Claude defaults to yes. The premortem fixes that..
Claude is agreeable by design. One framing shift changes how it reasons about your decisions.
Claude defaults to yes.
Ask it “is this a good plan?” and it will find reasons to say yes. It’s not broken — it’s trained to be helpful, and “helpful” usually means agreeable. But when you’re stress-testing a decision, agreeable is the last thing you want.
The fix is a premortem.
A premortem is the opposite of a postmortem. Instead of figuring out what went wrong after something fails, you assume it already failed and work backward to find why — before you start.
The method comes from psychologist Gary Klein, published in Harvard Business Review. Daniel Kahneman called it his single most valuable decision-making technique. Research from Wharton and Cornell calls this “prospective hindsight” — and found it significantly increases your ability to identify causes of future failures.
The mechanism matters: when you ask “what could go wrong?” people give cautious, hedged answers. When you say “this already failed, tell me why,” the brain switches into narrative mode and generates more specific, honest, creative reasons. The frame changes what the mind produces.
With Claude, this becomes something you can run in 5 minutes on any decision.
Instead of “is this a good plan?” say: “This plan failed 6 months from now. Walk me through exactly how that happened.” Claude stops looking for reasons your plan will work. It explains how it fell apart.
I over-rely on this. Every time I run a premortem — on a hire, a launch, a technical decision — I find at least one blind spot I would have missed. Not because Claude is smarter. Because the frame forces a different kind of thinking.
The plan doesn’t change much. But the decision behind it does.
What’s one decision you’re holding right now where you’d rather find the flaw yourself than discover it later?