Use Claude Code as an agentic tutor in your learning environment
The author gave Claude Code a tutor role with a CLAUDE.md brief so it could explain concepts and interact with his learning environment.
Done withClaude Code
- What they did
- The author gave Claude his old SQL pipeline blog post and gists, then had it write a CLAUDE.md telling it to teach him dbt instead of just migrating the code. Claude explained concepts, gave skeletons for him to fill in, and ran installs and diagnostics. He stepped in whenever it started building things itself.
- How it went
- He learned dbt by migrating his pipeline and called it great. Claude kept jumping ahead to build things, suggested shortcuts like SELECT *, and invented column values until challenged. He let it write the Dagster Python.
- Worth knowing
- Expect to keep correcting Claude's urge to just do the work. The author also notes it can mislead, so check its claims, especially on newer or niche technology.
Try it yourself with Claude Code
Act as my tutor for [subject, e.g. Rust or linear algebra] inside this project folder. First write a CLAUDE.md that says: explain concepts at [my level], ask me questions before giving answers, and use the files, notebooks and exercises in this folder as teaching material. Then read the folder and start with a short lesson on [first topic] followed by one exercise for me. Don't change or delete my files without asking me first.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
Source: rmoff.net · Feb 20, 2026
Related use cases
Turn tickets into merged pull requests
Pulls tasks from GitHub Issues or Linear, then runs Claude Code or Codex in isolated Kubernetes pods to carry each one through to a PR.
Audit subscriptions and email companies to cancel them
Claude Code pulled transactions across credit cards, flagged recurring charges, and drafted cancellation emails, recovering $700.
Audit ad accounts across six platforms
A Claude Code skill runs parallel subagents performing 190 audit checks across ad platforms and produces a prioritized action plan.
Run persistent financial research with an agent
LangAlpha is a Claude Code-style agent for investing research that keeps persistent workspaces and memory so analysis such as models and comps can be updated across sessions.
Custom agent
Try Devin on research tasks (mostly failed)
Answer.AI had Devin fetch an author's recent papers and research transcript summarization; it got stuck parsing HTML and returned generic results, rated a failure.
Run academic literature reviews from seed papers
Poster built an agent skill that starts from seed papers, searches backward and forward, screens candidates, and iteratively refines a literature review.
Custom agent
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.