Customer Persona Builder
Most advertisers target on demographics alone: woman, 25-45, based in a major city. That's not the problem. The real problem is not knowing what that person is thinking about at 2am, or what excuse she invents right before checkout. The surface question is who to target; the deep question is why this person buys, and why she doesn't. This prompt pulls personas out of your real customer data, personas rooted in pain, objection, and buying trigger. It puts your ad copy and your targeting on the same foundation.
You are an experienced performance marketer and buyer psychologist. Your expertise: decoding buying behavior from raw customer data (reviews, objections, questions, return reasons) and turning it into ad targeting. Your job is NOT to write a generic demographic profile; it's to extract why this person buys, why she hesitates, and the trigger that moves her to act. I'll give you: - [PRODUCT AND PRICE] - [CHANNEL: where I sell] - [EXISTING CUSTOMER DATA: reviews, DM questions, return reasons, survey answers, order notes] - [ANY DEMOGRAPHIC INFO I ALREADY HAVE] DELIVER THE OUTPUT IN THIS EXACT ORDER, WITH THESE EXACT HEADERS: ═══ 2-3 BUYER PERSONAS ═══ For each persona: short name plus one-line summary, core motivation (what she's trying to solve), biggest objection (the excuse right before purchase), buying trigger (what gets her to yes), the channel where she's most active. ═══ AD ANGLE FOR EACH PERSONA ═══ One hook line that breaks the objection, plus one soft CTA that uses the trigger. ═══ WHICH ONE TO LEAN INTO FIRST ═══ Flag the persona with the highest volume or easiest conversion based on the data, state why in one sentence. RULES: - Base this only on the data I give you. Do NOT invent demographics, income, or occupation that isn't in the data. - No made-up statistics, no "the average customer is like this" cliches. - Every persona must tie back to a real quote or behavior; if it doesn't, say "this isn't in the data, ask this question instead." - Write in plain, direct, actionable language. Skip the jargon.
How to use it
- Step 1: Hand over your product, price, and whatever raw customer data you have, as-is. Reviews, return reasons, DM questions, order notes, survey answers: all of it is gold. Put in real sentences, not invented demographics.
- Step 2: Focus the output on the trio of motivation, objection, and buying trigger. A persona only works if it answers 'why does she hesitate,' not just 'what does she want.'
- Step 3: Turn the personas into an ad set. Write one hook that breaks each persona's objection, one CTA that uses her trigger. Start with a single persona, test the rest as more data comes in.
Example / tip
Input: Handmade natural soap, $19, sold on Etsy. Customer reviews: 'my skin is sensitive, store-bought stuff always made me itch,' 'bought it as a gift, the box was so nice,' 'shipping was a bit slow but the product is great.' AI output (shortened): Persona 1, Sensitive-Skin Sarah: motivation is a chemical-free alternative, objection is 'is this actually different or just marketing,' trigger is ingredient transparency and dermatologist-style language. Persona 2, Gift-Buyer Grace: motivation is a thoughtful, good-looking gift, objection is 'will it arrive on time,' trigger is box visuals and clear shipping timelines, channel is Instagram.
Usage example
Copy the prompt as is, fill in the bracketed fields for your own business, and paste it into ChatGPT or Claude. The more concrete your input, the more useful the output. Take the first draft, ask for a one-sentence fix on whatever you don't like, then give it a final pass in your own voice.
When not to use it
Don't force it if you have no real input to work with. A prompt doesn't fill an empty field with data, it organizes and speeds up what you already know. Never publish the output unchecked; AI sometimes produces a claim that sounds right but is wrong or made up. Always verify anything that needs proof yourself: numbers, prices, guarantees.
Output quality checklist
- Is the output specific to your input, or generic filler that fits any business? If it's generic, run it again with more concrete input.
- Does every number, ratio, or claim have something backing it? Delete the unbacked ones or soften them honestly.
- Does it sound like you? Simplify the cliches and inflated lines in your own voice.
- Does it give one clear next step? If the reader knows what to do, the output did its job.
