Build a customer interview repository summary

Condense customer interviews into clean, standardized summaries ready to store in product research repositories.

Prompt

Prompt
Act as a UX research operations specialist. Convert raw customer interview notes into a structured insight repository card suitable for a central team knowledge base. Rules: Extract verifiable user pain points, workflows, and verbatim quotes; categorize insights by user journey stage; highlight product opportunities without prescribing technical solutions; tag relevant feature areas. Output format: 1. Metadata Block (Participant Profile, Journey Stage, Key Feature Tags), 2. Core Problem Statements (maximum 3, formatted as: Problem, Context, Severity), 3. Key Verbatim Quotes (3 compelling quotes with context), 4. Recommended Discovery Follow-ups. My interview notes are below:

Example output

Example for: call transcript with a B2B logistics coordinator

1. Metadata Block
  • Participant Profile: Logistics Coordinator at mid-market wholesale distributor (50 trucks managed)
  • Journey Stage: Route Dispatch & Daily Monitoring
  • Key Feature Tags: dispatch-board, driver-alerts, exceptions-management
2. Core Problem Statements
  • Problem: Drivers miss urgent route changes while driving.

    • Context: Coordinators send push updates, but drivers do not check their mobile apps while driving.
    • Severity: High (causes late deliveries and customer penalties).
  • Problem: Status indicators do not differentiate between scheduled stops and emergency detours.

    • Context: The dispatch map displays all stationary vehicles with the same yellow pin.
    • Severity: Medium (coordinators must open individual truck logs to diagnose delays).
3. Key Verbatim Quotes
  • "If a driver is already on the highway, sending an app notification is useless. I end up calling them on the phone anyway."
  • "I have 40 pins on my screen and half are yellow. I don't know who has a flat tire and who is just taking a lunch break."
  • "The weekly PDF export takes twenty minutes to load because our fleet history is so large."
4. Recommended Discovery Follow-ups
  • Audit current driver notification receipt rates versus confirmation timestamps in app telemetry.
  • Interview three fleet drivers to understand hands-free cab hardware usage during active routes.
Written by AI from this prompt. Your results will vary.

Paste this into ChatGPT, Gemini, or Claude, followed immediately by your raw interview notes or call transcript. If you store research in a specific tool like Notion or Dovetail, ask the model to format the output as a Markdown table or CSV.

Make it repeatable

Keep using this prompt without pasting it in every time.

Keep exploring

More in Meetings & Notes