---
type: method
slug: research-synthesis
title: "Synthesise user research into insights"
category: "Product Development"
subcategory: "Discovery & research"
level: intermediate
source: https://deepstoryresearch.com/method/research-synthesis
publisher: Deepstory Research
---

> **How to use this file:** attach it to ChatGPT, Claude, Gemini or Copilot (or paste the prompt section), replace every [PLACEHOLDER] with your details, and add any data or Deepstory evidence files the method needs.

## When to use this method
- 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).

## Prompt

# 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.

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