# Claude Managed Agents Beta platform for custom long-running agents with managed execution and persistent sessions. Canonical profile: https://ki-agentenkompass.de/en/agents/claude-managed-agents/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-10-19 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Developer platform in beta; a distinct offering alongside Claude Code and Cowork. - Provider: Anthropic - Product family: Claude Managed Agents - Profile type: Agent platform - Environment: Managed cloud; optional self-hosted sandbox - Connections: Long-running tasks, Sessions, Tools, MCP, Scheduling - Setup: Requires an API account, agent configuration and beta header. - Pricing model: USD 0.08 per running session-hour plus model usage. ## Key features ### Long-running tasks Run multi-step tasks asynchronously. Source: https://platform.claude.com/docs/en/managed-agents/overview ### Sessions Retain files and history across interactions. Source: https://platform.claude.com/docs/en/managed-agents/overview ### Tools Use files, shell and web tools. Source: https://platform.claude.com/docs/en/managed-agents/overview ### MCP Connect custom services through MCP. Source: https://platform.claude.com/docs/en/managed-agents/overview ### Scheduling Configure recurring runs. Source: https://platform.claude.com/docs/en/managed-agents/overview ## Example workflows ### Example task 1 - Your input: Analyze approved documents in a background task. - Possible result: A draft for expert review. - What to check: Check inputs, output and performed actions. ### Example task 2 - Your input: Prepare a recurring repository report. - Possible result: A draft for expert review. - What to check: Check inputs, output and performed actions. ## Requirements and limits ### Setup Requirement: Requires an API account, agent configuration and beta header. Source: https://platform.claude.com/docs/en/managed-agents/overview ### Product boundaries Limitation: Beta terms apply; a self-hosted sandbox still uses the managed platform. Source: https://platform.claude.com/docs/en/managed-agents/overview ### Output quality Not yet confirmed: Success rates and German-language operation have not been tested here. Source: https://platform.claude.com/docs/en/managed-agents/overview ## A good fit if … - you want to build your own agents on the Claude API and can plan for an API key and development effort - tasks should run for hours and recur on a cron schedule with run history and webhooks - you want sandboxes on your own infrastructure for compliance or data residency reasons ## Less suitable if … - you need zero data retention or a HIPAA BAA; neither applies to Managed Agents at present - you expect a ready-made interface without coding; access is through the API, SDKs and a beta header Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Own models only You set a Claude model per agent, and the docs list only Claude models as supported. You need a Claude API key and can also use the service through Claude Platform on AWS or Claude Models on Google Cloud. The whole offering is still in beta. - Model families named: Anthropic (Claude) - Model choice: You choose - Your own API key: Yes - Router or custom endpoint: No - Local models: No Documented · Sources accessed on: 2026-11-05 - [Claude Managed Agents: Overview](https://platform.claude.com/docs/en/managed-agents/overview) ## Europe & regional availability Provider sources reviewed again. This assessment applies to the access described here. Reviewed scope: Product access and explicitly stated exceptions Reviewed on: 2026-10-19 ### API beta also covers supported European countries With requirements Germany is on the Claude API country list. Managed Agents is enabled by default for API accounts and requires an API key and beta header. MCP tunnels and dreaming require separate preview access. Region covered: Germany; other countries according to the provider list Documented reason: The sources state access conditions; they do not show EU regulation as a cause. Official source: https://platform.claude.com/docs/en/managed-agents/overview Official source: https://platform.claude.com/docs/en/api/supported-regions ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Claude Managed Agents (beta) via the Claude API with an Anthropic cloud sandbox Sources reviewed: 2026-11-05 ### Account used Documented: Requests use a Claude API key from the Console and the beta header. For MCP services that need sign-in, a session references a vault holding stored OAuth credentials. On Claude Platform on AWS each scheduled session runs as an IAM role in your AWS account. Evidence: https://platform.claude.com/docs/en/managed-agents/overview Evidence: https://platform.claude.com/docs/en/managed-agents/sessions Evidence: https://platform.claude.com/docs/en/managed-agents/scheduled-deployments ### Admin approval Documented with conditions: Access is enabled by default for all API accounts. Per tool you can set whether calls run without confirmation, require confirmation or are evaluated individually by the server. An inference geography set for a session is validated against the workspace's allowed geographies. Evidence: https://platform.claude.com/docs/en/managed-agents/overview Evidence: https://platform.claude.com/docs/en/managed-agents/tools Evidence: https://platform.claude.com/docs/en/managed-agents/sessions ### Data access & team sharing Documented with conditions: The agent reads and writes files in its sandbox, runs commands and calls web and MCP servers as far as you enable the tools; web access can be limited to domains. Uploaded files, GitHub, memory stores and vaults are optional resources. Team sharing is not described. Evidence: https://platform.claude.com/docs/en/managed-agents/overview Evidence: https://platform.claude.com/docs/en/managed-agents/scheduled-deployments ## Prices and included usage Pricing