Claude Code AI features and pricing (October 2026)

Claude Code is Anthropic's agentic coding tool. It reads a codebase, edits files, runs commands and works with git, in the terminal, in VS Code and JetBrains, in a desktop app and in the browser, and suits individual developers as well as enterprise teams.

Claude Code runs on several surfaces that share the same engine, so CLAUDE.md instructions, settings and MCP servers carry over. It connects to tools through the Model Context Protocol, can be customized with skills and hooks, runs subagents and background agents in parallel, and offers routines that run on a schedule in the cloud. The Agent SDK lets teams build their own agents on the same tools.

Access comes with a paid Claude subscription or an Anthropic Console account, and the CLI, VS Code and JetBrains also work with Amazon Bedrock, Google Cloud and Microsoft Foundry. Under commercial terms Anthropic does not train models on code or prompts sent to Claude Code, with a standard retention of 30 days.

• Builds features and fixes bugsYou describe a feature or paste an error, and Claude Code plans the approach, edits the relevant files and verifies the result. Developers move from description to working change with fewer manual steps.
• Handles tedious maintenanceIt writes tests for untested code, fixes lint errors across a project, resolves merge conflicts, updates dependencies and writes release notes. Teams clear backlogs of chores that rarely get prioritized.
• Reviews pull requests in CIThrough GitHub Actions or GitLab CI/CD, Claude Code reviews pull requests and triages issues automatically. Reviewers get a first pass on every change.
• Runs recurring tasks on a scheduleRoutines run in the cloud on a schedule or on GitHub events, for example nightly CI failure analysis or weekly dependency audits. Recurring checks happen without anyone starting them.

• Can run through Amazon Bedrock, Google Cloud or Microsoft Foundry, so companies can use existing cloud contracts.
• No model training on commercial-plan data; zero data retention available for qualified Enterprise accounts.
• Same engine and configuration across terminal, IDE, desktop and web.

Anthropic PBC has its registered address in San Francisco. For users in the EU, Anthropic Ireland, Limited in Dublin is responsible.

Consumer plans (Pro, Max) have a training opt-in setting, while Team, Enterprise and API use commercial terms without training. For company use choose a commercial plan or a cloud provider route. The agent runs commands on developer machines, so define permission rules and review changes before merge.

No reviews yet. Be the first to share how your team uses it.

Every review shows its verification level. We read each one before it goes live. How we check reviews