This copy-ready data analysis prompt helps you build a forecasting sanity check with fewer blank-page decisions. Paste it into Claude and ChatGPT, 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.
4.9(16 ratings)380 copies
Updated By Site Admin
45 words · v1.2
Fill in the blanks · 3 variables
Claude promptReplace every highlighted token before sending
<task>
We forecast {metric} using {method}. List the assumptions that must hold, the data quality requirements, and five sanity checks before trusting the forecast. Explain how to backtest it and what a reasonable error range looks like. Do not present the forecast as certainty.
Context:
{context}
</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 ({metric}, {method}, {context}) 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. Reconcile totals to a trusted source, verify the query and review the statistical claim with an analyst.
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
Metric: weekly active teams
Method: your method
Context: Add the relevant business or project context.
Example output
**Finding:** activation within 7 days predicts 90-day retention, but the effect is concentrated in self-serve signups.
**Method:** cohort by signup month, activation defined as completing two core actions within 7 days, retention measured on day 90. Excludes internal accounts and trials.
**Caveat:** sales-assisted accounts are small and may be underpowered. This is correlational, not causal. **Sanity check:** total users reconcile to the billing table within 0.4%.
Tips for a better result
Give the schema and the metric definition before asking for an interpretation.
Ask for the query or code so you can rerun it and check a known total.
Require a 'what this cannot tell us' section to surface confounders.
Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.
Common mistakes
Trusting a percentage without checking the denominator or sample size.
Treating correlation as causation in a retention or revenue analysis.
Letting the model invent a result for data it was not given.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the build a forecasting sanity check prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
Design a cohort retention analysis 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.
A data analysis prompt for analyse a survey without overclaiming. It gives ChatGPT and Claude 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.
Explain statistical power simply with a prompt built for ChatGPT and Claude. 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.
ChatGPTClaude
4.8(33)483 copies
SA
Written and reviewed by Site Admin
Author & Platform Administrator
Administrator and lead editor at AIPrompt123, curating high-performance AI prompts, SEO/AEO/GEO strategies, and developer repositories.
Last reviewed 16 April 2026 · version 1.2 · tested on Claude, ChatGPT
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.