Anthropic has launched Claude Managed Agents in public beta, a suite of composable APIs for building and hosting cloud-based AI agents on the Claude Platform. The offering provides a full production stack including sandboxed code execution, checkpointing, credential management, scoped permissions, and end-to-end tracing. Key features include long-running autonomous sessions, multi-agent coordination, and trusted governance with scoped permissions. Early adopters include Notion, Rakuten, and Sentry. Internal testing showed up to 10-point improvement in task success over standard prompting loops.
Sort: