What Is Claude Code

An agentic CLI that reads your repo, edits files, runs tests, and commits — all with permission gates you control.

Claude Code is not autocomplete. It is an agent that operates a real terminal: it reads files, runs commands, writes code, and waits for your approval at each risky step. It lives in your terminal first, but the same agent now runs in the VS Code and JetBrains extensions, a desktop app, and on the web at claude.ai/code — everything in this course transfers.

The mental shift: instead of typing characters, you describe outcomes. Instead of clicking Run, you watch the agent run things and read back the output. Instead of debugging line by line, you tell it what's broken and it iterates until tests pass.

Vibe coding is the practice of working at this altitude. You stay in flow on the what, the agent handles the how. The skills you'll build in this course are the prompts, patterns, and guardrails that make this loop reliable.

Watch · Anthropic

The team that builds Claude Code explains the agentic model this whole course is built on — worth 10 minutes before you type your first prompt.

Check your understanding

Q1. Which of these best describes Claude Code?

Q2. What is the core mental shift of "vibe coding"?

· Score 100% on the quiz.

Vocabulary in this lesson

AgentA model wired to tools and a loop: it reads, acts, checks the result, and goes again until the task is done or you stop it.Vibe codingBuilding software by describing what you want to an agent and judging the result rather than reading every line of code.Permission requestThe harness pausing before a risky tool call to ask you yes or no; the simplest human-in-the-loop gate there is.

Plain-English definitions from the AI Coding Dictionary.