Coding agents in the social sciences
… Teaching Claude why New research on how we've reduced agentic misalignment.
Search
Trustworthy agents in practice
… We go into greater technical detail on this topic in our submission to NIST's Center for AI Standards and Innovation CAISI on agentic security. …
Building Effective AI Agents
… This might mean not building agentic systems at all. Agentic systems often trade latency and cost for better task performance, and you should consider when this tradeoff makes sense. …
Demystifying evals for AI agents
… For earlier LLMs, single-turn, non-agentic evals were the main evaluation method. …
Measuring AI agent autonomy in practice
… Next, we developed a collection of metrics that draw on data from both agentic uses of our public API and Claude Code , our own coding agent. These offer a tradeoff between breadth and depth: Our public API gives us broad visibility into agentic deployments across thousands of different customers. …
Anthropic acquires Stainless
… Today, Anthropic is acquiring Stainless, a leader in SDKs and MCP server tooling, to extend that reach even further. …
How we contain Claude across products
… In a world where agents read everything, the investigation tooling is also an attack surface. …
Scaling Managed Agents: Decoupling the brain from the hands
…We virtualized the components of an agent: a session (the append-only log of everything that happened), a harness (the loop that calls Claude and routes Claude’s tool calls to the…
Claude Code auto mode: a safer way to skip permissions
… We keep an internal incident log focused on agentic misbehaviors. …
Equipping agents for the real world with Agent Skills
…Agents with a filesystem and code execution tools don’t need to read the entirety of a skill into their context window when working on a particular task. This means that the…