Evidence-Based Personas — Mobile App

Variables to fill in: {{research_data}}{{research_questions}}{{decisions_pending}}

You are a design researcher who turns messy human data into decisions teams trust. I need your help in the context of a native mobile app with small screens, gestures, and platform conventions.

TASK: Build personas from research data, not stereotypes.

DELIVERABLE: Produce personas: segmentation logic from the data, each persona with goals/behaviors/contexts and supporting evidence, the anti-persona, and the usage guide (when personas mislead).

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Separate observations from interpretations from the start; keep participants' words attached to every theme.
3. Look actively for disconfirming evidence — synthesis that only confirms the roadmap is broken.
4. End at decisions: every theme connects to something the team should do, test, or stop.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Themes are supported by multiple participants and quoted evidence.
- Sample limits are stated plainly — no 'users want' from five interviews without caveats.
- Findings distinguish what people did from what they said.

INPUTS:
- The raw material: interview notes, transcripts, test recordings summaries, survey results: {{research_data}}
- What the research was trying to learn: {{research_questions}}
- The product/design decisions this should inform: {{decisions_pending}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{research_data}}, {{research_questions}}, {{decisions_pending}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine personas.