Create intermediate Works with: Any AI

Evidence-Based Persona Builder

Table output Has example

Create personas from real data.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Build personas from evidence. Research data (interviews, surveys, analytics, support tickets): [RESEARCH_DATA]. Product context: [PRODUCT_CONTEXT]. Number of segments: [NUMBER_OF_SEGMENTS].

Process: cluster participants by goals, behaviors, and contexts (not demographics alone); name the segments; for each, write a persona with a descriptive name, a photo-free description, role or situation, goals, tasks, pain points, behaviors, tools used, motivations, barriers, and representative quotes (verbatim, with source IDs). Include a "confidence" note for each element (strong evidence, partial, assumption) and the number of participants behind it.

Return a one-page persona format, a comparison table across personas, and a list of design implications ("Prioritize speed for X; provide guidance for Y"). Avoid stereotypes, avoid invented details such as hobbies unless evidenced, and mark assumptions clearly. Add a process to retire or update personas when new data arrives. Do not fabricate data.

Include a one-line summary of each persona suitable for a poster, the number of participants behind each, and one design decision that the persona would have changed in a recent project, to test its usefulness.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

Persona: Maya, the coordinator (based on 7 of 12 interviews).
Situation: schedules shifts for 15 part-time staff across two sites.
Goals: avoid double bookings; respond to swap requests fast.
Behaviors: keeps a spreadsheet and a chat group; checks messages every hour (quote, P4: "I am the human calendar").
Pains: last-minute swaps (6 of 7); no history of who covered what (4 of 7).
Barriers to a new tool: time to enter staff (5 of 7).
Confidence: strong for goals and pains; partial for tool preferences (assumption flagged).
Design implication: one-tap swap approvals and an import from spreadsheet.
Not included: age, hobbies, family status, which the data did not support.

• persona