Review my analysis for errors before it goes out
A rigorous second-pair-of-eyes check of an analysis for logic, data, statistical, and communication mistakes, ranked by severity.
The prompt
Review my analysis for errors before I share it.
The question it answers: [BUSINESS QUESTION]
The analysis: [PASTE the write-up, key queries or code, tables, and chart descriptions]
Data used: [sources, date ranges, filters]
Audience and what they will decide: [e.g. "leadership deciding whether to expand the pilot"]
Check for:
1. Question fit: does the analysis actually answer the question asked, or a slightly different one?
2. Data problems: wrong filters, missing periods, duplicates from joins, test or internal records, survivorship bias, incomplete recent data.
3. Logic and math: denominators, averages of averages, percentage vs. percentage-point confusion, double counting, mismatched time windows.
4. Statistics: small samples, no measure of uncertainty, multiple comparisons, correlation presented as causation, Simpson's paradox, regression to the mean.
5. Comparisons: is the baseline fair? Are segments comparable?
6. Charts: truncated axes, misleading scales, unlabeled units.
7. Conclusions: are claims stronger than the evidence? Are caveats stated?
Return:
- A findings table: Issue | Where | Severity (critical / important / minor) | Why it matters | Suggested fix.
- The 3 checks I should run before sending.
- Rewritten versions of any overstated conclusions.
Be direct. If something cannot be judged from what I shared, say what you would need to see.
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
- BUSINESS QUESTION
- sources, date ranges, filters
- e.g. "leadership deciding whether to expand the pilot"
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
- Write a data dictionary for a table or datasetProduces clear column-level documentation with definitions, types, allowed values, grain, and known caveats so others can use the data safely.
- Write a model card to document a machine learning modelA complete model card covering intended use, data, performance by segment, limitations, fairness checks, and monitoring plan.
- Write the caveats and limitations section of my analysisAn honest, readable limitations section that explains uncertainty and data gaps without burying the conclusion.
- Write a pre-registration and analysis plan for my studyDrafts a pre-registration covering hypotheses, sampling, variables, analysis decisions, and exclusion rules before data collection.