Category
16 AI prompts for Data Analysis
Cleaning, querying, statistics and the chart that says the thing.
Written and tested for The AI University. Each carries its variables, a usage guide and the cases where it will let you down. Free with an account.
16 prompts
- Data Analysis
Segmentation Analysis
Produces segments that are actionable and stable, since statistically clean but unusable is the standard failure.
ClaudeChatGPT002Open → - Data Analysis
Analysis Plan Before the Query
Writes down the question, the method and what would count as an answer before you touch the data — the discipline that prevents fishing.
ClaudeChatGPT000Open → - Data Analysis
SQL Review for Correctness
Reviews a query for the silent wrongness that produces plausible numbers — fan-out joins, null semantics and filters applied after the outer join.
ClaudeChatGPTGemini000Open → - Data Analysis
Chart That Makes the Point
Chooses the chart from the claim you are making rather than from the data's shape, and names the misreadings to design against.
ClaudeChatGPTGemini000Open → - 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 → - Data Analysis
Anomaly Investigation
Investigates a number that moved, ruling out instrumentation before looking for a business explanation.
ClaudeChatGPT000Open → - Data Analysis
Data Dictionary
Defines grain and null semantics per field, since those are what consumers of the data get wrong.
ClaudeChatGPT000Open → - Data Analysis
Cohort Analysis Design
Defines the cohort by an event rather than a date range, or you end up measuring seasonality.
ClaudeChatGPT000Open → - Data Analysis
Dashboard Specification
Requires every tile to answer a stated question, since tiles without one become decoration.
ClaudeChatGPT000Open → - Data Analysis
Forecast Review
Judges on the error distribution rather than on the last data point, which is noise.
ClaudeChatGPT000Open → - Data Analysis
Metric Definition Review
Treats two teams reporting one metric differently as a governance problem rather than a query bug.
ClaudeChatGPT000Open → - Data Analysis
Data Quality Monitoring
Alerts on distribution shift as well as on nulls, since silent skew is the expensive failure.
ClaudeChatGPT000Open → - Data Analysis
Experiment Analysis
Checks the sample ratio before anything else, since broken randomisation invalidates every result that follows.
ClaudeChatGPT000Open → - Data Analysis
Survey Analysis
Reports non-response bias alongside every finding, since who did not answer shapes the result.
ClaudeChatGPT000Open → - Data Analysis
Analysis Notebook Review
Checks the joins and the filters, which is where notebook conclusions actually go wrong.
ClaudeChatGPT000Open → - Data Analysis
Data Pipeline Review
Checks idempotency and late-arriving data, both of which are otherwise discovered in production.
ClaudeChatGPT000Open →