What Are Managed Agents
A configurable agent harness on managed infrastructure. It can reason and use enabled tools, but authority, safety, and business correctness remain your responsibility.
Source: Anthropic's Managed Agents overview. All Managed Agents endpoints require managed-agents-2026-04-01; memory-store endpoints currently use a separate header. Beta behavior may change.
4 Core Concepts
The API is organized around four resources. Treat Agent and Environment definitions as governed configuration, and bind every Session to an explicit version and trust boundary.
How It Flows
Your application selects a tested Agent version and Environment, starts a Session, sends an event, and observes the event stream. It must also authorize tools, handle approvals, interrupt unsafe work, and validate outputs.
What “Managed” Does Not Mean
The service reduces harness and runtime work. It does not certify a workflow, authorize business actions, or remove application responsibilities.
always_allow; safe behavior is not automatic.Messages API vs Managed Agents
If you've used Claude's Messages API before, here's what changes.
| Feature | Messages API | Managed Agents |
|---|---|---|
| Agent loop | You design and host it | Managed harness |
| Execution | Your infrastructure and isolation | Cloud or self-hosted sandbox |
| Files and commands | You implement any tools | Available only when configured |
| Tool authorization | Your application enforces it | Your policies/application enforce it |
| State | You choose and persist it | Session event history and filesystem |
| Observability | You instrument it | Event stream plus your logs and alerts |
| Long-running work | Possible with your orchestration | Designed for asynchronous sessions |
| Production safety | Requires your threat model, evaluation, access controls, approvals, monitoring, and incident plan | |
When to Use Managed Agents
Not every task needs an agent. Here's when they make sense.