Financial Model & Forecast Builder Prompt for ChatGPT & Claude

This is a free, ready-made prompt for chatgpt & claude that a 12-month forecast table with the assumptions exposed and the break-even month named. Copy it, replace the bracketed parts, and paste it into your AI — no login and no cost.

The prompt — for ChatGPT, Gemini & DeepSeek

✎ Editable — click in, customize or extend this prompt, then copy. Your edits copy with it.

The prompt — Claude version

Same prompt, structured with the XML tags Claude follows most reliably.

<role>You are a financial modeller. Build a 12-month forecast for [BUSINESS].</role>

<task>
Inputs: price and unit [PRICE AND UNIT]; starting customers [STARTING CUSTOMERS]; growth assumptions [MONTHLY GROWTH ASSUMPTIONS]; costs [COSTS].

Deliver:
1. ASSUMPTIONS TABLE - every assumption you are using, one per line, with the value - so the whole model can be challenged at a glance.
2. THE FORECAST - a markdown table, 12 rows (Month 1-12), columns: Customers | Units sold | Revenue | Costs | Monthly profit | Cumulative cash. Compute every cell; show the formula logic under the table in 3 lines.
3. BREAK-EVEN - the month cumulative cash turns positive, and the customer count it requires.
4. SENSITIVITY - recompute the final cumulative cash with growth 30% lower and with price 15% lower; give both numbers and one sentence on which assumption the business lives or dies by.

Acceptance check: the tables' arithmetic must be internally consistent - I will spot-check three cells. Round to whole dollars.
</task>

✎ Editable — click in, customize or extend this prompt, then copy. Your edits copy with it.

This prompt for your model

ChatGPT version Claude version Gemini version DeepSeek version Grok version Mistral Le Chat version Llama version Copilot version Perplexity version Qwen version Kimi version GLM version

How to use this prompt

Replace the bracketed placeholders — [BUSINESS], [PRICE AND UNIT], [STARTING CUSTOMERS], [MONTHLY GROWTH ASSUMPTIONS], [COSTS] — with your own details, then paste the whole prompt as your first message. The bracketed parts are the only editing needed; the instructions around them are what make the answer come back structured instead of vague. If the first result is close but not right, ask the AI to adjust one thing at a time rather than rewriting the prompt.

Want a different version of this prompt?

Open the prompt gateway and type your goal in one line — it builds a fresh prompt around your exact wording, formatted for whichever model you run, with your choice of tone and output format.