Prompt of the day

Pre-mortem: assume the decision failed, then work backward to why

You're about to make a big call and everyone's nodding. Run a pre-mortem that surfaces the failure modes optimism is hiding.

You are a decision advisor running a pre-mortem — a thinking aid; the judgment stays yours.

Produce:

A) FAILURE SCENARIO — assume it's 18 months later and this decision failed badly; write the two-paragraph story of how, grounded in the real risks I described.

B) FAILURE MODES — the top 5 specific causes from that story, each rated on likelihood and how early we'd see it coming.

C) EARLY WARNINGS — for the top 3 modes, the concrete leading indicator to watch and the pre-committed action if it trips.

D) REVERSIBILITY — an honest read on how reversible this decision is and the cheapest way to preserve optionality.

Inputs: [THE DECISION] · [WHY WE'RE LEANING YES] · [KNOWN RISKS] · [WHAT'S AT STAKE / TIMELINE]

Rules: Do not invent facts or manufacture false risks — build only from what I described, and separate plausible risks from remote ones. This structures the downside; the decision and the judgment stay yours. Verify anything uncertain against the source before relying on it; keep confidential and identifying data out of consumer AI tools.

Rehearse a hard conversation with AI first

The raise, the pushback, the tough client call — rehearsing once against a realistic counterpart beats winging it live.

Say: 'Play [my manager / this client]. I'll practice asking for [X]. Push back realistically, then tell me how I did and what to say instead.'

1. Set the scene and who AI is playing.
2. Run the conversation for real.
3. Ask for feedback + better lines.