Skip to content
Codextroop Prompt Library

Risk Assessment

Pre-Mortem Risk Audit

AI Tools:
ChatGPT + 3 moreWorks with ChatGPT, Claude, Gemini, Perplexity
Category: Problem Solving

Assume the plan already failed, list specific failure mechanisms, and change the plan while failure is still cheap.

Prompt Quality - 97/100 · Strong

The Prompt

pre-mortem-risk-audit.md

You are running a pre-mortem: assume the following plan has already failed, and work backward to explain why.

THE PLAN:
{{plan}}

TIMEFRAME:
{{timeframe}}

INSTRUCTIONS:
1. Assume it is {{timeframe}} later and the plan has failed clearly and undeniably. Do not hedge - commit to the premise.
2. Generate 8 - 10 distinct, specific reasons it failed. Avoid vague causes like "poor execution" - name the actual mechanism.
3. Sort into: things we could have predicted with information we already have vs things we genuinely couldn't have known.
4. For every predictable failure reason, propose one concrete change to the plan, right now, plus a "who should watch for this" note.
5. For unpredictable ones, propose one early-warning signal instead of a preventive fix.
6. Close with the single most likely failure mode, ranked by (probability × impact), and what to do about it this week.

OUTPUT FORMAT:
- Failure reasons (numbered, specific mechanisms)
- Predictable vs unpredictable split
- Preventive changes (table: Failure reason | Preventive change | What to watch)
- Top-ranked failure mode + this week's action

CONSTRAINTS:
- Write as if reporting on what happened - not "it might fail if..."
- Do not pad the list by restating the same cause in different wording. If you run out of distinct causes, say so with fewer, sharper ones.

Negative prompt

Included when you copy the prompt

Do not hedge into "it might fail if". Do not use vague causes like poor execution or communication. Do not invent facts about the plan that were not provided.

The PromptUTF-8

Fill in your details below - this prompt updates as you type, then copy it.

Fill in your details

0 of 2 filled. Preview updates as you type - then copy the finished prompt (negative prompt included when present).

What you are about to do - launch, project, decision, change.

When failure would be assessed, e.g. 3 months after launch.

pre-mortem-risk-audit.md

Prompt preview

You are running a pre-mortem: assume the following plan has already failed, and work backward to explain why.

THE PLAN:
{{plan}}

TIMEFRAME:
{{timeframe}}

INSTRUCTIONS:
1. Assume it is {{timeframe}} later and the plan has failed clearly and undeniably. Do not hedge - commit to the premise.
2. Generate 8 - 10 distinct, specific reasons it failed. Avoid vague causes like "poor execution" - name the actual mechanism.
3. Sort into: things we could have predicted with information we already have vs things we genuinely couldn't have known.
4. For every predictable failure reason, propose one concrete change to the plan, right now, plus a "who should watch for this" note.
5. For unpredictable ones, propose one early-warning signal instead of a preventive fix.
6. Close with the single most likely failure mode, ranked by (probability × impact), and what to do about it this week.

OUTPUT FORMAT:
- Failure reasons (numbered, specific mechanisms)
- Predictable vs unpredictable split
- Preventive changes (table: Failure reason | Preventive change | What to watch)
- Top-ranked failure mode + this week's action

CONSTRAINTS:
- Write as if reporting on what happened - not "it might fail if..."
- Do not pad the list by restating the same cause in different wording. If you run out of distinct causes, say so with fewer, sharper ones.
0 / 2 filledPreview
pre-mortemrisklaunchfailure modes

Next in this pack

Assumption Stress-Test (Red Team)

People also copied

Assumption Stress-Test (Red Team)

When to use this prompt

Use it when

  • You need help with managers.
  • You need help with engineers.
  • You need help with operators.
  • You need help with founders.

Skip it when

  • You only need a one-line ask with no constraints, format, or context.
  • You cannot supply the fill-in details the template asks for.
  • A different category or tool-specific workflow fits the job better.

How to get a good result

Done when

The output clearly completes “Pre-Mortem Risk Audit”: it matches the requested format, uses your filled-in details, and is ready to use without another prompting round.

Common mistakes

  • Leaving plan, timeframe vague - the model then invents placeholders.
  • Asking ChatGPT, Claude, Gemini, or Perplexity for a shorter answer after a long structured prompt - that throws away the format rules.
  • Running it once without providing your constraints, stack, or examples of good/bad output.

FAQ

What do I fill in before I copy this prompt?
Replace these placeholders with your details: plan, timeframe. Required fields are marked on the page. The prompt text updates as you type.
Which AI tools is this prompt written for?
It works best with ChatGPT, Claude, Gemini, Perplexity. Copy the filled prompt and paste it into the tool you already use.
What should a good result look like?
The output clearly completes “Pre-Mortem Risk Audit”: it matches the requested format, uses your filled-in details, and is ready to use without another prompting round.
What are common mistakes with this prompt?
Leaving plan, timeframe vague - the model then invents placeholders. Asking ChatGPT, Claude, Gemini, or Perplexity for a shorter answer after a long structured prompt - that throws away the format rules. Running it once without providing your constraints, stack, or examples of good/bad output.

Best for

  • Managers
  • Engineers
  • Operators
  • Founders

More prompts like this — same topic and style.

More like this

Assumption Stress-Test (Red Team)
Devil's Advocate - Break the Idea First
5 Whys + Fishbone Hybrid
Weighted Decision Matrix