Blog
SQL, data, and practical AI — plain English. Filter by topic or search.
All articles
Markdown and project instruction files (CLAUDE.md, AGENTS.md, and friends)
Part 6 of the Claude Code tutorial. How CLAUDE.md, AGENTS.md, README, and related instruction files split work between humans and agents, with a sample CLAUDE.md skeleton and the…
What bad data actually means
Bad data is a shrug, not a diagnosis. Learn five practical quality dimensions (completeness, accuracy, consistency, timeliness, uniqueness) with workplace examples so you name the failure mode before…
First agentic task with approvals
Part 2 walks one low-risk agentic task with approvals: owned notes into a short status deck, tight tool access, and human review before anything leaves your desk. First…
Memory and context: what sticks, what resets
Part 5 of the Claude Code tutorial. Chat resets with /clear or a new session, CLAUDE.md reloads every time, auto memory can carry learnings if you verify it…
Notebooks vs scripts for teammates
Notebooks help you explore. Scripts help you repeat. Learn when to stay in a notebook, when to graduate to a .py file, and how to hand work to…
