Build a 12-month cash-flow forecast with a prompt built for Claude and ChatGPT. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
4.7(35 ratings)513 copies
Updated By Author
51 words · v1.0
Fill in the blanks · 2 variables
Claude promptReplace every highlighted token before sending
<task>
Build a 12-month cash-flow forecast for {business}. Use the assumptions below. Show opening cash, inflows, outflows, net cash and closing cash by month. Add a downside scenario with 20 percent lower revenue and 30-day slower collections. Highlight the month with the lowest cash and what to do about it.
Assumptions:
{assumptions}
</task>
Think carefully before answering. Keep any reasoning separate and put the final deliverable inside <answer> tags.
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.
How to use this prompt
1
Open Claude and start a new chat. Paste the prompt exactly as written.
2
Replace each placeholder ({business}, {assumptions}) with your own details. Leave the instructions and the output format untouched.
3
Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.
4
Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.
5
Review the result. Every formula, input and tax assumption with an accountant or qualified analyst. This is not financial advice.
Worked example
This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.
Example input
Business: your business
Assumptions: Paste the revenue, cost and timing assumptions here.
Example output
**Base case:** revenue grows 18%, gross margin stays at 71%, CAC payback improves from 11 to 9 months.
**Downside:** growth of 6%, churn +1.2 pts, 30-day slower collections. Closing cash falls below the three-month buffer in September.
**Key sensitivity:** a 10% change in churn moves annual revenue by roughly 14%, more than any pricing change modelled.
**Assumptions:** no new hires beyond plan, no FX movement, no debt drawdown. This is financial modelling, not investment advice. Verify tax treatment with an accountant.
Tips for a better result
State the currency, period, tax jurisdiction and decision being made up front.
Ask for formulas and a sensitivity table, not a paragraph of reassurance.
Treat every output as a model to check, not a forecast to trust.
Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.
Common mistakes
Treating a plausible model as a prediction.
Letting the model assume a growth rate without showing the basis.
Acting on AI-generated tax or investment guidance without a licensed professional.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the build a 12-month cash-flow forecast prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
A finance prompt for stress-test a business plan. It gives Claude and ChatGPT a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
This copy-ready finance prompt helps you explain compound interest with a table with fewer blank-page decisions. Paste it into ChatGPT and Claude, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
Analyse customer lifetime value by segment with a prompt built for Claude and ChatGPT. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
ClaudeChatGPTDeepSeek
4.8(30)556 copies
A
Written and reviewed by Author
AIPrompt123 Contributor
Contributing author and prompt engineer at AIPrompt123.
Last reviewed 6 June 2026 · version 1.0 · tested on Claude, ChatGPT
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.