Anthropic Launches Claude Managed Agents: Dreams, Outcomes, Multiagent Orchestration
Anthropic
Announced at the Code with Claude SF event on May 6, Anthropic shipped three features for Claude Managed Agents. Dreams (research preview) reviews past session transcripts, deduplicates memories, and surfaces patterns across sessions for self-improving agents. Outcomes (public beta) lets developers define rubric-based evaluation criteria — a grader requests another attempt if output falls short, with reported gains of up to 10 percentage points on task success rates. Multiagent Orchestration (public beta) allows a lead agent to delegate sub-tasks to specialist sub-agents with their own models, prompts, and tools, all observable in Claude Console.
Why it matters
Dreams is the first production-facing self-improving memory mechanism accessible via API from a major lab. Combined with Outcomes' self-correction loop and parallel sub-agent delegation, these features push Claude Managed Agents toward long-horizon autonomous operation.
Importance: 4/5
Anthropic frontier lab; three significant API features — first production self-improving memory (Dreams), autonomous self-correction (Outcomes), and hierarchical multi-agent orchestration, all in one release.