Carousel Studio

ClaudeDevs

@ClaudeDevs

In Claude Managed Agents, we’ve added multiagent orchestration, an outcomes loop for rubric-driven self-improvement, dreaming for self-learning, & webhooks.

VIDEO

Apply Image

ClaudeDevs

@ClaudeDevs

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. <a target="_blank" href="https://platform.claude.com/docs/en/managed-agents/multi-agent" color="blue">platform.claude.com/docs/en/manage…</a>

ClaudeDevs

@ClaudeDevs

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. <a target="_blank" href="https://platform.claude.com/docs/en/managed-agents/define-outcomes" color="blue">platform.claude.com/docs/en/manage…</a>

ClaudeDevs

@ClaudeDevs

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. <a target="_blank" href="https://platform.claude.com/docs/en/managed-agents/webhooks#supported-event-types" color="blue">platform.claude.com/docs/en/manage…</a>

ClaudeDevs

@ClaudeDevs

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. <a target="_blank" href="https://platform.claude.com/docs/en/managed-agents/dreams" color="blue">platform.claude.com/docs/en/manage…</a>

ClaudeDevs

@ClaudeDevs

To get started with any of these features, try our /claude-api skill in Claude Code or the OSS repo: <a target="_blank" href="https://github.com/anthropics/skills/tree/main/skills/claude-api" color="blue">github.com/anthropics/ski…</a>