Prompt: Build a Customer Persona

A prompt for a customer persona grounded in supplied research, not invented demographics or made-up quotes.

The prompt

You are a market researcher building a customer persona for {{PRODUCT OR SERVICE}}.

Objective: Build one persona representing {{SEGMENT — e.g. small business owners who've outgrown spreadsheets}}, based only on the research notes supplied below.

Context: This persona will be used for {{USE CASE — e.g. briefing a copywriter on landing page tone}}. The research notes are:
{{PASTE RESEARCH NOTES OR SURVEY FINDINGS HERE}}

Constraints:
- Base every trait, goal and frustration on something stated or clearly implied in the research notes — do not invent demographics, job titles or quotes not present in the notes
- Exactly 4 sections: Snapshot, Goals, Frustrations, What would make them buy
- Snapshot: one short paragraph, no more than 40 words
- Goals and Frustrations: 3 bullets each, one sentence per bullet
- Flag, in a final line, any commonly expected persona detail (age, income, job title) the notes don't actually support

Output format: Return the 4 sections as Markdown headings with the content below each, followed by the flagged-gaps line.

Before finishing, check every claim traces back to the research notes and that Goals and Frustrations each have exactly 3 bullets.

Example

Input

PRODUCT OR SERVICE: Ledgerly, simple bookkeeping software for sole traders
SEGMENT — e.g. small business owners who've outgrown spreadsheets: sole traders who currently track finances in a spreadsheet
USE CASE — e.g. briefing a copywriter on landing page tone: briefing a copywriter on landing page tone
PASTE RESEARCH NOTES OR SURVEY FINDINGS HERE:
  Survey of 30 sole traders: 22 said they use a spreadsheet for bookkeeping. Most common complaint was losing track of receipts and forgetting to log expenses until tax time. Several mentioned dreading the January tax deadline. Most said they'd pay for something that just "did it for them" with minimal setup. Nobody mentioned wanting extra reporting features.

Output

## Snapshot
A sole trader currently managing finances in a spreadsheet, who wants bookkeeping handled with minimal setup rather than more features to configure.

## Goals
- Keep expenses logged as they happen instead of reconstructing them later
- Avoid the scramble that currently happens around the January tax deadline
- Spend as little setup time as possible getting the system working

## Frustrations
- Losing track of receipts before they can be logged
- Forgetting to log expenses until tax time, creating a backlog
- Dreading the January deadline because records aren't kept up to date

## What would make them buy
Software that "just does it for them" with minimal setup, not one that adds reporting features nobody in the research asked for.

Flagged gaps: the notes give no age, income or specific job title/industry for this segment — these were not stated or implied and are left out rather than invented.

Why it works

Restricting the persona to the supplied research notes stops the model inventing a plausible-sounding age or income that has no basis in real data.
Fixing the section structure to exactly 4 parts keeps the persona usable as a quick briefing document rather than a sprawling profile.
Flagging unsupported but commonly expected details is more useful than silently omitting them, since it tells the reader what still needs research.

Why the basic version fails

“Create a customer persona for our product” almost always returns a name, an age, a stock photo description and a fabricated quote — none of it grounded in anything real. Teams then treat invented demographics as fact when briefing campaigns.

What this prompt fixes

Restricting every claim to the supplied research notes stops the model filling gaps with plausible-sounding fiction. The fixed 4-section structure keeps the persona short enough to actually be used in a briefing, and the flagged-gaps line makes clear what still needs research rather than hiding the gap behind an invented number.

Tips per model

ChatGPT likes to add a name and photo description by default — if you don’t want either, say so explicitly in the objective.
Claude tends to stick closely to only the supplied notes, which is the behaviour you want here even if the output feels sparser than a typical persona template.
Paste raw research notes rather than a summary — a summary you wrote yourself may already contain your own assumptions that the model then treats as fact.