Customer persona builder
Eight prompts that turn the customer data you already have (reviews, interview notes, support tickets, sales calls) into evidence-backed personas. You finish with a one-page persona, a jobs-to-be-done map, the buying journey with objections, matched messaging, and a short plan to validate whatever is still an assumption.
What's inside (8 prompts)
- 1. Persona signals from customer reviews Free
Paste reviews (yours or a competitor's) and extract who is buying, what triggered the purchase, what they value and what disappointed them, with every insight tied to a quote. - 2. Synthesize customer interviews into persona insights Free2 steps
Turn messy interview transcripts or call notes into a structured synthesis: patterns across customers, notable differences, and the quotes that matter, ready to build personas from. - 3. Pain points and needs from support tickets
Mine support tickets, chat logs or inbound emails for recurring problems, confusion and unmet needs that should shape your persona and your marketing. - 4. Jobs-to-be-done map for your persona
Map the functional, emotional and social jobs your customer is "hiring" you to do, including what they would use instead, so your persona explains why people buy, not just who they are. - 5. Buying journey and objections map
Map how your persona goes from first noticing the problem to buying, with the questions, objections and information they need at each stage. - 6. One-page persona profile (evidence labeled) 2 steps
Assemble your research into a clean, one-page persona your team will actually use, with each line labeled as evidence, inference or assumption, then stress-test it. - 7. Match messages, offers and channels to each persona
Translate a persona into usable marketing: key messages, headlines, hooks for ads and email, the offer framing that fits, and the channels to test first. - 8. Validate your persona: interview guide and survey 2 steps
Turn the assumptions in your persona into a short, unbiased interview guide and a quick survey, so you can confirm or correct the persona with real customers.
Free samples from this pack
Persona signals from customer reviews
Fill in: [business description] [reviews]
You are a customer research analyst. I want to understand who our customers are from what they write in reviews. Business: [business description] Reviews: [reviews] Evidence rule: ground every claim in the data I pasted. Label each insight as one of: (evidence) when it is directly supported, with a short quote or reference; (inference) when it is a reasonable reading of the data; (assumption) when the data does not cover it. Never invent quotes, demographics, percentages or customer names. If the data is too thin to support a conclusion, say so. Analyze the reviews and give me: 1. Customer segments: 2-4 distinct groups you can see in the reviews (based on situation, goal or experience level, not invented demographics). For each, quote 2 reviews that show it and estimate how many reviews fit it (count them, do not guess percentages). 2. Triggers: what was happening in their life or business that made them look for this. 3. Desired outcomes: what "success" looks like in their words. Quote phrases verbatim. 4. Delighters: what exceeded expectations. 5. Frustrations and deal-breakers: what disappointed people, especially in 1-3 star reviews. 6. Language bank: 15 exact phrases customers use that would work in marketing copy. 7. What the reviews cannot tell us: important persona questions this data does not answer. Keep it skimmable. Do not write a polished persona yet; this is raw material.
Synthesize customer interviews into persona insights
Fill in: [business description] [research question] [interview notes]
You are a qualitative researcher. I ran customer interviews to answer this question: [research question] Business: [business description] Interview notes (labeled by customer): [interview notes] Evidence rule: ground every claim in the data I pasted. Label each insight as one of: (evidence) when it is directly supported, with a short quote or reference; (inference) when it is a reasonable reading of the data; (assumption) when the data does not cover it. Never invent quotes, demographics, percentages or customer names. If the data is too thin to support a conclusion, say so. For each interview, write a compact summary: - Context: who they are and their situation (only what they said) - Trigger: what made them act now - Before: how they handled the problem previously - Desired outcome: in their words - Hesitations: what almost stopped them - Decision factors: what tipped them over - Best 2 quotes (verbatim) Keep each summary under 120 words. Do not merge interviews yet.
Now synthesize across all interviews: 1. Patterns: themes that appear in 3 or more interviews. For each, list which customers mentioned it and one representative quote. 2. Differences: where customers split into meaningfully different groups (by situation, motivation or decision process). Describe each potential persona group in 2 sentences and list which customers belong to it. 3. Surprises: anything that contradicts what a business like this would normally assume. 4. Answer to the research question in 4-6 sentences, labeled with evidence strength. 5. Gaps: what we still do not know and who we should talk to next (for example, people who churned or chose a competitor). Stay strictly within the interview data.
Questions
What exactly do I get?
8 copy-paste prompts (some are multi-step sequences) with fill-in [brackets], the goal of each prompt, the model it suits best, tips and an example output. It arrives as a Markdown file (opens in any text editor, Notion, Google Docs or Word).
Which AI do I need?
Any of ChatGPT, Claude or Gemini. This pack suits Claude, then Gemini, then ChatGPT best. Free plans handle most prompts; very long pasted inputs work better on paid plans with longer context.
How long does it take?
About 45-60 minutes in one session, depending on how much context you paste in and how much you edit.
Will it work for my business?
The prompts are templates. They work because you fill in your own details, but results vary with your input and the model, so always review the output. If the pack is not useful to you, ask for a refund.
Can I get a refund?
Yes. Email us within 14 days of purchase for a full refund. No questions asked.
Prompts for Business Community
A members-only space for people who use AI at work: new prompts as they are written, workflow breakdowns, and a place to ask how to get a specific result.
Email me when it opens