Data analysis scripts with AI: pandas, SQL and charts
Bots write pandas fast; check the numbers.
What to do
- Give column names, types and a few sample rows (no private data).
- Ask for each cleaning step to be printed with row counts.
- Verify one aggregate by hand.
- Ask for charts with labeled axes and units.
Copy this prompt
Write Python (pandas + matplotlib) to [analysis]. Columns: [list with types]. Sample rows: [paste anonymized]. Print row counts after each cleaning step and explain assumptions.Check the bot's work
Spot-check totals.
Questions
Can I trust the bot on data analysis code?
Use it to plan and explain, then verify. Spot-check totals.
Which bot works best?
Grok Bot, ChatGPT, Claude and Gemini all handle this prompt. Paste the same prompt into two and compare; disagreements show where to check a source.
Where these facts come from
- OWASP Top 10
- CISA: Secure by Design
- GitHub Docs: Secret scanning
- W3C: WCAG overview
- Open Source Initiative: Licenses
- NIST SP 800-218: Secure Software Development Framework
Tools, features and prices change often. We don't list prices; check each vendor's official pricing page. Never paste secrets into a prompt. Checked Oct 30, 2026.
Coding with bots · Agents, tools and setup: all lessons →