Check whether my data is reliable enough to base a decision on
A fitness-for-use review that lists the dataset's limitations and which fields, periods, or segments should not drive this decision.
The prompt
Before I use this data to make or support a decision, help me judge whether it is reliable enough and what its limits are.
Data: [PASTE A SAMPLE, PROFILE, OR DESCRIPTION]
Source and how it was collected: [system, survey, manual entry, or third party; date range]
Decision it will support: [e.g. "which stores to close", "whether to renew the vendor"]
Known issues: [OPTIONAL]
Assess it against this decision, not in the abstract:
1. Coverage: does it include the full population, period, and segments the decision is about?
2. Timeliness: is it recent enough?
3. Definitions: are key metrics defined the same way across the period and across sources?
4. Accuracy signals: completeness, duplicates, manually entered fields, unexplained jumps.
5. Sample size: are any segments too small to compare?
6. Proxy risk: is a metric standing in for something it doesn't really measure?
Return:
1. A verdict: Fit to use / Use with caveats / Not fit for this decision, with reasons.
2. A table: Field, segment, or period | Issue | Effect on the decision | Use it? (yes / with caveat / no).
3. The data that should NOT be used for this decision, and why.
4. The limitations I must state when I share results, in plain language.
5. What it would take to make the data usable, and whether that's worth the effort.
Be candid. If the data can't answer the question, say so instead of stretching it. The decision and its risk stay with me and the data owner.
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 A SAMPLE, PROFILE, OR DESCRIPTION
- system, survey, manual entry, or third party; date range
- e.g. "which stores to close", "whether to renew the vendor"
- OPTIONAL
How this prompt is built
This prompt follows the RTF structure (Role, Task, Format). RTF tells the model who to be, what to do and what shape the answer should take. It is the quickest structure that still gives noticeably better results than a bare request.
Related prompts
- Turn my monthly or quarterly numbers into an executive business reviewTurns your numbers into an executive business review: headline, performance vs. plan, drivers, risks, and decisions needed, as a report or slides.
- Compare performance against targets and find the biggest gapsCompares actuals against targets for every KPI, sizes each gap, and ranks the gaps that matter most so you know where to focus.
- Check whether my KPIs measure activity or real value, and fix themSorts your KPIs into activity, output, and outcome measures, flags vanity metrics, and redesigns the set around the outcomes that matter.
- Challenge my interpretation of the data and find other explanationsStress-tests your conclusions for alternative explanations, cherry-picking, and averaging traps, then gives you a defensible version.