How It Actually Works
Versioned agents, isolated session sandboxes, permission policies, networking, tools, and events — including the defaults you must change for a production candidate.
5-Step Lifecycle
A common lifecycle is: create a versioned Agent, create an Environment, start a Session, send and stream Events, then steer or interrupt. Your application must persist the IDs and tested versions it actually used.
Available Tool Categories
These capabilities can be configured; they are not a blanket entitlement. Disable tools a task does not need. The built-in agent toolset defaults to always_allow, while MCP toolsets default to always_ask.
The Sandbox
Each cloud session receives a fresh isolated Linux container. An Environment configuration may be reused, but sessions do not share that cloud sandbox. Self-hosting moves runtime hardening and isolation duties to you.
Control Checklist
Platform optimizations such as prompt caching and compaction do not replace explicit application controls.
always_ask for risky built-in and MCP actionsBeta Notice
anthropic-beta: managed-agents-2026-04-01Memory-store endpoints currently use
agent-memory-2026-07-22 instead. The SDK sets applicable beta headers automatically. The API and pricing may change. Managed Agents is stateful and, per the current overview, is not eligible for Zero Data Retention or HIPAA BAA coverage. Review privacy, retention, residency, contracts, and deletion requirements before using real data.Sources reviewed 31 Aug 2026: overview, cloud environments, permission policies, and self-hosted security model.