Risk Assessment
Devil's Advocate - Break the Idea First
AI Tool:
GrokWorks with Grok
Category: Problem Solving
Search for real precedent, then argue the most likely failure. Stay adversarial until the verdict. DeeperSearch if you have it.
Prompt Quality - 95/100 · Strong
The Prompt
grok-devils-advocate-idea.md
Before I commit to this, I want you actively trying to find reasons it fails - not brainstorming ways to make it work, the opposite. Search for real precedent on X and the web. Use DeeperSearch if it is available. THE IDEA: {{idea}} WHY I THINK IT'LL WORK: {{why}} INSTRUCTIONS: 1. Search for whether anyone has tried something similar - recently, publicly, on X or elsewhere - and what happened to it. Real precedent beats hypothetical objections. 2. List every way this could fail, ranked from most to least likely, based on what you found plus your own reasoning. Be specific - "market risk" isn't an answer. "The specific thing you're assuming your users want is the exact thing three similar products got wrong last year" is. 3. Pick the single failure mode you think is most likely to actually happen, and argue for it as if you're trying to talk me out of doing this entirely. 4. Then, honestly, tell me if you still think it's worth doing despite that - and what would need to be true for the biggest risk to not matter. 5. Give me one gut-check question I should be able to answer confidently right now, and if I can't, that's a sign I'm not ready. OUTPUT FORMAT: - Precedent found (what's been tried, what happened) - Ranked failure modes (specific, not generic) - Full argument for the single most likely failure - Honest verdict: still worth it or not, and the condition that would need to hold - The gut-check question CONSTRAINTS: - Do not soften into "but it could also work great" until the honest verdict step - stay fully in the adversarial role until then. - Precedent from search beats hypothetical reasoning - if you find a real example, lead with that over a guessed failure mode.
Negative prompt
Included when you copy the prompt
Do not brainstorm ways it succeeds until the verdict step. Do not use generic risks like "market risk" or "execution." Do not invent precedent - if you found none, say so. Do not skip the gut-check question.
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).
grok-devils-advocate-idea.md
Prompt preview
Before I commit to this, I want you actively trying to find reasons it fails - not brainstorming ways to make it work, the opposite. Search for real precedent on X and the web. Use DeeperSearch if it is available. THE IDEA: {{idea}} WHY I THINK IT'LL WORK: {{why}} INSTRUCTIONS: 1. Search for whether anyone has tried something similar - recently, publicly, on X or elsewhere - and what happened to it. Real precedent beats hypothetical objections. 2. List every way this could fail, ranked from most to least likely, based on what you found plus your own reasoning. Be specific - "market risk" isn't an answer. "The specific thing you're assuming your users want is the exact thing three similar products got wrong last year" is. 3. Pick the single failure mode you think is most likely to actually happen, and argue for it as if you're trying to talk me out of doing this entirely. 4. Then, honestly, tell me if you still think it's worth doing despite that - and what would need to be true for the biggest risk to not matter. 5. Give me one gut-check question I should be able to answer confidently right now, and if I can't, that's a sign I'm not ready. OUTPUT FORMAT: - Precedent found (what's been tried, what happened) - Ranked failure modes (specific, not generic) - Full argument for the single most likely failure - Honest verdict: still worth it or not, and the condition that would need to hold - The gut-check question CONSTRAINTS: - Do not soften into "but it could also work great" until the honest verdict step - stay fully in the adversarial role until then. - Precedent from search beats hypothetical reasoning - if you find a real example, lead with that over a guessed failure mode.
0 / 2 filledPreview
When to use this prompt
Use it when
- You need help with researchers.
- You need help with founders.
- You need help with operators.
- You need help with writers.
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 “Devil's Advocate - Break the Idea First”: it matches the requested format, uses your filled-in details, and is ready to use without another prompting round.
Common mistakes
- Leaving idea, why vague - the model then invents placeholders.
- Asking Grok 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: idea, why. 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 Grok. Copy the filled prompt and paste it into the tool you already use.
- What should a good result look like?
- The output clearly completes “Devil's Advocate - Break the Idea First”: 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 idea, why vague - the model then invents placeholders. Asking Grok 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
- Researchers
- Founders
- Operators
- Writers
Related Prompts
More prompts like this — same topic and style.