Analysis Notebook Review
Checks the joins and the filters, which is where notebook conclusions actually go wrong.
Free — no card needed
Create a free account
to open Analysis Notebook Review — and the other 364 prompts across 21 categories.
Already have an account?
Running it, start to finish
- Check the grain on both sides of every join.
- Total how many rows were dropped across the whole notebook.
- Restart the kernel and run it end to end.
What you get back
The output this produces, every time.
- Traces grain through every join and checks whether row counts are ever asserted.
- Audits filters for boundary errors and silent null dropping.
- Compares the stated conclusion against what the code actually establishes.
Getting better results
Where this usually goes wrong, and how to avoid it.
- Count rows at every step. A fan-out inflates every downstream aggregate, and without a row count assertion nothing reveals it.
- Check the cumulative filtering. Individually reasonable filters routinely discard a third of the data without anyone noticing.
- Run it top to bottom in a fresh session. Notebooks accumulate hidden state, and a result that will not reproduce cannot be trusted.
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.