Turn a business question into a SQL query
Describe your tables and the question you need answered and get a correct, commented SQL query with assumptions spelled out.
Get a clear recommendation of the best chart type, how to build it, and which popular choices to avoid for your message.
Help me choose the best chart.
Data: {{data}}
The one message I want the viewer to take away: {{message}}
Audience: {{audience}}
Where it will appear: {{medium}}
Respond with:
1. Recommended chart: the single best chart type, and why it fits this data and message better than the alternatives.
2. Two alternatives and when each would be better.
3. One tempting chart to avoid for this case, and the specific problem it creates.
4. Build spec: what goes on each axis, sort order, how to treat colour (what to highlight, what to mute), what to label directly instead of using a legend, axis starting point, and the number format.
5. Title: write an insight-style title (states the finding) and a subtitle that gives the unit and time period.
6. Honesty check: how this chart could mislead (truncated axis, dual axes, cherry-picked range, too many categories) and how to prevent that.
If the data or message is too vague to decide, ask up to two clarifying questions first. Keep the answer under 450 words.Tying the chart to one message prevents generic advice, and the avoid and honesty sections catch misleading designs. Describe any existing draft chart to get specific critique.
Licensed CC0 (public domain) Version 1 · history
Describe your tables and the question you need answered and get a correct, commented SQL query with assumptions spelled out.
Turn a dataset description into a step-by-step exploration plan with checks, hypotheses and the first charts to make.
Paste a regression table and get a careful interpretation of coefficients, fit and reliability, with warnings about causal claims.
Convert raw findings and numbers into a short, decision-ready summary with the answer first, evidence, caveats and next steps.
Set up a proper cohort retention analysis, from defining cohorts and the activity event to producing the table and reading it correctly.
Convert a stakeholder's fuzzy ask into a scoped analysis brief with the real question, definitions, data needed and success criteria.
Comments (0)
Sign in to join the discussion.
No comments yet. Be the first to share how it worked.