Redesigning source control at Anthropic
As our merges per day grew more than tenfold, source control became our biggest development bottleneck. Here, we share how we migrated to an in house version control system in five months.
AI & ML17 min read
Anthropic Engineering
How Anthropic builds agents, evals and infrastructure.
How we contain Claude across products
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
AI & ML18 min read
An update on recent Claude Code quality reports
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
AI & ML8 min read
Scaling Managed Agents: Decoupling the brain from the hands
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
AI & ML9 min read
How we built Claude Code auto mode: a safer way to skip permissions
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
AI & ML15 min read
Harness design for long-running application development
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
AI & ML21 min read
Eval awareness in Claude Opus 4.6’s BrowseComp performance
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
AI & ML9 min read
Building a C compiler with a team of parallel Claudes
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
AI & ML11 min read
Quantifying infrastructure noise in agentic coding evals
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
AI & ML8 min read
Effective harnesses for long-running agents
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
AI & ML9 min read
Introducing advanced tool use on the Claude Developer Platform
Claude can now discover, learn, and execute tools dynamically to enable agents that take action in the real world. Here’s how.
AI & ML11 min read
Code execution with MCP: building more efficient AI agents
Learn how code execution with the Model Context Protocol enables agents to handle more tools while using fewer tokens, reducing context overhead by up to 98.7%.
AI & ML6 min read
Making Claude Code more secure and autonomous with sandboxing
Learn how Claude Code's new sandboxing feature protects developers with filesystem and network isolation, reducing permission prompts and increasing user safety.
AI & ML5 min read
Equipping agents for the real world with Agent Skills
Discover how Anthropic builds AI agents with practical capabilities through modular skills, enabling them to handle complex real world tasks more effectively and reliably.
AI & ML6 min read
You're all caught up ✓