Opening soon

Claude Code & Command-Line AI

Use Claude Code in the terminal to set up projects, give it the right context and write precise prompts.

5 chapters · 22 lessons

Want a note when it opens?

Join the waitlist and we'll email you when the course is ready.

What you'll cover

The chapters

The plan for the full course. Lessons open when the course does.

Self-check

5 quick questions. Pick an answer to see why it's right or wrong. Nothing is saved.

Question 1 of 5
After writing `export ANTHROPIC_API_KEY='sk-ant-...'` to ~/.zshrc, what must you do for the change to take effect in the current terminal session?
Question 2 of 5
After installing nvm and running `nvm install 20`, what command should be run to confirm the correct Node.js version is active?
Question 3 of 5
What format does an Anthropic API key begin with?
Question 4 of 5
A Claude response generated a Node.js server that uses `fetch` instead of `axios`. What does this code choice suggest about its assumptions?
Question 5 of 5
Which of these is an AI coding tool least able to infer from your project's files without being told?

In the news

From NewsPals, our sister newsroom.

ZDNet’s 138 Developer Survey Says 75% Prefer Claude Code Over Codex (opens in new tab)Aug 15, 2026
A small but useful survey suggests developers care less about leaderboard sparkle and more about tools that behave during real work.
Building Knowledge Bases That Actually Remember: Claude's Self-Maintaining AI Workflows (opens in new tab)May 23, 2026
How to build persistent AI memory systems that evolve without constant manual updates

Key terms

CLAUDE.md: A Markdown file in a project that Claude Code reads at the start of each session, holding standing instructions, conventions and context.
Persistent context: Instructions and facts kept in files the tool loads every session, so you do not have to repeat them in each prompt.
Project scaffolding: Generating the starting structure of a project, such as folders, configuration files and base modules, before writing feature code.
Root cause analysis: Tracing a bug back to the condition that started it, instead of patching the symptom where it first showed up.
Dependency management: Tracking which packages and modules a project relies on, and changing them in an order that keeps the system consistent.
Secret management: Storing and rotating API keys, tokens and passwords so they never appear in source code, logs or prompts.
Prompt engineering: Writing instructions for an AI model with clear structure, context and constraints so the output is accurate and usable. Read the explainer

Help us choose

Pick the one you'd take first. Your vote helps us decide what to finish next.