Find out where your plan will fail before it does
Claude can look 6 months into your future and show you exactly where your plan could fail. It’s called a pre-mortem. Here are 5 prompts to make better decisions.
Why you need this
Ask Claude “Is this a good plan?” and it hunts for reasons to say yes. So you execute on something broken and find out weeks later.
A premortem flips it: You tell Claude the plan already failed and make it explain why.
Google, Goldman Sachs, and Procter & Gamble run it before every major launch.
How to use these prompts
- Tap Copy on prompt 1 and paste it into Claude. Replace [Describe it in full, with timeline, budget, and what success looks like] with your own plan.
- Then paste prompts 2 to 5 one after another, in the same chat, so Claude can build on its own answers.
Tip. The more detail you give in prompt 1, the sharper the failures will be. Include your real timeline, budget and what success looks like.
1.The Premortem Prompt
You're a forensic failure analyst. My plan: [Describe it in full, with timeline, budget, and what success looks like]. It's 6 months from today and this plan failed completely. Write the autopsy.
Give me the 7 most likely causes of death, ranked, and for each: what killed it, how it unfolded month by month, the assumption I held that allowed it, and the first warning sign I'd have seen. Every failure traces back to a detail I gave you or you cut it. No generic advice. Never reassure me.
2.The Verdict
Now make it commit instead of handing you a list.
From those 7 failures, tell me which is most likely and which is most dangerous, and explain why they're different. Then name the single biggest hidden assumption I'm making that I don't realise is an assumption. Be blunt. If my plan has a fatal flaw, say the words.
3.The Rebuild
Turn the autopsy into a plan that survives it.
Rewrite my plan with every one of those failure modes closed off. Show me what changed and why. Then give me a pre-launch checklist of 3 to 5 things I must verify before I execute anything, and tell me what result on each would mean I should walk away entirely.
4.The Adversary
The upgrade almost nobody runs. Point it at the person who wins if you lose.
Now play the person who benefits most from my plan failing. A competitor, a rival, someone who wants my spot. You've seen my plan. Tell me exactly where you'd attack it, what you'd do the week I launch, and the move I'd never see coming.
5.The Tripwire
So you catch it while there is still time to change course.
For each failure mode, give me one measurable signal that would tell me it's starting to happen, and the exact week I should check for it. I want tripwires, not vibes.
Save this page for your next plan
Bookmark it and come back before your next big decision or launch. Want more guides like this?
Questions? Write to dmg@dynamicmindsgroup.com. Claude is a trademark of Anthropic. Dynamic Minds Group is not affiliated with or endorsed by Anthropic.