Data Dictionary
Defines grain and null semantics per field, since those are what consumers of the data get wrong.
Free — no card needed
Create a free account
to open Data Dictionary — and the other 364 prompts across 21 categories.
Already have an account?
Running it, start to finish
- State what one row represents for every table.
- Define what null means for each nullable column.
- Document known quality issues with their date ranges.
What you get back
The output this produces, every time.
- States the grain of every table, which is the source of most incorrect analysis.
- Documents what null means per column, since one representation often carries several meanings.
- Records known quality issues and date ranges, which saves more analyst time than anything else.
Getting better results
Where this usually goes wrong, and how to avoid it.
- Distinguish event time from write time. It is quietly responsible for a large share of wrong analysis, and the column name rarely reveals which it is.
- List deprecated status values. An analyst filtering on the values present in recent data silently drops historic rows.
- Write the known-issues section. It is the one nobody writes because it records problems, and it is the most useful part of the document.
More Data Analysis prompts
All Data Analysis →- Data Analysis
Segmentation Analysis
Produces segments that are actionable and stable, since statistically clean but unusable is the standard failure.
ClaudeChatGPT002Open → - Data Analysis
Metric Definition Review
Treats two teams reporting one metric differently as a governance problem rather than a query bug.
ClaudeChatGPT000Open → - Data Analysis
A/B Test Design and Reading
Designs a test that can actually detect the effect you care about, and states the decision rule before the data arrives.
ClaudeChatGPT000Open →
Written for The AI University. Every prompt in this library is original work — authored, tested and revised here, not collected from elsewhere. 365 of them, free with an account.