Claude Code 101

What the course covers

Claude Code 101 is a free, self-paced course on Anthropic Academy for developers who are new to software engineering or new to AI coding agents. Its curriculum runs in four parts:

• What is Claude Code? What a coding agent is, how Claude Code differs from chat-based AI tools, and how the agentic loop, context window, tools and permissions work together.
• Your first prompt: installing Claude Code in the terminal, VS Code, JetBrains, Claude Desktop or on the web, and writing a first prompt.
• Daily workflows: the explore, plan, code, commit workflow, context management with /compact, /clear and /context, and code review.
• Customising Claude Code: the CLAUDE.md file, subagents, skills, MCP servers and hooks.

It ends with a course quiz.

Prerequisites

Anthropic lists basic familiarity with a code editor and the command line, and a Claude account (Pro, Max or Enterprise) or an API key. The course itself is free; using Claude Code for the exercises needs one of those.

Is it worth your time?

Yes, if you are about to use Claude Code on anything real. The biggest mistakes new users make are treating it like a chat window, running one endless conversation, and granting permissions without understanding them. This course addresses all three early. It is also official, so the commands and file names match the current product rather than an older release.

What you can do after it

• Install and start Claude Code in a real project.
• Choose between approval, auto-accept and Plan Mode for a task.
• Keep sessions focused with /clear, /compact and /context.
• Write a first CLAUDE.md and know what belongs in it.
• Understand what subagents, skills, MCP and hooks are for, even if you do not use them yet.

How it fits the Coding with AI tools roadmap

The Claude Code edition of the Sefism roadmap uses this course in the first two stages: understanding what agents are good and bad at, then setting up your project context. The roadmap then adds what a product course does not dwell on: reviewing AI code with a checklist, testing first, debugging with evidence, security, and keeping your own skills sharp.

Common questions

How long does it take? It is self-paced. Leave extra time to try each lesson in a real project, which is where it sticks.

What should I take next? Claude Code in Action, Anthropic's follow-on course on longer, less supervised sessions.