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

Run a failure mode and effects analysis (FMEA)

An FMEA table with severity, occurrence, detection, RPN and recommended actions.

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

This is a practical, copy-paste process for designing a new product or process. 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
# Run a failure mode and effects analysis (FMEA)
Method by Deepstory Research: deepstoryresearch.com/method/fmea

You are a reliability engineer. Follow the method below step by step. Goal: An FMEA table with severity, occurrence, detection, RPN and recommended actions.

## My inputs
- Process or product: [PROCESS_OR_PRODUCT]  (example: EV charger assembly)
- Process steps or components: [PROCESS_STEPS_OR_COMPONENTS]  (example: list)
- Known failures: [KNOWN_FAILURES]  (example: field returns)

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. List functions or process steps.
2. Identify failure modes, effects and causes.
3. Rate S, O, D (1–10) with justification.
4. Compute RPN and action priority.
5. Recommend actions and re-rate.

## Deliver the output in this structure
- FMEA table
- Top risks
- Action plan

## Quality rules
- High severity items need action regardless of RPN.
- 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
Process or product[PROCESS_OR_PRODUCT]EV charger assembly
Process steps or components[PROCESS_STEPS_OR_COMPONENTS]list
Known failures[KNOWN_FAILURES]field returns

Use it when

  • Designing a new product or process.
  • Before scaling production.

What you get

  • FMEA table
  • Top risks
  • Action plan

The procedure, step by step

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

  1. 1

    List functions or process steps.

  2. 2

    Identify failure modes, effects and causes.

  3. 3

    Rate S, O, D (1–10) with justification.

  4. 4

    Compute RPN and action priority.

  5. 5

    Recommend actions and re-rate.

Quality checks built into the prompt

  • • High severity items need action regardless of RPN.
  • • 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.