Skip to main content
MethodProduct DevelopmentDiscovery & researchStarter

Plan and run user interviews

A research plan and interview guide that uncovers real behaviour, not polite opinions.

Use this task 3 quick questions, then open it in ChatGPT, Claude or Gemini.

This is a practical, copy-paste process for validating a problem before building. Use it when you want a clear structure, then add your own details.

Published by Deepstory Research. Reviewed Sep 2026.

How to use this method

  1. 1. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
  2. 2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
  3. 3. Add your materialAttach your own files, data or brief so the AI works from your facts, not guesses.

The prompt

Paste it as-is. The AI will ask for anything still in [BRACKETS].

Download .md
# Plan and run user interviews
Method by Deepstory Research: deepstoryresearch.com/method/user-interview-guide

You are a senior UX researcher. Follow the method below step by step. Goal: A research plan and interview guide that uncovers real behaviour, not polite opinions.

## My inputs
- Research goal: [RESEARCH_GOAL]  (example: why small shops stop using our billing app)
- Participants: [PARTICIPANTS]  (example: 8 churned users)
- Session length: [SESSION_LENGTH]  (example: 30 minutes)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. Write research questions (what we need to learn).
2. Define recruitment criteria and screener.
3. Write an interview guide: warm-up, past-behaviour questions, deep dives, wrap-up.
4. Remove leading and hypothetical questions.
5. Create a note-taking template.

## Deliver the output in this structure
- Research questions
- Screener
- Interview guide
- Note template
- Consent script

## Quality rules
- Ask about past behaviour ("tell me about the last time…"), never "would you use…".
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

What you need to give the AI

InputPlaceholderExample
Research goal[RESEARCH_GOAL]why small shops stop using our billing app
Participants[PARTICIPANTS]8 churned users
Session length[SESSION_LENGTH]30 minutes

Use it when

  • Validating a problem before building.
  • Understanding why users churn.

What you get

  • Research questions
  • Screener
  • Interview guide
  • Note template
  • Consent script

The procedure, step by step

Read this before you run it, so you can check the AI actually followed the method.

  1. 1

    Write research questions (what we need to learn).

  2. 2

    Define recruitment criteria and screener.

  3. 3

    Write an interview guide: warm-up, past-behaviour questions, deep dives, wrap-up.

  4. 4

    Remove leading and hypothetical questions.

  5. 5

    Create a note-taking template.

Quality checks built into the prompt

  • • Ask about past behaviour ("tell me about the last time…"), never "would you use…".
  • • Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].

Evidence for this method

This method runs on your own material: your files, brief or code. If your task needs market or economic numbers, attach a sourced context file from the evidence library alongside the prompt.

Browse evidence

Run next

Methods that chain well after this one.

Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment decisions need a qualified professional.