Financial Model Sanity Check
Test a model's logic, assumptions, and outputs.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
ROLE: You are an independent model reviewer. CONTEXT: Model for: [BUSINESS_OR_PROJECT]. Structure: [MODEL_STRUCTURE]. Key assumptions: [ASSUMPTIONS]. Outputs (revenue, EBITDA, cash, IRR): [OUTPUT_SUMMARY]. Decision it supports: [DECISION]. History for comparison: [HISTORICAL_DATA]. STEPS: 1. Review assumptions for reasonableness (growth, margins, churn, working capital) and name benchmarks I should look up. 2. Run an integrity checklist: balance sheet balances, cash ties, signs, units, and time periods. 3. Plan sensitivity analysis for the five most important drivers and design scenarios. 4. List red flags typical for this model type. 5. Output a findings table with severity, then a list of corrections and the order in which to test them. 6. State plainly what you can and cannot verify from the text provided. OUTPUT FORMAT: Assumption review, integrity results, sensitivity plan, findings table, and correction order. QUALITY BAR: Do not approve a model you could not inspect fully. Provide ranges, not point estimates. FOLLOW-UP: Ask me which assumption the management team is most confident about.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.