What is Claude Code?
Claude Code is an agentic coding tool: an assistant that reads your codebase, edits files, runs commands, and integrates with your development tools. While it excels at coding, it can help with anything you can do from the command line — writing docs, running builds, searching files, researching topics.
It runs in three execution environments and many interfaces. The agentic loop, tools, and capabilities are identical everywhere; only where code executes and how you interact changes.
| Environment | Where code runs | Use case |
|---|---|---|
| Local | Your machine | Default. Full access to your files, tools, and environment |
| Cloud | Anthropic-managed VMs | Offload tasks, work on repos you don’t have locally |
| Remote Control | Your machine, controlled from a browser | Web UI while keeping everything local |
Interfaces include the terminal CLI, the desktop app, VS Code and JetBrains extensions, claude.ai/code, Slack, and CI/CD pipelines. Because Claude sees your whole project — not just the current file — it can make coordinated edits across files, run tests to verify them, and commit changes when you ask. That is the key difference from inline code assistants.
Check your understanding
Section titled “Check your understanding”Question 1What makes Claude Code different from an inline code assistant?
Claude Code searches, reads, and edits across the project, runs commands, and verifies its own work — inline assistants only see the current file.
Question 2Which environment runs your code on Anthropic-managed VMs?
Cloud sessions execute on Anthropic-managed VMs; Remote Control keeps execution on your machine while you drive from a browser.