Learn what Claude Code is, how it differs from other coding assistants, and how its use of tools lets it read files, run commands, and explain code for you.


Video: Introduction

Exploring code with Claude

Video: What is a coding assistant

Claude uses tools!

Video: Claude Code in action

A rough first draft

Refining the UI with Claude Code

Your improved form!

What is Claude Code?

Set up Claude Code on a real project, then guide it with CLAUDE.md and context controls, make safe edits with plan mode, and extend it with custom commands, MCP servers, and GitHub.


Claude Code setup

Project setup

Video: Adding context

Bootstrap CLAUDE.md for the UI generator

Pulling files in for questioning with @

Video: Making changes

Making changes

Planning a cross-file edit

Video: Controlling context

Controlling context

Measuring and compacting a session

Video: Custom commands

Custom commands

Creating a reusable test-writing command

Video: MCP servers with Claude Code

MCP servers with Claude Code

Connecting a filesystem MCP server

Video: Github integration

Github integration

Getting Hands On

Automate Claude Code with hooks that run before and after its tools, blocking risky file reads, type-checking edits, and flagging duplicate code, then drive Claude from your own scripts with the SDK.


Video: Introducing hooks

Introducing hooks

Video: Defining hooks

Defining hooks

Video: Implementing a hook

Implementing a hook

Fixing a faulty hook

Blocking .env reads with a hook

Gotchas around hooks

Video: Useful hooks

Useful hooks

Catch Type Errors with a Post-Tool-Use Hook

Another useful hook

Video: The Claude Code SDK

The Claude Code SDK

Run your first Agent SDK query

Grant the SDK a tool

Claude Code or the Claude Agent SDK?

Video: Summary and next steps

Hooks and the SDK

Claude Code puts an AI coding agent right in your terminal, but reliable results come from guiding it well, not just asking it to write code. This hands-on course shows you how. You'll start with what actually makes Claude Code work: tool use, the mechanism that lets it read files, run commands, and act on real projects. From there you'll master the skill that matters most, context management, using CLAUDE.md, file mentions, and commands like /compact to feed Claude exactly what it needs and nothing more. Along the way you'll make safe, reviewable edits with Plan mode, turn repeated prompts into custom slash commands, connect external tools through MCP servers, and integrate Claude Code with GitHub. Then you'll automate your workflow with hooks and reach beyond the terminal with the Claude Agent SDK to run Claude in scripts and CI. Real workflows, real codebases, results you can trust.

<h2>Turn Your Terminal into an AI-Powered Development Environment</h2> Claude Code is Anthropic's agentic coding assistant that lives in your terminal, reading your files, running commands, and editing code on your behalf. This course shows you how to use it well — not by typing hopeful prompts and accepting whatever comes back, but with deliberate workflows that produce reliable results. You'll work inside a real project the whole way through, and because DataCamp provides a ready-to-use environment, you'll run actual Claude Code sessions from the very first exercise, with no installation or API key required. <br><br> <h2>Understand How Claude Code Actually Works</h2> Before you can guide a tool, you need to know what it is doing. You'll learn what a coding assistant really is, and how a language model — which can only turn text into text — uses tool calls to read files, run commands, and act on the outside world. You'll see why Claude's strength with tool use is exactly what sets Claude Code apart, and watch it take on real tasks: profiling and optimizing a popular open-source library, analyzing data in a notebook, restyling a web app through a live browser, and reviewing a pull request for a security issue on GitHub. <br><br> <h2>Build a Reliable Daily Workflow</h2> Strong results with Claude Code come down to one core skill: managing context. You'll set up Claude on a project with /init and a CLAUDE.md file, point it at the right code using @ file mentions and memory mode, and keep long sessions focused with /context, /compact, and /clear. From there, you'll make safe, reviewable changes with plan mode and extended thinking, commit them with messages Claude writes for you, and turn repetitive prompts into custom slash commands. Finally, you'll extend Claude Code with MCP servers and wire it into GitHub to review pull requests automatically. <br><br> <h2>Automate and Extend with Hooks and the SDK</h2> Claude Code does not have to wait for your next prompt. You'll learn to write hooks that run automatically before and after Claude uses a tool — blocking reads of sensitive files such as .env, type-checking every edit and feeding errors back so Claude can fix them, and even launching a second Claude instance to catch duplicate code before it lands. Then you'll step outside the terminal entirely with the Claude Code SDK, driving Claude from your own scripts, pipelines, and scheduled jobs. <br><br> By the time you finish, you'll know how to set up Claude Code on any project, guide it with just enough context, and extend it with custom commands, MCP servers, hooks, and the SDK — a practical, end-to-end foundation for shipping real work with an AI coding assistant you can trust.

Claude Code 101

Get hands-on with Claude Code, Anthropic's terminal AI agent: master context, plan mode, custom commands, MCP, and hooks to ship real work you can trust.

Claude Code in Action

A rough first draft

Claude Code in Action

Bài tập tương tác thực hành