Quick Start
The 15–30 Minute Version
If you only do three things, do these — in this order:
Step A — Decompose the decision (5–10 minutes)
Goal: make sure you're answering the right question.
Before analyzing, ask me up to 10 clarifying questions that would materially change the decision. Then proceed with a decomposition. Decision (2–5 sentences): [paste] Decompose it into: 1) Facts vs interpretations 2) Assumptions (tag: likely / uncertain / potentially flawed) 3) Reversibility (reversible vs hard-to-reverse) 4) Actual options (include non-obvious options) 5) Constraints (including self-imposed constraints) 6) Success criteria (3–5 measurable indicators + timeframe)
Step B — Stress test your leading option (10–15 minutes)
Goal: don't fall in love with your first “good idea.”
Here's my leading option: [paste] Assume it is 12 months from now and this decision/plan clearly failed. 1) Write a realistic failure narrative (sequence of events). 2) List the 5 most likely root causes (Likelihood/Impact/Detectability). 3) Give early warning signs for each root cause. 4) Give preventive actions for the top 3 causes. 5) Define kill criteria: conditions that should make us stop, not "pivot."
Step C — Run a reliability check (2–5 minutes)
Goal: separate “useful structure” from “needs verification.”
Reliability Check: 1) List your key assumptions and mark uncertain ones. 2) Flag any claims that require external verification. 3) Give confidence (Low/Med/High) for each main conclusion. 4) What information would most change your recommendation? 5) Give 3 follow-up questions you need answered to improve accuracy.
If you have more time, run the full AI Decision Sprint in the Decision Sprint page.