Financial model sanity check: AI prompt for finance
A ready-to-run prompt for data analysis work in corporate finance. It assigns the AI a specific senior role, takes your details as variables, and defines the output format — so the first result is usable, not a warm-up.
What this prompt does
Act as a VP of FP&A. It structures the request the way experienced practitioners brief a colleague: context first, then explicit deliverables, then quality constraints.
Best for
Finance professionals — and anyone doing this work — who need data analysis handled to a professional standard for leadership and investors. Typical moments: budget cycles, board reporting and investment decisions.
Before you use it
Have these details ready to replace the highlighted variables:
[business type][paste assumptions]
The prompt
Act as a VP of FP&A. Review these model assumptions for a [business type]: [paste assumptions]. Benchmark each against typical ranges for the industry, flag anything aggressive or internally inconsistent (e.g., headcount vs revenue growth), and list the 5 assumptions the valuation is most sensitive to, with a suggested low/base/high range for each.
Quality checklist before you run it
- Paste real data or a representative sample, not a description of it
- Sanity-check every calculated number independently
- Ask the model to state its assumptions before trusting conclusions
Common mistakes
- Trusting output numbers without independent spot-checks
- Describing your data instead of pasting a real sample
- Acting on findings whose assumptions you never read
When to use it — and when not to rely on it
Use it whenever data analysis would otherwise start from a blank page. Don't rely on it as a finished product: outputs need your judgment, your facts, and — in regulated work — professional review.
Related prompts
- KPI tree builder — Consulting
- Pipeline review analysis — Sales
- Comparative market analysis — Real Estate
- Investor update one-pager — Finance
- Salary negotiation script — Finance
- Conversion funnel diagnosis — E-commerce
Logical next step
After this, most finance teams move on to Investor update one-pager.
All Finance prompts · All Data Analysis prompts · Search the full library