Turn a vague data request into a clear analysis plan
Converts a fuzzy stakeholder ask into a scoped plan with the real question, data needed, deliverable, and clarifying questions.
The prompt
Help me turn a vague data request into a clear, scoped analysis plan before I start pulling data.
The request as I received it: [PASTE the message, ticket, or what was said]
Who asked and their role: [e.g. "VP of Sales", "product manager for onboarding"]
Decision they are likely trying to make: [YOUR GUESS, or "unknown"]
Data I think is available: [tables, tools, dashboards, known gaps]
Deadline and effort I can give it: [e.g. "by Friday, about 1 day"]
Steps:
1. Restate the request as the underlying business question and the decision it supports. If there are several plausible interpretations, list them.
2. Write 5-8 clarifying questions to send the requester, ordered by how much the answer changes the work (time window, population, metric definition, comparison, level of precision needed).
3. Propose the smallest analysis that answers the question: metrics with definitions, cuts, comparison or baseline, and the method.
4. List the data needed, likely sources, and known quality risks.
5. Define the deliverable: format (number, table, chart, memo, dashboard), and what "done" looks like.
6. Flag scope creep risks and what I should explicitly leave out.
Return:
- A one-paragraph problem statement.
- The clarifying questions as a ready-to-send message.
- An analysis plan table: Step | Data/source | Method | Output | Est. effort.
- Assumptions I am making, each marked [CONFIRM].
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- PASTE the message, ticket, or what was said
- e.g. "VP of Sales", "product manager for onboarding"
- YOUR GUESS, or "unknown"
- tables, tools, dashboards, known gaps
- e.g. "by Friday, about 1 day"
- CONFIRM
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Explain my Excel model to a non-technical executiveTurns a complex spreadsheet or model into a plain-English walkthrough an executive can follow, trust, and question.
- Run a fair lending review of loan pricing and approval dataA structured fair lending analysis plan and readout that tests for disparities in approvals, pricing, and exceptions.
- Clean a messy datasetA step-by-step cleaning plan for duplicates, missing values, formats, and outliers.
- Find what my dashboard is not telling meReviews a dashboard for blind spots, missing comparisons, vanity metrics, and misleading views, and suggests what to add.