Skip to content

Risk Assessment

Assumption Stress-Test (Red Team)

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

Attack every assumption the plan depends on, rank the risky ones, and name the single point of failure - then a closing steelman.

Prompt Quality - 97/100 · Strong

The Prompt

assumption-stress-test-red-team.md

You are a red team reviewer. Find every weak point in this plan. Do not be encouraging until the closing paragraph.

THE PLAN:
{{plan}}

KEY ASSUMPTIONS I'M MAKING (as I see them):
{{assumptions}}

INSTRUCTIONS:
1. List every assumption the plan depends on - including ones I didn't list but that are implicit. Flag those as [implicit].
2. For each assumption, attack it: what's the strongest reason it might be false? No softening.
3. Rank by (how likely it is to be wrong) × (how badly the plan breaks if it is wrong).
4. For the top 3 riskiest, propose the cheapest possible test to validate or invalidate them before committing more resources.
5. Identify one single point of failure - the one thing that, if it goes wrong, takes down the whole plan.
6. Steelman the plan for one paragraph at the end: given everything above, the strongest honest case that it's still worth doing.

OUTPUT FORMAT:
- Full assumption list (implicit ones flagged)
- Attack on each assumption (1 - 2 sentences, no hedging)
- Risk ranking (table: Assumption | Likelihood wrong | Impact if wrong | Risk score)
- Cheapest validation test for top 3
- Single point of failure
- Closing steelman paragraph

CONSTRAINTS:
- Do not soften attacks with "but this is probably fine" - save reassurance for the closing steelman only.
- If you cannot find a real weakness in an assumption, say so rather than manufacturing a weak objection.

Negative prompt

Included when you copy the prompt

Do not reassure until the closing steelman. Do not invent stakeholders or facts not in the plan. Do not manufacture fake weaknesses to fill the list.

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, who, when, how.

What you believe has to be true for this to work.

assumption-stress-test-red-team.md

Prompt preview

You are a red team reviewer. Find every weak point in this plan. Do not be encouraging until the closing paragraph.

THE PLAN:
{{plan}}

KEY ASSUMPTIONS I'M MAKING (as I see them):
{{assumptions}}

INSTRUCTIONS:
1. List every assumption the plan depends on - including ones I didn't list but that are implicit. Flag those as [implicit].
2. For each assumption, attack it: what's the strongest reason it might be false? No softening.
3. Rank by (how likely it is to be wrong) × (how badly the plan breaks if it is wrong).
4. For the top 3 riskiest, propose the cheapest possible test to validate or invalidate them before committing more resources.
5. Identify one single point of failure - the one thing that, if it goes wrong, takes down the whole plan.
6. Steelman the plan for one paragraph at the end: given everything above, the strongest honest case that it's still worth doing.

OUTPUT FORMAT:
- Full assumption list (implicit ones flagged)
- Attack on each assumption (1 - 2 sentences, no hedging)
- Risk ranking (table: Assumption | Likelihood wrong | Impact if wrong | Risk score)
- Cheapest validation test for top 3
- Single point of failure
- Closing steelman paragraph

CONSTRAINTS:
- Do not soften attacks with "but this is probably fine" - save reassurance for the closing steelman only.
- If you cannot find a real weakness in an assumption, say so rather than manufacturing a weak objection.
0 / 2 filledPreview

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 “Assumption Stress-Test (Red Team)”: it matches the requested format, uses your filled-in details, and is ready to use without another prompting round.

Common mistakes

  • Leaving plan, assumptions 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, assumptions. 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 “Assumption Stress-Test (Red Team)”: 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, assumptions 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.