checked: 2026-10-19 USD 0.08 per running session-hour plus model usage. Billing depends on plan, usage and setup. Pricing details: https://platform.claude.com/docs/en/about-claude/pricing ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Managed cloud sandbox in beta; optionally your own sandbox Sources reviewed: 2026-11-05 ### Files and working state Documented: Sessions keep conversation history, sandbox state and outputs server-side and resume after pauses. Transcripts persist until you delete them; zero data retention does not apply to Managed Agents. Evidence: https://platform.claude.com/docs/en/managed-agents/overview ### Sign-ins Documented: For MCP credentials stored in a vault, Anthropic handles token refresh according to the documentation. If a vault is archived at a scheduled trigger, the run is recorded as failed and the deployment is paused automatically. The page gives no validity periods. Evidence: https://platform.claude.com/docs/en/managed-agents/sessions Evidence: https://platform.claude.com/docs/en/managed-agents/scheduled-deployments ### Starting further runs Documented: Sessions start through the API, manually via a deployment's run endpoint or by cron schedule (time zone configurable, up to 1,000 deployments per organisation). While running you can steer or interrupt the agent. Evidence: https://platform.claude.com/docs/en/managed-agents/scheduled-deployments Evidence: https://platform.claude.com/docs/en/managed-agents/overview ### Human intervention Documented with conditions: A permission policy can require confirmation for tool calls; the built-in tools are otherwise enabled. For custom tools the session pauses until your application returns the result. Evidence: https://platform.claude.com/docs/en/managed-agents/tools ### Detecting errors Documented: Each trigger attempt of a deployment creates a run record that can be filtered for errors. Session progress and outcomes also arrive through the event stream and webhooks. Evidence: https://platform.claude.com/docs/en/managed-agents/scheduled-deployments ### Resuming after failures Documented: A session that reaches its budget pauses and goes idle. For unrecoverable errors such as an archived environment or vault the deployment is paused until you update it; after unpausing, missed triggers are not backfilled, and a rate-limited session start is not retried until the next scheduled time. Evidence: https://platform.claude.com/docs/en/managed-agents/scheduled-deployments Evidence: https://platform.claude.com/docs/en/managed-agents/sessions ### Editorial assessment Run records, webhooks and pause logic are documented. You have to set up permission policies, budgets and the review of failed runs yourself. ## Memory and conversation continuity Scope: Managed Agents with memory stores (beta) Sources accessed: 2026-11-04 Versioned text stores attached to selected sessions and used through file tools. ### Storage and scope Documented: Memory stores are workspace-scoped collections of text documents mounted as session directories. Changes produce immutable versions. - [Using agent memory](https://platform.claude.com/docs/en/managed-agents/memory) - [Managed Agents overview](https://platform.claude.com/docs/en/managed-agents/overview) ### Selection and timing Documented: Agents read and write using file tools; mount guidance is automatically added to the system prompt. What is saved follows the task and agent instructions. - [Using agent memory](https://platform.claude.com/docs/en/managed-agents/memory) - [Managed Agents overview](https://platform.claude.com/docs/en/managed-agents/overview) ### Inspect, edit and delete Documented: API and Console support inspection and editing; APIs delete memories or entire stores. Historical content requires targeted redaction or deletion of the entire store. - [Using agent memory](https://platform.claude.com/docs/en/managed-agents/memory) - [Managed Agents overview](https://platform.claude.com/docs/en/managed-agents/overview) ### Agent and channel boundaries Documented: Stores can be attached and shared across sessions per user, team or project; read_only/read_write controls writes. - [Using agent memory](https://platform.claude.com/docs/en/managed-agents/memory) - [Managed Agents overview](https://platform.claude.com/docs/en/managed-agents/overview) ### Retrieval Partly documented: The agent receives the mount path, description and instructions and reads needed files. A preliminary semantic search index is not documented. - [Using agent memory](https://platform.claude.com/docs/en/managed-agents/memory) - [Managed Agents overview](https://platform.claude.com/docs/en/managed-agents/overview) ### Session reset and compaction Partly documented: New sessions start with fresh context; attached stores outlive sessions. Dreaming consolidates memory into a new store; active-conversation compaction is separate and not explained here. - [Using agent memory](https://platform.claude.com/docs/en/managed-agents/memory) - [Managed Agents overview](https://platform.claude.com/docs/en/managed-agents/overview) ## Context Beta terms apply; a self-hosted sandbox still uses the managed platform. Provider sources reviewed; examples are editorial suggestions. No hands-on test. ## Open points Requirements and limits, not yet confirmed: - Output quality ## Sources - https://platform.claude.com/docs/en/managed-agents/overview - https://platform.claude.com/docs/en/about-claude/pricing ## Provider Product and provider are documented through the linked original sources. - Operator: Anthropic - Organization: Provider - Website: https://platform.claude.com/docs/en/managed-agents/overview - Reviewed: 2026-10-19 - Provider source: https://platform.claude.com/docs/en/managed-agents/overview - Provider source: https://platform.claude.com/docs/en/about-claude/pricing [Sources and method](https://ki-agentenkompass.de/en/sources/)