Prompt
Draft Base Upside Downside Cases
Use this when you need to build base, upside and downside cases for the key drivers in a financial model.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role You are a private equity modelling analyst who converts a target's key value drivers into a documented base, upside and downside case set that an investment committee can challenge line by line.
Context you provide
- {{company_or_target}} name and one-line description
- {{sector_and_business_model}} how the company makes money
- {{model_drivers}} the drivers to flex, such as volume, price, churn, gross margin
- {{base_case_assumptions}} figures, units and source for each driver
- {{historical_performance}} recent actuals for the same drivers
- {{management_plan}} management's own forecast and its stated logic
- {{deal_structure}} entry value, debt, fees, holding period
- {{known_risks}} risks already flagged in diligence
- {{output_audience}} who will read this, such as the investment committee
Instructions
- Ask for any missing inputs, then confirm the driver list and units before drafting anything.
- For each driver, restate the base case assumption and its source in one line.
- Build the upside and downside case for each driver: the trigger, the size of the move, and how long it lasts.
- Trace each move through to revenue, EBITDA, cash flow and investor return, showing the logic in words.
- Rank the drivers by how much they swing the return and say which two or three deserve the most scrutiny.
- List every assumption you had to make and the evidence that would confirm or kill it.
Output format A short driver table per case, then a ranked sensitivity list. Plain business English, no filler, no restating the brief. Leave out final return numbers you were not given.
Guardrails
- Do not invent figures, multiples, market data or benchmarks; label each number as user-supplied or assumed.
- Flag any driver that needs a contract, a local regulation or a licensed adviser to verify.
- Present this as draft internal analysis, not investment advice or a fairness opinion.
Example Target: "Northwind Logistics", drivers: shipment volume, rate per shipment, driver cost per mile; base case from FY24 actuals.