---
type: method
slug: root-cause-analysis
title: "Find the root cause of a problem (5 Whys + fishbone)"
category: "Operations, Supply Chain & Manufacturing"
subcategory: "Manufacturing & quality"
level: starter
source: https://deepstoryresearch.com/method/root-cause-analysis
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
- A defect, outage or complaint keeps recurring.

## Prompt

# 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.

---
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.
