Write the caveats and limitations section of my analysis
An honest, readable limitations section that explains uncertainty and data gaps without burying the conclusion.
The prompt
Write the caveats and limitations section for my analysis so readers understand how far they can trust it.
Main findings: [PASTE summary]
Data and method: [sources, time period, sample size, method]
Known issues: [e.g. "missing data for March", "survey response rate 14%", "no control group", "small segments"]
Audience and decision: [who reads it and what they will decide]
Steps:
1. Identify the limitations that actually matter for the decision, including ones I may have missed: sample size and uncertainty, selection or response bias, data quality gaps, correlation vs. causation, short time windows, seasonality, definition changes, and how far results generalize.
2. For each, state the likely direction and size of the effect on the findings (overstated, understated, or unclear).
3. Separate what we can say confidently from what is suggestive and what we cannot say.
4. Recommend what would reduce each uncertainty (more data, a test, a different method) and whether it is worth doing before deciding.
5. Express uncertainty in plain terms, such as ranges, rather than only p-values.
Return:
- A short "How confident are we?" summary (3-4 sentences) for the top of the doc.
- A limitations table: Limitation | Effect on findings | How confident we are | What would fix it.
- A plain-English version for executives (under 100 words).
Tone: candid and specific, not defensive. Do not add limitations that would not change the decision, and do not weaken findings the evidence clearly supports.
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 summary
- sources, time period, sample size, method
- who reads it and what they will decide
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.
- Review my analysis for errors before it goes outA rigorous second-pair-of-eyes check of an analysis for logic, data, statistical, and communication mistakes, ranked by severity.
- 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 a pre-registration and analysis plan for my studyDrafts a pre-registration covering hypotheses, sampling, variables, analysis decisions, and exclusion rules before data collection.