Claude Managed Agents Overview

Summary

Anthropic offers two ways to build with Claude, each suited to different use cases: Messages APIClaude Managed AgentsWhat it isDirect model prompting accessPre-built, configurable agent harness that runs in managed infrastructureBest forCustom agent loops and fine-grained controlLong-running tasks and asynchronous workLearn moreMessages API docsClaude Managed Agents docs Claude Managed Agents provides the harness and infrastructure for running Claude as an autonomous agent. Instead of building your own agent loop, tool execution, and runtime, you get a fully managed environment where Claude can read files, run commands, browse the web, and execute code securely. The harness supports built in prompt caching, compaction, and other performance optimizations for high quality, efficient agent outputs. Claude Managed Agents is built around four concepts: ConceptDescriptionAgentThe model, system prompt, tools, MCP servers, and skillsEnvironmentA configured container template (packages, network access)SessionA running agent instance within an environment, performing a specific task and generating outputsEventsMessages exchanged between your application and the agent (user turns, tool results, status updates) Define the model, system prompt, tools, MCP servers, and skills. Create the agent once and reference it by ID across sessions.Configure a cloud container with pre-installed packages (Python, Node.js, Go, etc.), network access rules, and mounted files.Launch a session that references your agent and environment configuration.4Send events and stream responsesSend user messages as events. Claude autonomously executes tools and streams back results via server-sent events (SSE). Event history is persisted server-side and can be fetched in full.Send additional user events to guide the agent mid-execution, or interrupt it to change direction. When to use Claude Managed Agents Claude Managed Agents is best for workloads that need: Long-running execution - Tasks that run for minu...