Claude Managed Agents
Anthropic-managed agents for Claude workflows.
Anthropic's managed-agent offering for building and running Claude-powered agents that can orchestrate multi-step tasks and tool use.
Recent stories
Anthropic published Claude Managed Agents examples for long-running production agents. The patterns cover outcome rubrics, self-correction, and sharing sandbox context between agents.
ClaudeDevs reports Sonnet 5 with a Fable 5 advisor reached ~92% of Fable 5's SWE-bench Pro score at ~63% of the price. Other builders route implementation to Sonnet, Codex, GPT-5.5, or GLM workers.
Anthropic opened scheduled deployments and environment-variable vaults in Claude Managed Agents public beta, and Dynamic Workflows is now generally available in Claude Code. The update adds cron-style jobs, secret injection, and deeper parallel orchestration for long-running agents.
Anthropic added self-hosted sandboxes in public beta and MCP tunnels in research preview to Claude Managed Agents. Use the new options to keep agent execution inside your perimeter or private cloud and reach internal MCP servers without public exposure.
Anthropic added Dreaming in research preview plus public-beta Outcomes, multiagent orchestration, and webhooks to Claude Managed Agents. Teams should try the new grader loops and shared-container sub-agents if they want more control over long-running agent work.
Anthropic released ready-to-run finance templates for pitchbooks, valuation reviews, KYC, and month-end close across Cowork, Claude Code, and Managed Agents. Use them to start with bundled connectors, skills, and subagents instead of building each workflow from scratch.
Anthropic put memory into public beta for Claude Managed Agents, storing retained context as files developers can export and edit. The change lets agent state persist across sessions without a separate memory service.