Insights for the Rest of Us
Analytics and AI without the intimidation. Plain-language guides to SQL, data work, and practical AI. Examples you can use at work, a little humor, no PhD required.
Different jobs
All articles →
How to test whether a cheaper AI decision model is good enough for your team
New AI decision models launch with big scores, but the only test that counts is yours. Here is how to check a cheaper model on your own past cases with three spreadsheet formulas, using Decision Bench's published answers as a worked example.
- SQL · November 10, 2024 · 14 min read
SQL Tutorial 13: Strategies for Maintenance and Optimization
Keep databases healthy over time with backups you can restore, slow query awareness, stats and vacuum concepts, access grants, and on-call hygiene. Close the SQL series with a full path recap and next learning links.
- Analytics · September 6, 2026 · 12 min read
A/B tests intuition for analysts
A/B tests need a clear unit, a primary metric, and honest peeking rules. A green checkmark with +3.2% lift can still be calendar-driven science if you stop early.
- Models · October 12, 2026 · 10 min read
How good is Qwen at languages other than English?
Use Qwen for multilingual drafts with a four-step protocol: bound the text, name the register, attach glossary terms, and human-verify legal lines. Skip English-bridge round trips for warranty language.
- Data work · September 11, 2026 · 13 min read
When to stop prompting an AI chatbot and do the task yourself
Prompting has a clock. When facts, feeling, or your signature matter, close the chat and do the task yourself.
