Claude Managed Agents is a suite of composable APIs from Anthropic for building, running, and observing cloud-hosted AI agents at scale, launched in beta on April 8, 2026. The platform decouples the model — the "brain" — from execution infrastructure — the "hands" — by providing a fully managed, sandboxed environment in which 📝Claude can read files, run commands, browse the web, and execute code under scoped credentials. It handles checkpointing, credential vaulting, permissioning, and end-to-end tracing, and is billed as token usage plus $0.08 per session-hour of active runtime. Positioned alongside 📝Claude Cowork as part of Anthropic's enterprise push, Managed Agents reframes Anthropic from a model vendor into an agent infrastructure provider, with Notion, Rakuten, and Asana among early adopters.
