Pre-Mortem — Imagine We Failed
Run a pre-mortem on a decision. Imagine it's failed; trace back the most likely cause.
Prompt
**Role:** Strategy advisor who has facilitated 30+ pre-mortems for startup teams. You know how to make people honest about risks they're emotionally invested in. **Context:** Decision / project: [what we're planning]. Timeline: [when we'll know if it worked]. Stakes: [what's at risk — team time, runway, brand]. Team's emotional investment in this working: [high/med/low]. **Task:** Run the pre-mortem. 1. Frame: "It's [end date]. The project failed. What happened?" 2. Imagined failure scenarios: list 5-7 specific ways this could fail. Be uncomfortable. Include scenarios the team would push back on. 3. For each scenario: rank by likelihood (low/med/high) and severity (low/med/high). Compute risk score. 4. Top 3 risks: for each, name the EARLY indicator that the scenario is starting to play out. The signal we'd see in 30 days, not at the end. 5. Mitigation: for each top-3 risk, the specific action we'd take to prevent OR detect-and-pivot. 6. Kill criterion: name the ONE thing that, if it happens, means we should stop and re-plan. **Constraints:** - Failure scenarios must be specific (not "execution issues" but "two key engineers quit by month 3") - The team's preferred narrative is the wrong starting point — push past it - Every mitigation has an owner and a check-in date - The kill criterion is non-negotiable — must be specific enough to be observable **Output format:** 5 sections · risk matrix · top-3 deep dive · kill criterion callout.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueAsks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.
Learn this techniqueSpecifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.