wiki / raw / anthropic-claude-managed-agents-overview-2026
# Core concepts
loading…
Original source: https://platform.claude.com/docs/en/managed-agents/overview SHA256: 85e7cc25595bea746e6752d361db13b58020d159237d4fe11cdef2fc120bc816
Copy page
Anthropic offers two ways to build with Claude, each suited to different use cases:
| Messages API | Claude Managed Agents | |
|---|---|---|
| What it is | Direct model prompting access | Pre-built, configurable agent harness that runs in managed infrastructure |
| Best for | Custom agent loops and fine-grained control | Long-running tasks and asynchronous work |
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 run code securely. The harness supports built-in prompt caching, compaction, and other performance optimizations for high-quality, efficient agent outputs. To build your own agent loop with direct model access instead, see Using the Messages API.
Create your first agent session
Create a session and send your first event
Event types, rate limits, CLI flags, and other lookup tables
Core concepts
Claude Managed Agents is built around four concepts:
| Concept | Description |
|---|---|
| Agent | The model, system prompt, tools, MCP servers, and skills |
| Environment | Configuration for where sessions run: an Anthropic-managed cloud sandbox, or a self-hosted sandbox on your own infrastructure |
| Session | A running agent instance within an environment, performing a specific task and generating outputs |
| Events | Messages exchanged between your application and the agent (user turns, tool results, status updates) |
How it works
- 1
Create an agent
Define the model, system prompt, tools, MCP servers, and skills. Create the agent once and reference it by ID across sessions.
- 2
Create an environment
Configure where the agent runs: a cloud sandbox, or a self-hosted sandbox on your own infrastructure.
- 3
Start a session
Launch a session that references your agent and environment configuration.
- 4
Send events and stream responses
Send user messages as events. Claude autonomously runs tools and streams back results through server-sent events (SSE). Event history is persisted server-side and can be fetched in full.
- 5
Steer or interrupt
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 minutes or hours with multiple tool calls
- Cloud infrastructure: Secure sandboxes with pre-installed packages and network access
- Self-hosted execution: Sandboxes on infrastructure you control for compliance or data-residency requirements
- Minimal infrastructure: No need to build your own agent loop, sandbox, or tool execution layer
- Stateful sessions: Persistent filesystems and conversation history across multiple interactions
- Scheduled execution: Recurring agent runs on a cron schedule through scheduled deployments
Supported tools
Claude Managed Agents gives Claude access to a set of built-in tools:
- Bash: Run shell commands in the sandbox
- File operations: Read, write, edit, glob, and grep files in the sandbox
- Web search and fetch: Search the web and retrieve content from URLs, optionally restricted to an allowlist or blocklist of domains
- MCP servers: Connect to external tool providers
See Tools for the full list and configuration options.
Beta access
To get started, you need:
- A Claude API key
- The
managed-agents-2026-04-01beta header on all requests - Access to Claude Managed Agents (enabled by default for all API accounts)
Within the beta, MCP tunnels and dreaming are in a more limited research preview. Request access to enable them.
Claude Managed Agents is stateful by design: sessions are long-running, resume cleanly after pauses, and store conversation history, sandbox state, and outputs server-side. Because of this, Managed Agents is not currently eligible for Zero Data Retention or HIPAA Business Associate Agreement (BAA) coverage. You retain control over this data: you can delete sessions, and separately delete any files you uploaded, at any time through the API. For eligibility across all features, see API and data retention.
See Rate limits and Branding guidelines in the reference.
Was this page helpful?
Claude Managed Agents overview/
Core concepts
Ask Docs