Financial Model Assumptions Prompt Template
Write the narrative behind a financial model with key assumptions, sensitivity analysis, and scenario planning.
The Prompt
Make it specific to you
PromptITIN asks a few questions and builds a version tailored to your use case.
How to use this template
Copy the template
Click the copy button to grab the full prompt text.
Fill in the placeholders
Replace anything in [BRACKETS] with your specific details.
Paste into any AI tool
Works with ChatGPT, Claude, Gemini, Cursor, and more.
Or enhance with AI
Sign in to PromptITIN and let AI tailor the prompt to your exact situation in seconds.
Why this prompt works
Labelling each assumption as Data/Benchmark/Estimate/Hypothesis is the transparency tool that transforms assumptions documents from narratives into testable frameworks — it immediately signals to any reader which parts of the model are grounded and which are speculative. The single-lever scenario design ensures scenarios remain analytically useful rather than becoming arbitrary best/worst case fantasies.
Tips for best results
- Build your assumptions document in the spreadsheet alongside the model, not in a separate Word document — when assumptions are linked directly to model inputs, updating them automatically updates the forecast
- The most common fundraising mistake is presenting only the base case — presenting all three scenarios with clear drivers signals financial sophistication and builds investor confidence that you understand your own business
- Run a 'garbage in, garbage out' test: give your model to someone who doesn't know the business and ask them to find the assumption that makes the model most fragile. They'll find something you've normalised
- Update the assumptions document monthly and track how actual performance compares to assumptions — this builds a learning record that improves future models dramatically
- The 'riskiest assumption' flag is your most important management tool: if it's CAC trajectory and CAC starts rising in month 2, you have an early warning system built into your model