// Track

Claude Managed Agents

Production Agent Infrastructure from Anthropic

Anthropic's hosted agent harness for async production pipelines — define agents, provision environments, stream session events, orchestrate multi-agent workflows, and apply production-grade versioning and cost discipline.

Recommended: Complete Claude Code Operations first

8 lessons~70 min total

Lessons are shown in recommended order. Complete them in sequence for the best experience — or jump to any lesson.

Lesson 304·8 min read

From Code to Cloud — Choosing Managed Agents

Managed Agents is not a better Claude Code — it is a different infrastructure path for a specific class of production workloads. Know the decision matrix before you build.

Lesson 305·9 min read

Defining Your Agent

An agent definition is the contract between your requirements and Anthropic's infrastructure — every field is a decision with operational consequences.

Lesson 306·8 min read

Environments and Containers

The execution environment defines what your agent can do and what it can reach — configure it minimally, deliberately, and with security as a first principle.

Lesson 307·9 min read

Sessions and Event Streaming

Sessions are the runtime unit of Managed Agents — understanding session lifecycle, event types, and how to consume them correctly is the foundation of reliable production integrations.

Lesson 308·9 min read

Multiagent Orchestration

Orchestrating multiple Managed Agents requires understanding thread isolation, the callable_agents pattern, and when specialization actually earns its coordination overhead.

Lesson 309·9 min read

Tool Confirmation and Custom Tools

Giving agents tools is giving them the ability to take actions in the world — permission policies and custom tool design are how you control exactly what actions they can take.

Lesson 310·8 min read

Memory in Managed Agents

Managed Agents does not have automatic memory — the agent must explicitly write and query memories, and understanding what is and is not persisted is critical for long-running pipelines.

Lesson 311·10 min read

Production Patterns for Managed Agents

Shipping a Managed Agents pipeline to production requires versioning discipline, health verification, cost modeling, and a tested migration path — not just a working prototype.