Create personas with AI: step by step, backed by evidence, not invented

Create personas with AI in four steps

• 1. Collect material: reviews on comparison sites, posts in forums and communities, your own customer conversations, support requests, search queries from your campaigns. AI can search and summarize; check every quote you keep against its source.
• 2. Find patterns: which problems, triggers and objections come up more than once, from different people? Let the AI group them and check each group against the quotes behind it.
• 3. Write personas: for each persona, who they are, what they want to achieve and what makes them hesitate, backed by quotes. Mark what you infer as an assumption.
• 4. Check: do the personas really differ, or are they variants of the same person? Are there any who would push back on your offer? Is a group that buys from you missing?

Typical mistakes with AI personas

• Invented quotes: a language model writes statements that sound real. Without a source, a quote is not evidence.
• All the same: ten personas with the same situation and the same doubt show an average, not an audience.
• Only agreement: personas that approve every piece of copy are useless for checking. Language models tend to agree with their users; a study by Anthropic calls this “sycophancy”.
• Profile instead of decision: check whether the persona says what matters for their decision, or mainly age, hobbies and favorite brands.

A profile, or a persona that reads your copy

Classic personas are profiles a team reads. Synthetic users react to copy and pages themselves: you show them two versions and get objections and a choice. That is fast and works before launch, but it doesn’t replace measurement in the market. UX studio concludes that ChatGPT does not replace usability tests with real people; AIMultiple sees the main use in hypotheses and early tests. See synthetic users.

Create personas with 99takes in Claude

• 99takes researches your competitors and public customer voices in Claude and builds your audience from them: 10 to 14 personas covering a wide range, each piece of evidence with its source. Where evidence is missing, it says so, and an audience with no evidence at all is marked as a hypothesis.
• You set it up once for 15 credits. After that, the personas read your copy and pages in every check. See audience research.
• The verdict follows the personas the offer is made for; the extended audience is reported separately.
• To try it out, there are ready-made audiences, for example software buyers at mid-sized companies, or consumers.

Frequently asked questions