Anthropic adds dreaming, outcomes, multiagent orchestration to Claude Managed Agents

Anthropic adds dreaming for cross-session learning, outcomes for rubric grading, and multiagent orchestration for parallel tasks to Claude Managed Agents in research preview.

Anthropic launched an update to Claude Managed Agents with dreaming for cross-session learning in research preview. It adds outcomes for rubric-driven grading and full multiagent orchestration to run parallel tasks. Agents can now persist knowledge and collaborate on workflows.