The Prompt Engineer logoThe Prompt Engineer

Marketing · Engineered

Build a Buyer Profile From Real Customer Evidence

Turn reviews, comments and call notes into a usable messaging profile.

You are a customer research analyst. Build a buyer profile using only the evidence I supply. Do not invent a persona.

EVIDENCE
[PASTE RAW MATERIAL — reviews, support tickets, survey answers, DMs, comments, sales call notes. Messy is fine.]
What I sell: [YOUR OFFER] at [PRICE]

METHOD
1. Extract the recurring language. List the exact phrases customers use for their problem, their goal, and their frustration — verbatim, with how many times each theme appears.
2. Separate what they SAY they want from what their behavior suggests they want. Flag any gap.
3. Identify the trigger event that made them start looking for a solution.
4. Identify what they tried before and why it failed them, in their words.
5. List objections and hesitations that appear in the evidence, ranked by frequency.
6. Note who else is involved in the decision, if the evidence shows it.

OUTPUT
- Profile summary in 150 words, written as one specific person, not a demographic
- Their problem in their own words, top 5 verbatim phrases
- Desired outcome, top 5 verbatim phrases
- Trigger events
- Failed alternatives and why
- Objections, ranked
- Words and phrases to use in my copy, taken straight from the evidence
- Words and phrases to avoid, because customers never use them or react badly to them
- The three strongest messaging angles this evidence supports, and one angle the evidence does NOT support even though I might assume it

RULES
- Every claim must trace to something in the evidence. Mark anything you inferred as [INFERRED] and say what it is based on.
- If the evidence is too thin for a section, write [INSUFFICIENT EVIDENCE] and tell me what to collect.
- Do not fill gaps with typical industry assumptions.

How to use this prompt

  1. Copy the whole template — the structure matters as much as the words.
  2. Replace every bracketed placeholder with your real details. Vague inputs produce vague output.
  3. Paste it into ChatGPT, Claude or Gemini and let it finish before you judge it.
  4. Give one round of feedback: name what to keep, what to cut, and what to change, then ask for the revised version.

Why it works

This prompt gives the model a role, the background it cannot guess, the outcome you actually want, the limits it must respect and the exact format for the answer. Those five pieces are the difference between a generic paragraph and something you can use. The words behind them are explained in the prompting glossary.

More free prompts

A template does not know your business. The Prompt Engineer does the asking for you.

Get The Prompt EngineerAll free prompts