Skip to main content
MethodOperations, Supply Chain & ManufacturingManufacturing & qualityStarter

Find the root cause of a problem (5 Whys + fishbone)

A structured root-cause investigation with fishbone categories, 5 Whys chains and corrective actions.

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

This is a practical, copy-paste process for a defect, outage or complaint keeps recurring. 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
# Find the root cause of a problem (5 Whys + fishbone)
Method by Deepstory Research: deepstoryresearch.com/method/root-cause-analysis

You are a quality engineer trained in lean and six sigma. Follow the method below step by step. Goal: A structured root-cause investigation with fishbone categories, 5 Whys chains and corrective actions.

## My inputs
- Problem statement: [PROBLEM_STATEMENT]  (example: 8% of bottles leaking after filling)
- Where and when: [WHERE_AND_WHEN]  (example: line 2, night shift, since March)
- Data available: [DATA_AVAILABLE]  (example: defect logs)

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 a precise problem statement (what, where, when, how much).
2. Brainstorm causes on a fishbone (people, method, machine, material, measurement, environment).
3. Run 5 Whys on the most likely causes.
4. Propose how to verify each root cause with data.
5. Define corrective and preventive actions (CAPA).

## Deliver the output in this structure
- Problem statement
- Fishbone
- 5 Whys chains
- Verification plan
- CAPA plan

## Quality rules
- Stop at a cause you can act on; never stop at "human error".
- 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
Problem statement[PROBLEM_STATEMENT]8% of bottles leaking after filling
Where and when[WHERE_AND_WHEN]line 2, night shift, since March
Data available[DATA_AVAILABLE]defect logs

Use it when

  • A defect, outage or complaint keeps recurring.

What you get

  • Problem statement
  • Fishbone
  • 5 Whys chains
  • Verification plan
  • CAPA plan

The procedure, step by step

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

  1. 1

    Write a precise problem statement (what, where, when, how much).

  2. 2

    Brainstorm causes on a fishbone (people, method, machine, material, measurement, environment).

  3. 3

    Run 5 Whys on the most likely causes.

  4. 4

    Propose how to verify each root cause with data.

  5. 5

    Define corrective and preventive actions (CAPA).

Quality checks built into the prompt

  • • Stop at a cause you can act on; never stop at "human error".
  • • 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.