← Index13 entries · By Subject
Section VI · Subject Matter

Finance prompts

Prompts for budgets, forecasts, variance analysis, unit economics, and investor-ready financial updates.

§ Overview

Finance work lives in spreadsheets, but it ships as narrative — the variance commentary, the investor update, the board slide that explains why cash moved. The prompts here sit on both sides of that line. Some help with the analytical scaffolding: breaking down unit economics like CAC, LTV, and payback; modeling best, base, and worst cash-flow scenarios; calculating runway and the zero-cash date; stress-testing the assumptions behind a model. Others handle the writing: a plain-English expense variance narrative, a month-end close memo, a monthly investor financial update, or the financial section of a board deck.

The most important thing to understand is what AI is and isn't doing for you. These prompts produce analysis aids and drafts — they help you organize inputs, frame a variance story, and structure a forecast. They do not produce authoritative numbers. A language model can transpose a figure, misapply a formula, or 'reason' its way to a confident but wrong total. Every number that comes out has to be traced back to your actuals and recomputed in your own model before it goes near a leadership audience.

Used that way, AI is a real time-saver for the explanatory layer of the job — turning a wall of variances into a readable commentary that separates timing differences from genuine overspend, or drafting the takeaway headlines for board slides you'll back with verified data.

§ Field Notes

What makes a good finance prompt

A strong finance prompt is explicit about definitions and inputs. LTV and runway can be calculated several ways, so a good prompt states the exact formula, the period, and the assumptions, and asks the model to show its work so you can check each step. It should also distinguish between what's given (your actuals) and what's modeled (assumptions and scenarios), so the output doesn't blur fact and forecast.

The best prompts also ask for the 'so what.' A variance table is data; a prompt that asks the model to flag material movements, separate timing from structural change, and propose root causes to investigate produces something a CFO can actually use — provided you verify the underlying figures.

§ Pro Tips

Get sharper results

  • 01Provide the numbers; don't ask the model to estimate them. Paste your actuals and let AI organize, narrate, and structure — never let it guess a figure you haven't supplied.
  • 02Recompute every output. Treat AI math as a draft calculation to be checked in your spreadsheet, especially for runway, payback, and break-even where a single transposed input changes the answer.
  • 03When building scenarios, define your best/base/worst assumptions yourself and have the model carry them through period by period. The value is in consistent mechanics, not in the model inventing optimistic inputs.
  • 04For investor and board content, ask for takeaway headlines plus the supporting data points and likely follow-up questions — then pressure-test that the story matches your verified actuals before it leaves your hands.
§ FAQ

Common questions

Can I trust AI to do the math in a financial model?

Treat it as an analysis aid, not a calculator of record. It can lay out a forecast or compute a variance, but language models make arithmetic and formula errors that look authoritative. Always recompute the numbers in your own spreadsheet before relying on them.

Is it safe to paste financials into an AI tool?

Be cautious with sensitive or non-public figures, especially in consumer-grade tools where inputs may be retained or used for training. Use a tool with appropriate data controls, or anonymize and scale the numbers, before sharing anything confidential.

What's AI actually good at in finance, then?

The explanatory and structural layer: turning variances into readable commentary, drafting close memos and investor updates, and outlining board slides. It's strong at framing and narrative once you supply verified inputs, and weak at being the source of truth for the inputs themselves.

§ The Prompts · 13
№ 129finance

Build an Annual Department Operating Budget Draft

Drafts a justified, category-organized annual operating budget for a single department from prior-year actuals and planned drivers.

For
chatgpt·claude
№ 130finance

Update a 12-Month Rolling Forecast with New Actuals

Refreshes a 12-month rolling forecast using the latest closed-period actuals and updated business assumptions.

For
chatgpt·claude
№ 131finance

Explain Budget vs. Actual Variances for the Period

Computes and prioritizes material budget-versus-actual variances and proposes plausible root causes to investigate.

For
chatgpt·claude
№ 132finance

Break Down Unit Economics: CAC, LTV, and Payback

Calculates and interprets CAC, LTV, LTV:CAC, and payback period from acquisition and retention inputs.

For
chatgpt·claude
№ 133finance

Draft a Monthly Investor Financial Update

Turns monthly metrics, wins, and challenges into a candid, investor-grade financial update with a clear cash and runway section.

For
chatgpt·claude
№ 134finance

Write a Plain-English Expense Variance Narrative

Converts categorized expense variances into a readable monthly commentary that separates timing from true over- or underspend.

For
chatgpt·claude
№ 135finance

Model Best, Base, and Worst Cash-Flow Scenarios

Builds best, base, and worst cash-flow scenarios with period-by-period balances and flags when cash could turn negative.

For
chatgpt·claude
№ 136finance

Analyze Cash Runway and Model Spend-Cut Options

Calculates current runway and zero-cash date, then models how specific spend-cut options extend runway with their trade-offs.

For
chatgpt·claude
№ 137finance

Analyze Pricing Changes and Their Margin Impact

Quantifies the margin and break-even impact of a price change and stress-tests it against several volume scenarios.

For
chatgpt·claude
№ 138finance

Stress-Test the Assumptions Behind a Financial Model

Critically reviews a financial model's assumptions for aggressiveness, sensitivity, and internal consistency.

For
chatgpt·claude
№ 139finance

Design a Finance KPI Dashboard for Leadership

Specifies a grouped, audience-appropriate finance KPI dashboard with exact metric definitions and a layout plan.

For
chatgpt·claude
№ 140finance

Summarize Month-End Close Results for Leadership

Produces a skimmable month-end close memo covering results versus plan, balance-sheet moves, adjustments, and open items.

For
chatgpt·claude
№ 141finance

Draft the Financial Section of a Board Deck

Outlines the financial slides of a board deck with takeaway headlines, supporting data points, and anticipated-question talking points.

For
chatgpt·claude