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.
Latest posts
All articles →
Review, tests, and not trusting green checkmarks
After Codex edits, do not ship on green checkmarks alone. Read the diff, run tests, hunt secrets, check scope, and keep a human on the commit. Diff smells and undo patterns included.
Cowork vs chat vs Claude Code
Chat, Claude Code, and Claude Cowork share a model family but not a job. Part 1 of the Claude Cowork tutorial separates…
Validation checks you can automate
Automated checks catch bad data before leadership does. Build small scripts for row counts, referential integrity, freshness, and yesterday versus last week…
Skills, tasks, and scheduled help (as product offers)
Skills, tasks, and scheduled help in ChatGPT Codex are power-ups, not day-one defaults. Climb a complexity ladder, hedge product renames, and never…
Team habits and safety rails
Part 10 closes the Claude Code tutorial with team rails: shared CLAUDE.md and skills, required PRs and green CI, secrets policy, no…



