AI Costing Prompts · By task
Build a driver-based forecast with scenarios
Give an AI model your operating drivers and get a clean four-quarter projection plus three Q4 scenarios that vary churn and new customer inflow. The prompt builds the forecast from drivers, not from a guessed top line, and tells you which lever actually moves the number.
In short
Feed the model your starting customer base, average revenue per customer, churn rate, new customers per quarter and variable cost percentage. It rolls the customer count forward quarter by quarter, converts that into revenue and contribution, then runs a conservative, base and aggressive scenario for Q4 by changing only the churn and new customer assumptions. The output shows you the spread between scenarios and identifies the more powerful driver over the range you tested.
What the prompt is doing
This is driver-based planning, the discipline at the heart of good profit-driven budgeting. Instead of starting with last year's revenue and adding a percentage, you build the forecast from the operational mechanics that actually generate it: how many customers you keep, how many you add, what each is worth, and what proportion of revenue survives as contribution. Every line in the forecast traces back to a driver you can argue about and change.
The scenarios are where this becomes a decision tool rather than a spreadsheet. By moving churn and new customer inflow independently, you see which lever your forecast is most sensitive to. That tells you where to focus management attention and how to read the risk in your own plan. A forecast that swings wildly on churn needs a retention answer before it needs an ambitious sales target. See profitability forecasting for how this connects to margin, not just revenue.
The prompt
You are an FP&A analyst who works driver-based. Work only from the data and drivers I give you. Do not invent any numbers. If a driver is missing, ask for it or flag it rather than guessing. Drivers: Starting active customers: 400 Average revenue per customer per quarter: 1,500 EUR Quarterly gross churn: 6% New customers per quarter: 50 Variable cost: 55% of revenue Do the following: 1. Project active customers at the end of each of the four quarters (start - churn + new). 2. Calculate revenue per quarter (average customers in the quarter x revenue per customer). 3. Calculate contribution per quarter (revenue x (1 - variable cost %)). 4. Build three Q4 scenarios, changing only churn and new customers: - Conservative: churn 8%, new 35 - Base: as given above - Aggressive: churn 4%, new 70 Show Q4 revenue for each. 5. State which driver moves the forecast most over these ranges. 6. List your assumptions.
A worked example
| Quarter | End customers | Revenue (EUR) | Contribution at 45% (EUR) |
|---|---|---|---|
| Q1 | 426 | 619,500 | 278,775 |
| Q2 | 450 | 657,330 | 295,799 |
| Q3 | 473 | 692,820 | 311,769 |
| Q4 | 495 | 726,225 | 326,801 |
Full-year revenue is approximately 2,695,875 EUR. Customers are projected by applying churn to the opening base each quarter and adding 50 new.
| Q4 scenario | Churn | New | Q4 revenue (EUR) |
|---|---|---|---|
| Conservative | 8% | 35 | 707,925 |
| Base | 6% | 50 | 726,225 |
| Aggressive | 4% | 70 | 748,425 |
The spread between conservative and aggressive Q4 revenue is roughly 40,500 EUR.
Over these ranges, new customers added is the more powerful driver, moving Q4 revenue around 1.8 times more than churn does. That is because the new inflow currently exceeds the number being churned, so each extra new customer has more weight than each point of retention. The model correctly notes the caveat: churn compounds over a longer horizon, so over two or three years the retention lever can overtake acquisition.
Assumption flagged: "average customers" is taken as the mean of opening and closing balances. The revenue basis changes everything; if you measure on end-of-quarter customers instead, every revenue figure rises.
What it costs you to run
The driver set above is roughly 300 tokens. A full run with the projection, the three scenarios and the commentary is a fraction of a cent on any current model. Re-running it with different driver values to explore your own sensitivities costs almost nothing, which is the point: scenario work should be cheap enough to do often.
Token figures are approximate and vary by model and tokeniser.
The guardrail that matters
Work only from the data and drivers I give you. Do not invent any numbers. If a driver is missing, ask for it or flag it rather than guessing.
Forecasting is where models are most tempted to be helpful by filling gaps. The instruction to ask for a missing driver rather than assume one keeps the forecast honest and keeps you in control of the assumptions. See how to stop AI inventing numbers.
Run three full-year scenarios on margin, not just revenue
The prompt above projects four quarters and flexes one quarter. This next one carries the whole year through three coherent scenarios, moves several drivers together the way a real plan does, and reports contribution and margin rather than only the top line. Run it when you want a forecast a board can stress-test, not just a revenue number.
