As of 13 August 2026, AI can only partly create a user persona for your UK customers.

What to actually do

1. Hand it to a person

   The route this page recommends

   A person who owns the outcome does this end to end, worth it when the failure is dear.

2. Use a tool built for this

   Second choice

3. Do it yourself

   The distant third

   A chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.

   How to actually do it

   1. Open one document containing the customer research you are allowed to use, including interview notes, survey findings, support themes and relevant analytics.
   2. Remove names, contact details and other personal information that the persona does not need, then group the remaining evidence by customer need, behaviour, barrier and decision factor.
   3. Write down the product decision the persona must inform and the customer group covered by the research.
   4. Paste the business context, customer group and evidence into the prompt, keeping different research sources clearly labelled.
   5. Ask the chatbot to produce the persona and the separate evidence, interpretation and unsupported-claim table specified in the prompt.
   6. Compare every characteristic, motivation, behaviour and quote in the draft against the original research, deleting claims that have no supporting evidence.
   7. Send the checked draft to a product or research colleague and ask them to challenge the customer group, assumptions, missing viewpoints and proposed product implications.
   8. Save the final persona with its evidence links, open questions and the date of the research, then use it as a decision aid rather than as a substitute for new customer research.

   Prompt

   Create a UK customer persona from the research below. Use only evidence in the supplied material and clearly label any interpretation as an interpretation. Do not invent demographics, quotes, motivations, behaviours, locations, income, accessibility needs or technology use. If the evidence is too thin or contradictory, say so instead of filling the gaps.
   
   Produce:
   1. A short persona name that is not a real person's name.
   2. A one-sentence summary.
   3. Relevant characteristics, with each claim linked to the research evidence.
   4. Goals and jobs to be done.
   5. Needs, frustrations and barriers, including any accessibility or inclusion issues explicitly supported by the research.
   6. Behaviours and decision factors.
   7. What this customer is not, to prevent the persona being overgeneralised.
   8. Three representative quotes copied exactly from the research, with the source identified. If there are no suitable quotes, say that.
   9. Product, service and content implications.
   10. Open questions and assumptions that need further research.
   11. A table separating direct evidence, reasonable interpretation and unsupported claims.
   
   Keep the persona specific enough to guide decisions but do not present it as representative of all UK customers. End with five checks a product colleague should make against the original research before using it.
   
   Business context: [describe the product, service and decision this persona will inform]
   Customer group being investigated: [describe the group without adding assumptions]
   Research material: [paste interview notes, survey findings, support themes, analytics or other evidence]

   Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.