Customer persona built from your real research

You are a customer research analyst. Build a customer persona from the evidence below. Do not invent details that are not supported by it.

Product or service: [WHAT YOU OFFER]
Segment I am focusing on: [e.g. "first-time buyers", "small agencies"]
How I will use the persona: [e.g. "to write website copy", "to prioritise features"]

Evidence (label each source):
"""
[S1] [INTERVIEW NOTES]
[S2] [CUSTOMER REVIEWS]
[S3] [SUPPORT TICKETS OR SURVEY ANSWERS]
"""

Produce the persona with these sections:
1. Name and one-line description (make clear the name is fictional).
2. Context: role, situation and what triggers them to look for a solution.
3. Goals and jobs to be done.
4. Pains and frustrations, using their own words where possible.
5. Objections and doubts before buying.
6. Where they look for information and whom they trust.
7. Words they use (and words they never use).

Rules:
- After every point, cite the source labels it comes from, e.g. [S1, S3].
- Mark anything that is a reasonable inference but not directly stated as "ASSUMPTION".
- Do not add demographics such as age, income or gender unless the evidence states them.
- End with "Evidence gaps": 5 questions to ask in the next customer interviews.

Example (excerpt):
Name: "Busy Bea" (fictional) — runs a two-person design studio and handles admin herself.

Trigger: misses an invoice deadline and loses a weekend fixing it. [S1, S3]

Pains: "I don't want another tool I have to learn." [S2] Sends invoices from her phone between client calls. [S1]

Objection: worries about moving client data from her spreadsheet. ASSUMPTION based on two tickets about imports. [S3]

Evidence gaps: How do they currently chase late payments?

When to use it

Use this prompt when your team talks about “the customer” but everyone pictures someone different. It is helpful before writing a website, planning a campaign or deciding which features to build. It works best once you have some real material: a handful of interviews, a page of reviews, or a sample of support tickets. It is also a quick way to see how much real evidence you actually have.

How to customize it

• [PRODUCT OR SERVICE] and [SEGMENT] keep the persona narrow. One sharp persona is more useful than one that tries to describe everyone.
• [HOW I WILL USE THE PERSONA] changes the emphasis. Copywriting needs language and objections; product work needs goals and workflows.
• [EVIDENCE] is the most important input. Label each source so the model can cite it. Remove personal data such as names and emails before pasting.

Why it works

Many personas are fiction dressed up as research: a stock photo, an age, a hobby and a set of guesses. This prompt pushes the other way. Requiring a source label after every point makes the persona auditable, and the “ASSUMPTION” tag separates inference from evidence. It is the same idea as asking a retrieval-augmented system to cite its sources.

The ban on unsupported demographics prevents a common form of stereotyping and keeps the focus on behaviour and motivation, which usually matter more for decisions. Using customers’ own words gives you copy you can test directly. The “Evidence gaps” section turns the persona into a research plan, not a finished document.

Tips and variations

• Share the persona with people who talk to customers every day, such as support or sales staff, and ask what feels wrong; their corrections are often the most valuable evidence.
• Build two or three personas from the same evidence and ask the model to list where they genuinely differ.
• Ask for a one-paragraph “day in the life” scenario, still with source labels, to share with the wider team.
• Revisit the persona every few months with new evidence; customers and markets change.
• If you collect data from customers, follow your privacy policy and local data protection rules.
• For marketing context, see how AI is changing marketing and advertising.