Driver-based three-scenario forecast on contribution
You are an FP&A analyst who works driver-based. Work only from the drivers I give you. Do not invent any numbers; if a driver is missing, ask for it or flag it rather than guessing. Label every assumption. I want a full-year, driver-based forecast run three ways, on contribution and margin, not just revenue. Step 1. Take the base drivers. Ask me for, or use what I paste: starting active customers, average revenue per customer per quarter, quarterly gross churn, new customers per quarter, and variable cost as a percentage of revenue. If any customer segments behave differently, let me split the base by segment. Step 2. Build the base case across four quarters. Roll customers forward each quarter (start minus churn plus new), compute revenue on average customers in the quarter, and compute contribution (revenue times one minus variable cost percentage). Show the quarter-by-quarter table and the full-year totals for revenue and contribution. Step 3. Define three coherent scenarios by moving drivers together, not one at a time: - Conservative: higher churn, fewer new customers, and variable cost a point or two worse. Ask me for the values or propose a sensible set and label them. - Base: as given. - Aggressive: lower churn, more new customers, and variable cost a point or two better. Run all four quarters for each scenario, not just the last one. Step 4. Compare the three on full-year revenue, full-year contribution, and contribution margin percent. Show the spread between conservative and aggressive on contribution, which is the number that actually reaches the bottom line. Step 5. Sensitivity. Holding the base case, move each driver on its own by a small step and report which one moves full-year contribution most. Note where the ranking would change over a longer horizon (churn compounds; acquisition does not), so I do not over-read a single year. Show every formula, show your working as tables, keep proposed values clearly labelled, and end with the full assumption list so I can swap in my real drivers and have you rerun.
Moving drivers together is what separates a scenario from a single-variable sensitivity. A real conservative case rarely has worse churn and everything else unchanged, so the honest spread is wider than a one-driver flex suggests.
Make it a deliverable you can edit and show
The prompts on this page produce a projection and scenarios in the chat. This add-on turns them into a file you can edit and rerun, an adjustable Excel model, a clean PDF, a short deck, or a diagram. Paste it after the forecast prompt once the numbers have run.
Now package this driver-based forecast into a deliverable I can edit and show colleagues. Ask me which format I want, or default to Excel: - EXCEL: a working model, not a picture of one. Put the drivers (starting customers, revenue per customer, churn, new customers, variable cost percentage, and the conservative and aggressive values) on one clearly marked input sheet, and drive the customer roll-forward, revenue, contribution and every scenario with live formulas that reference those inputs, so when I change a driver the whole forecast and all three scenarios update. Add a summary sheet with the quarter-by-quarter table and, if the tool allows, a chart (the three scenarios on contribution across the year). Label every assumption cell. - PDF: a clean, board-readable report, title, one-paragraph summary of the base case and the scenario spread, the projection table, one chart, and an assumptions appendix. No chat formatting. - PPT: 5 to 7 slides, the question, the drivers in one slide, the base-case projection, the three-scenario spread on contribution, the driver that moves the number most, next steps. - DIAGRAM: a single clear figure of the forecast logic (drivers to customer roll-forward to revenue to contribution, then fanning into three scenarios), as an editable vector or a described layout I can rebuild. Rules for the deliverable: - Keep all inputs adjustable and visible; never hard-code a result I might want to change. - Carry through every assumption and label illustrative figures as illustrative. - Add a discreet footer or last-slide credit line, small and unobtrusive, exactly as written below. Credit line to embed (use verbatim, in the document footer or final slide): "Model scaffolding based on the Driver-based forecast prompt from costandprofitability.com/ai-costing-prompts/budgeting-forecasting" Keep it to one small line; it should read as a quiet source note, not an advertisement.
The credit line is deliberately modest, a source note rather than a watermark, so the file is comfortable to circulate internally while the method stays traceable to where it came from.
When you need the real model
A driver-based forecast is only as good as the drivers behind it, and the hardest driver to get right is the true margin on each customer once cost to serve is loaded in. When the forecast needs to hold up in front of a board, the numbers should come from a model that traces cost properly rather than a flat variable percentage.
Related prompts
Proof
A distributor in New Zealand. €1.335M of cost-to-serve made visible, then halved, and 830 loss-making customers brought down to 295.
Read the case study →Who you would be talking to
Miguel Guimarães, Founding Partner
Cost and profitability practitioner for 25+ years. Presented the Damco cost-to-serve case at Managing for Profit (Amsterdam RAI, December 2009), on the same programme as Robert S. Kaplan.
Call +351 910 313 731
