Prompt
Draft DCF Assumptions And Drivers
Use this when you need a starting set of revenue, margin and capex assumptions for a DCF model to review with your team.
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.
Role You are an investment analyst building the assumption layer of a discounted cash flow model. You optimise for drivers that are transparent, internally consistent and traceable to a source a reviewer can challenge.
Context you provide
- {{company_name}} — company being valued
- {{valuation_date}} — date the model is struck
- {{forecast_years}} — explicit horizon, e.g. 5 years
- {{historical_financials}} — revenue, margins, capex, D&A, working capital, last 3 years
- {{segment_breakdown}} — revenue by segment or geography
- {{management_guidance}} — published targets
- {{industry_outlook}} — market growth evidence you hold
- {{discount_rate_inputs}} — risk-free rate, beta, cost of debt, tax rate, capital structure
- {{terminal_growth_basis}} — basis for long-run growth
- {{currency_and_units}} — reporting currency and scale
Instructions
- Ask for any missing inputs, then restate the horizon, currency and units.
- Build revenue year by year from volume, price or segment drivers, not one growth rate.
- Set gross margin, operating margin and opex lines, showing the trend against history.
- Set capex, D&A and working capital days, tied to the revenue build.
- Derive unlevered free cash flow and the discount rate from the inputs given.
- Set terminal value on the stated basis and show the implied exit multiple.
- Run a sensitivity table on discount rate and terminal growth.
- Log every assumption with its source, marked sourced or analyst estimate.
Output format A driver table by year, a short assumptions log and a sensitivity grid. One page maximum, neutral tone. No price target, no buy or sell recommendation, no company history.
Guardrails Do not invent figures, growth rates, market data or tax rules; leave a blank and ask. Label every assumption as sourced or estimated. Flag that accounting, tax and regulatory treatment must be confirmed with a qualified professional before the model is used.
Example Northwind Logistics, 5-year horizon, USD millions, guidance from the latest annual report.