In Claude Managed Agents, we’ve added multiagent orchestration, an outcomes loop for rubric-driven self-improvement, dreaming for self-learning, & webhooks.
VIDEO
Multi-agent orchestration enables task delegation to specialized sub-agents.
Each sub-agent has its own context window, but they share a container + filesystem to coordinate work.
platform.claude.com/docs/en/manage…
Each sub-agent has its own context window, but they share a container + filesystem to coordinate work.
platform.claude.com/docs/en/manage…
Agents can self-improve using a rubric that describes task completion.
A dedicated grader sub-agent uses the rubric to evaluate any work done and returns feedback for the next iteration.
platform.claude.com/docs/en/manage…
A dedicated grader sub-agent uses the rubric to evaluate any work done and returns feedback for the next iteration.
platform.claude.com/docs/en/manage…
Agents can post updates to webhooks configured in your Claude workspace.
This removes the need to keep an SSE stream open or poll for completion.
platform.claude.com/docs/en/manage…
This removes the need to keep an SSE stream open or poll for completion.
platform.claude.com/docs/en/manage…
Agents write to memory in a session. Dreaming is a background process that reflects over many sessions to curate memories: it can edit them based on patterns, add new skills, or remove stale ones.
platform.claude.com/docs/en/manage…
platform.claude.com/docs/en/manage…
To get started with any of these features, try our /claude-api skill in Claude Code or the OSS repo:
github.com/anthropics/ski…
github.com/anthropics/ski…
Generated by Thread Navigator
Press ⌘ + S to quick-export