Best PromptsProject Premortem
Run Gary Klein's premortem on any plan: assume total failure, write the postmortem in advance, and surface the risks meetings suppress.
Run a premortem on my plan.
The plan:
"""
[PASTE THE PLAN: a paragraph, a doc, or bullet points]
"""
Context: [TEAM SIZE, DEADLINE, BUDGET, and WHAT SUCCESS LOOKS LIKE in one measurable sentence]
The frame: it is [12 months] from now and this project has failed, not underperformed, failed. The premise is fixed; your job is the explanation. (This is Gary Klein's premortem: assuming the failure already happened bypasses the optimism that filters risk out of normal planning discussions.)
1. FAILURE STORIES: 5 to 7 distinct ways it died. For each:
- A one-line headline, written like the first line of a real postmortem.
- The chain of events, specific to MY plan: name the actual dependency, person-shaped gap, assumption, or number that gave way. Generic entries ("scope creep", "poor communication") don't count unless you show the specific form they take here.
- The earliest visible warning sign, stated as something observable ("the pilot customer stops answering emails"), not a feeling.
2. SORT THEM: preventable now / detectable early if we watch for it / pure bets we're consciously taking. The third category matters: knowing which risks we're accepting is different from not seeing them.
3. THE BIG THREE: rank by likelihood × damage. For each of the top three:
- The one change to the plan worth making this week.
- The tripwire: the metric and threshold that says it's happening ("if activation is under 20% by week 6").
- The response when the tripwire fires: adjust, pause, or kill; decided now, while nobody's sunk-cost-attached.
4. THE UNCOMFORTABLE ONE: the failure mode I'm least likely to want to hear, usually about the people, the premise, or me. Deliver it straight; softening it defeats the exercise.
Rules: use my actual numbers and names throughout. Where the plan doesn't contain enough to judge a risk, say what's missing instead of inventing specifics. Don't pad the list to hit a count: five sharp stories beat seven vague ones.How to use
Klein's research found prospective hindsight ('it already failed, explain why') surfaces materially more risks than 'what could go wrong?', because it makes pessimism the assignment instead of disloyalty. Run this after the plan is drafted but before it's committed, and bring the Big Three tripwires into the actual project doc. Rerun at each major milestone; the failure stories change as the project does.
More business prompts
Build me a monthly budget and a debt payoff plan from these numbers. Take-home income per month: [AMOUNT, and note if it varies] Fixed costs: [RENT/MORTGAGE, UTILITIES, INSURANCE, SUBSCRIPTIONS, TRANSPORT, CHILDCARE, with amounts] Variable spending, last 3 months if known: [GROCERIES, DINING, SHOPPING, ETC.] Debts: [FOR EACH: name, balan
Budget and Debt Payoff Plan
Turn your real income, bills, and debts into a monthly budget and a payoff schedule with the math shown and the tradeoffs named.
Build a 13-week cash flow forecast. Cash on hand today: [AMOUNT, and which accounts] Any restricted or committed cash: [AMOUNT AND WHAT IT IS FOR] Expected inflows: - Receivables outstanding: [CUSTOMER, AMOUNT, INVOICE DATE, TERMS, and how reliably each pays] - Recurring revenue: [AMOUNT, BILLING DATE, CHURN ASSUMPTION] - New sales expe
13-Week Cash Flow Forecast
Build the rolling weekly cash forecast operators actually run on: opening balance, timed inflows and outflows, and the week you run short.
Help me set pricing for [PRODUCT/SERVICE]. What it does and who buys it: [PRODUCT + BUYER] The alternative if they do not buy: [COMPETITOR, IN-HOUSE, SPREADSHEET, DOING NOTHING] What that alternative costs them: [MONEY, TIME, RISK. Estimate if needed and say so.] Value we create, quantified if possible: [TIME SAVED, REVENUE GAINED, COST
Pricing Strategy
Work out what to charge and how to package it: value basis, tier structure, the metric you meter on, and how to test before committing.