Articles from claude.com

Claude Code offers seven methods for steering its behavior—rules, skills, subagents, hooks, output styles, system prompt appending, and plugins—each with different context costs and authority levels.

Claude Code now turns session work into live, shareable artifact pages that update in place and are private to the organization.

Claude Managed Agents decouples model reasoning from code execution to let teams deploy production-grade agents without building custom infrastructure.

An Anthropic engineering leader describes how agentic coding shifted bottlenecks from writing code to verification, and outlines new norms for planning, review, context gathering, and team roles.

Anthropic's Code with Claude London event recap showcases keynotes and workshops on AI-assisted development using Claude Code and Claude Platform.

Claude Code's dynamic workflows orchestrate tens to hundreds of parallel subagents for complex tasks like codebase-wide migrations or audits.

Claude Code's success in large codebases hinges on a well-structured harness (CLAUDE.md, hooks, skills, plugins, LSP, MCP, subagents) and organizational ownership of configuration and adoption.

Claude Code introduces agent view, a CLI dashboard for managing multiple parallel AI sessions with peek, inline reply, and backgrounding.

Claude Managed Agents adds dreaming for self-improvement through memory review, outcomes for quality grading, and multiagent orchestration for parallel task delegation.

Claude Security public beta lets Enterprise customers scan code for vulnerabilities and generate targeted patches using Opus 4.7, with integrations across partner platforms.

Claude Code's desktop redesign adds parallel multi-session management, drag-and-drop layout, integrated terminal and file editor, plus streaming responses.

Claude's Opus 4.6 and Sonnet 4.6 now provide a 1M token context window at standard pricing with no long-context premium, and support up to 600 images or PDF pages per request.

Claude can now generate interactive charts, diagrams, and visualizations inline during conversations, allowing real-time adjustments as discussion evolves.

Anthropic introduces a one-copy-paste feature that lets users transfer their preferences and memory from other AI providers into Claude.