Agents
Anthropic Promotes Outcomes and Multi-Agent Orchestration to Public Beta in Claude Managed Agents
Alongside dreaming, Anthropic moved two previously experimental Managed Agents features into public beta: 'outcomes' (specify a goal and run an agent in a loop until achieved, comparable to Codex's /goals) and multi-agent orchestration (a coordinator agent that spins up subagents in parallel, baked into the platform). Webhooks for session and vault lifecycle events were also added, enabling event-driven agent architectures.
Source
↳ Follow the thread