Skip to main content
MethodProduct DevelopmentDiscovery & researchIntermediate

Synthesise user research into insights

Themes, insights, opportunity areas and recommendations from interview notes or survey data.

Use this task 2 quick questions, then open it in ChatGPT, Claude or Gemini.

This is a practical, copy-paste process for you have a pile of notes and need decisions. 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
# Synthesise user research into insights
Method by Deepstory Research: deepstoryresearch.com/method/research-synthesis

You are a product researcher. Follow the method below step by step. Goal: Themes, insights, opportunity areas and recommendations from interview notes or survey data.

## My inputs
- Raw notes or transcripts: [RAW_NOTES_OR_TRANSCRIPTS]  (example: attach)
- Research goal: [RESEARCH_GOAL]  (example: original questions)

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. Extract observations with participant IDs.
2. Cluster into themes (affinity mapping).
3. Write insights as "users do X because Y, which means Z".
4. Count frequency and note strength.
5. If useful, add a jobs-to-be-done view: the core functional job plus emotional and social jobs, the job steps, and the desired outcomes that current solutions under-serve.
6. Turn insights into opportunities and recommendations.

## Deliver the output in this structure
- Theme map
- Insight statements with evidence
- Frequency table
- Jobs-to-be-done view, if used (job statements, job map, under-served outcomes)
- Opportunities
- Open questions

## Quality rules
- Every insight cites participants; do not generalise from one voice.
- Job statements contain no solution in them.
- 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
Raw notes or transcripts[RAW_NOTES_OR_TRANSCRIPTS]attach
Research goal[RESEARCH_GOAL]original questions

Use it when

  • You have a pile of notes and need decisions.
  • Reframing a crowded market around the job customers are trying to get done (jobs-to-be-done).

What you get

  • Theme map
  • Insight statements with evidence
  • Frequency table
  • Jobs-to-be-done view, if used (job statements, job map, under-served outcomes)
  • Opportunities
  • Open questions

The procedure, step by step

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

  1. 1

    Extract observations with participant IDs.

  2. 2

    Cluster into themes (affinity mapping).

  3. 3

    Write insights as "users do X because Y, which means Z".

  4. 4

    Count frequency and note strength.

  5. 5

    If useful, add a jobs-to-be-done view: the core functional job plus emotional and social jobs, the job steps, and the desired outcomes that current solutions under-serve.

  6. 6

    Turn insights into opportunities and recommendations.

Quality checks built into the prompt

  • • Every insight cites participants; do not generalise from one voice.
  • • Job statements contain no solution in them.
  • • 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.