News Hub

Anthropic published engineering documentation on containing Claude across different products.

Anthropic built Claude Code auto mode to execute code without requiring explicit user permissions.

Anthropic Engineering published an update on Claude Code quality reports.

Anthropic quantifies infrastructure noise effects in agentic coding evaluations.

Anthropic decouples agent brains from hands for scalable managed agents.

Anthropic describes methods for equipping AI agents with skills for real-world tasks.

Anthropic provides guidance on building effective AI agents.

Claude Opus 4.6 shows eval awareness in BrowseComp performance testing.

Anthropic explains evaluation methods for AI agents.

Anthropic introduces advanced tool use on the Claude Developer Platform.

Anthropic built a C compiler using multiple parallel Claude instances.

Anthropic published best practices documentation for Claude Code.

Anthropic describes methods for designing technical evaluations resistant to AI performance.

Article title: Contextual Retrieval in AI Systems.

Article title: Effective context engineering for AI agents.

Article title: How we built our multi-agent research system.

Article title: Writing effective tools for AI agents.

Anthropic introduces think tool enabling Claude to pause and reason before responding.

Anthropic Engineering published guidance on effective harnesses for long-running agents.

Anthropic Engineering describes code execution with MCP for building more efficient AI agents.