience, owns one product surface (not the full product), reports to a Head of Product or VP. Manages 1-2 features and ~5 engineers, no direct reports. Sources: 6/9 interviews fit this shape.
What she's trying to do: Ship 1-2 meaningful improvements per quarter that show up in retention dashboards. Not building net-new products; iterating on a known surface. Quote: 'I'm not allowed to invent. I'm allowed to make this thing 10% better.'
What's getting in the way: Spends ~40% of week on writing - PRDs, retros, stakeholder updates, decision memos. None of it is the work she's measured on. Quote: 'My quarterly review never asks how good my Friday update was.' Mentioned in 7/9 interviews.
Current workaround: Templates copied from prior PRDs, ChatGPT for first drafts (then heavy editing), 'Sunday writing time' to catch up.
What would change if you solved it: 4-6 hours/week back, less Sunday work, more time for discovery (the part she's actually evaluated on but rarely gets to).
Common mistakes
Don't let the model invent quotes. If a claim doesn't have a verbatim source in your input, the persona section should say 'no direct evidence' rather than fabricate. Also: don't merge two personas into one. If 'busy growth PM' and 'senior staff PM' both appear in your data, ship two personas - merging produces a generic mush nobody recognizes. Third mistake: skipping the 'current workaround' section. It's the single most useful section because it tells you what you're competing against in the user's existing routine, which is almost always 'doing nothing' or 'using a template.'
More from AI Prompts for Product Managers
PRD draft from a one-line problem
Act as a senior product manager. I'm going to give you a one-line problem statement. Before drafting any PRD, do this: 1. State the…
Customer interview synthesis
Read the raw customer interview transcripts below. Produce: 1. The top 5 themes ranked by frequency (number of interviews where the theme…
Stakeholder weekly update
Convert my raw bullets below into a weekly stakeholder update. Use exactly three sections: 1. Shipped: each item with a one-line outcome,…
Why it works
Personas built from imagination are the worst documents in product. Personas built from real evidence are the best. This prompt does the second. Paste your transcripts, surveys, support tickets, or any direct customer voice, and get back a one-page persona that survives a 'where's the evidence?' challenge - because every claim is tied to a quote, a count, or a source. The output structure forces 5 sections: who they are (role, context), what they're trying to do (jobs not features), what's getting in the way (evidence-backed pain), how they currently work around it, and what would change for them if you solved it. Personas built this way are reusable across PRDs, marketing copy, design reviews, and exec pitches. Tested cleanest on Claude Opus 4.7.