An agentic coding tool, not autocomplete.
Claude Code takes a bug fix, a set of tests or a multi-day migration and does the work: it searches the whole codebase, plans, writes the code, runs the tests and opens the pull request, asking when it needs a decision. Developers steer and review from the terminal, their IDE, the desktop app, Slack or the web.
Included in Claude's Team and Enterprise plans, and available with a Claude Console account billed at API rates.
Developers decide; Claude Code does the implementation.
Anthropic's description of the shift: you set the direction as the architect and orchestrator, and Claude Code does the work, surfacing the decisions it needs from you.
- 01Agentic, not autocomplete
- It builds whole features from natural language: writes the code, creates the tests and opens the pull request.
- 02The whole codebase
- It searches the entire repository, not just the open file, which is what makes migrations, cross-file debugging and real code review possible.
- 03Long-running work
- Routine fixes and tests, and also refactors and new features that run for hours or days, several at once.
- 04Where developers already work
- Terminal, VS Code and JetBrains, the desktop app, the web, iOS and Android, Slack and GitHub.
- 05Your tools, its tools
- It uses your command-line tools such as Git, and MCP servers such as GitHub, to work with deployment, databases and monitoring.
- 06Asks before it acts
- In the terminal it runs locally, talks directly to the model APIs with no remote code index, and asks permission before changing files or running commands.
Six things Claude Code takes on.
Pick one to see what Anthropic describes.
Terminal, IDE, desktop, web, mobile and Slack
It fits the workflow instead of replacing it.
- The terminal, with the command-line tools you already use.
- Native extensions for VS Code (also Cursor and Devin Desktop) and JetBrains IDEs.
- The Claude desktop app, on Pro, Max, Ultra, Team and Enterprise plans.
- The web and the iOS and Android apps, for parallel work or coding on the move.
- Slack: kick off coding tasks from a channel, and debug and review in the thread.
- GitHub and GitLab: read issues and open pull requests.
Adopted without retraining
Anthropic's argument: because it works where developers already are, teams adopt it without changing how they work.
A bug report, followed to a merged fix.
Built from Anthropic's own examples. An illustration, not a promise of any particular set-up.
- ReportedA bug report lands in Slack.
- ReproducedClaude Code reads the code and reproduces it.
- FixedIt finds the root cause and edits the code.
- TestedIt runs your tests and opens a pull request.
- ReviewedCode Review, then a human approves the merge.
Illustrative. Your managed settings decide which commands Claude Code may run without asking.
© 2026 Mawkish Technologies. This guide, its diagrams and illustrations are protected by copyright. You’re welcome to learn from it and to quote it with credit and a link. Reproducing it, by hand or through AI, and publishing it as your own is not allowed. Read our copyright notice
Straight answers.
How do we get Claude Code?
Anthropic includes it in the Pro, Max and Ultra plans and in Team and Enterprise, and it can also be used with a Claude Console account, where it consumes API tokens at standard rates.
Is Claude Code secure?
Anthropic says that in the terminal it runs locally and talks directly to the model APIs, with no backend server or remote code index, and that it asks permission before changing files or running commands.
Can it run through our cloud provider?
Yes. Anthropic says Claude Code deploys through Amazon Bedrock, Google Cloud and Microsoft Foundry, integrating with your IAM, logging and VPC configuration, as well as through Anthropic's own cloud.
Does Anthropic train on our code?
Anthropic says that by default it does not train on Enterprise data, including code, conversations and proprietary information, except feedback you choose to send. Usage is subject to automated safety monitoring for misuse.
Can we enforce our coding standards?
Yes. Anthropic describes deploying CLAUDE.md files to system directories for company-wide standards, with repository-specific files for project architecture and contribution guidelines, which Claude Code reads automatically.
What is fast mode?
A high-speed configuration for Opus 5.5 with lower latency at a higher price per token, available in Claude Code and on the Claude Platform.
Checked against Anthropic's own pages in November 2026.
You are on Claude Code. Where next?
Claude Enterprise, the Claude Platform, Claude and Claude Code each have their own page. Visit them in any order. Choose one to go there.
You are currently viewing Claude Code
- 01Deploy to your peopleClaude EnterpriseClaude for every employee, with the controls IT needs.Secure access to Chat, Claude Cowork, Claude Code and your company's connectors for the whole workforce, with SSO, SCIM, audit logs, retention controls and spend limits.Chat and CoworkClaude CodeSSO and SCIMNo training by defaultGo to Claude Enterprise →
- 02Build into your productsClaude PlatformBuild Claude into your products, services and agents.The Claude API, its tools and Claude Managed Agents, for developers building AI into applications and running production agents, directly or on AWS, Google Cloud or Microsoft Foundry.Messages APIManaged AgentsMCP and skillsRegional residencyGo to Claude Platform →
- 03For everyone at workClaudeHand Claude a task, not just a question.The Claude app on web, desktop and mobile, with Cowork's ability to work across your files and tools, finished documents and decks, and Claude inside Microsoft 365, Google Workspace, Chrome and Slack.Tasks and schedulingArtifactsConnectors and skillsMicrosoft 365Go to Claude →
- You are here04For developersClaude CodeAn agentic coding tool for the whole codebase.Hand Claude a bug fix, a test or a multi-day migration and steer it from the terminal, the IDE, Slack or the web. It reads the whole repository, runs your tests and opens the pull request.Terminal and IDEIssues to PRsCode ReviewManaged settingsYou are viewing this page
Also on Claude
Talk it through with us.
Tell us what you want Claude to do for your organisation, and we will help you work out where to start, safely.
- Your goals, data and the systems involved
- Claude Enterprise, the Platform, or both
- A sensible first step
Anthropic, Claude, Claude Code and the other product names on these pages are trademarks of Anthropic, PBC. No Anthropic logo or artwork is used, and nothing here implies Anthropic's sponsorship or endorsement. Other names are the property of their owners. Screens shown are our own illustrations with sample data, not Anthropic screenshots. Product descriptions follow Anthropic's own published material and may change; check claude.com and anthropic.com for current details.
We call our approach to Claude Code the Ruelane Cadence: advice that stays on your side of the table.