Step-by-step guides for SQL, tools, and practical AI — skills you can use at work. Learn by doing, not by jargon.
Series
Step-by-step paths grouped by topic. Start at part 1 and work through at your pace.
Foundations
How analytics works and how everyday data becomes structured.
Core skills
SQL, Python, data quality, charts, and metrics — skills you reuse everywhere.
Data at work
Pipelines, stewardship, and how data moves through real teams.
AI fundamentals
Practical AI for everyday work — product-agnostic judgment and workflows.
AI products
One complete path per brand — first login through deep tools.
Analytics practice
Stats, experiments, customer and finance analytics, and career paths.
BI & workflow tools
Hands-on starters for Power BI, dbt, Airflow, and similar tools.
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…
What Work mode is for
Work mode is the agent for multi-step office jobs: files, apps, decks, sheets, and docs you still review. Part 1 of the ChatGPT Work tutorial separates Work from…
Intro to plotting for analysis
A chart for analysis is a decision tool, not decoration. Learn a small matplotlib stack that turns pandas groupbys into honest bars and lines you can explain at…
Skills: what they are, how to add and use
Part 4 of the Claude Code tutorial. Skills are on-demand playbooks in SKILL.md files. Add them under .claude/skills or ~/.claude/skills, invoke with /name, or let Claude load them…
Email, meetings, and workplace writing
Part 5 closes the ChatGPT everyday tutorial: audience-first emails, meeting agendas, action lists, and who/what/when follow-ups. Never auto-send. Check policy. Next: Work, then Codex, then Custom GPTs.
Python and SQL together
Use SQL for large filters and governed aggregates, then polish results in pandas. Learn a read_sql hybrid pattern, when each tool wins, and how to review AI-generated code…
Slash commands and common command patterns
Part 3 of the Claude Code tutorial. Type slash to find commands, Tab to complete them, and use shell patterns like claude -c and claude -p so you…
Studying and explaining hard topics simply
Part 4 of the ChatGPT everyday tutorial. Study hard topics with explain-simply loops, quizzes, teach-back, Study Mode ideas, and the mistakes that turn “learning” into copy-paste theater.
Export results and hand off
Finish the job with clean CSV exports, optional Parquet or SQL loads, and short metadata notes for every file. Learn what each destination needs so BI tools and…
Talking to a codebase: ask, explore, change
Part 2 of the Claude Code tutorial. Talk to a repo in three beats: ask for a map with real paths, explore until you know what might break,…











