InsightWorks with ChatGPT, Claude, Gemini

Customer personas from reviews and surveys

Build evidence-based personas from your own customer data, not stereotypes.

What you need

  • Survey answers or reviews
  • Basic customer data (AOV, repeat, channel)
  • Quiz results if any

The prompt

Using only the data below, build 3-4 customer personas for [BRAND].

Survey answers / reviews / quiz data: [PASTE]
Customer metrics by segment if available: [PASTE]

For each persona: name, share of customers (estimate from data), job-to-be-done, triggers to buy, barriers, the words they use, channels where we reach them, what they buy first and next, and one message that would resonate. Then list where personas overlap and what the data cannot tell us. Quote the data; do not invent demographics.

Replace everything in [BRACKETS]. Use a business or team account with training on your data switched off, and remove customer personal data before pasting.

What you get

Three or four evidence-backed personas with jobs, triggers, barriers, language and messages, plus gaps in the data.

The fortnightly brief

Get the brief

New AI tools worth a look, price changes, fresh deals and a real brand use case, for UK consumer brand teams. No spam, unsubscribe any time.