Blog
SQL, data, and practical AI — plain English. Filter by topic or search.
All articles
Orchestration in one metaphor
Orchestration is kitchen management for data: schedules, dependencies, and retries. Learn the Airflow and dbt mental models so broken morning numbers point to a clear task, not a…
Prompt patterns for data work
Good data prompts are contracts, not vibes. Part 3 of Practical AI for analytics people covers role, spec, output shape, and refuse rules, plus SQL-then-explain patterns that block…
Quality control and avoiding workslop
Part 6 of the Claude Cowork tutorial. Catch workslop before it ships: skim structure, check numbers and names, verify scope, then human sign-off. Auto mode screens risky actions;…
Dashboards vs single slides
Dashboards monitor change; single slides carry one decision. Learn the one-idea-per-view rule, a practical declutter checklist, and a worked redesign that splits a busy ops page into a…
Fine-tuning vs RAG
Fine-tuning changes how a model behaves; RAG fetches your documents at ask time. Learn when each helps, when to combine them, and why neither replaces data quality or…
