Anthropic launched Claude Managed Agents last month, greatly simplifying the work required to build and deploy cloud-hosted AI agents. This week, Claude Managed Agents are becoming more capable with three new features.

Anthropic releases dreaming, outcomes, and multiagent orchestration for Claude Managed Agents

The first new feature is called dreaming, which Anthropic classifies as a research preview. Anthropic says dreaming extends Claude’s memory capabilities “by reviewing past sessions to find patterns and help agents self-improve.”

Dreaming is a scheduled process that reviews your agent sessions and memory stores, extracts patterns, and curates memories so your agents improve over time. You decide how much control you want: dreaming can update memory automatically, or you can review changes before they land.

Anthropic describes how memory and dreaming work together to improve Claude Managed Agents:

Together, memory and dreaming form a robust memory system for self-improving agents. Memory lets each agent capture what it learns as it works. Dreaming refines that memory between sessions, pulling shared learnings across agents and keeping it up-to-date.

Meanwhile, outcomes is a new Claude Managed Agents feature that lets you explain what defines a successful result for the agent to accomplish.

With outcomes, you write a rubric describing what success looks like and the agent works toward it. A separate grader evaluates the output against your criteria in its own context window, so it isn’t influenced by the agent’s reasoning. When something isn’t right, the grader pinpoints what needs to change and the agent takes another pass. […]

You can also now define an outcome, let the agent run, and get notified by a webhook when it’s done.

Lastly, there’s multiagent orchestration, a new Claude Managed Agent tool that “lets a lead agent break the job into pieces and delegate each one to a specialist with its own model, prompt, and tools.”

For example, a lead agent can run an investigation while subagents fan out through deploy history, error logs, metrics, and support tickets.

These specialists work in parallel on a shared filesystem and contribute to the lead agent’s overall context. The lead agent can check back in with other agents mid-workflow because events are persistent and every agent remembers what it’s done.

Anthropic describes how Claude Managed Agents are already being used by companies like Netflix, which has already deployed multiagent orchestration for its platform team.

You can learn more about Claude Managed Agents and the three new features launching this week from Anthropic.

FTC: We use income earning auto affiliate links. More.