Claude Managed Agents

Claude Managed Agents are agents you build and host on the Claude Platform. Anthropic runs the agent loop, and the Claude Managed Agents block calls one from a Sim workflow.

With Claude Managed Agents, you can:

Run a hosted agent: Send a message to an agent in your Claude workspace and get its final response back
Pick the environment: Choose the agent and the environment it runs in, so the same workflow can target development or production
Attach credential vaults: Give the agent scoped access to the credentials it needs for the run
Use a memory store: Connect a memory store with read or write access and pass instructions for how the agent should use it
Send files: Attach files to the run for the agent to work with
Tag runs with metadata: Add key-value tags so runs can be traced and grouped later

In Sim, the Claude Managed Agents block lets a workflow hand work to an agent that lives on the Claude Platform instead of assembling the prompt, tools, and loop yourself. The block returns the agent's final text alongside its session ID and token counts, so you can chain the response into later blocks and track cost per run.

Usage Instructions

Invoke a Claude Platform Managed Agent from a workflow. Select a Claude Platform account, pick an agent and environment from that workspace, optionally attach vaults, a memory store, and files, and add metadata tags. Returns the assistant's final text.

Parameter	Type	Required	Description
`credential`	string	Yes	Claude Platform credential (Anthropic workspace API key) to run the agent with.
`agent`	string	Yes	Managed-agent id inside the linked Claude workspace.
`environment`	string	Yes	Environment id inside the linked Claude workspace.
`environmentType`	string	No	Environment execution model hint ('cloud' \| 'self_hosted'); the actual type is re-resolved server-side for routing.
`userMessage`	string	Yes	The user message to send to the Managed Agent.
`vaults`	array	No	Zero or more vault ids for MCP tool auth.
`vaultsAck`	boolean	No	Acknowledgement that the author may use the attached vaults.
`memoryStoreId`	string	No	Optional Agent Memory Store id.
`memoryAccess`	string	No	Memory store access mode: 'read_write' (default) or 'read_only'.
`memoryInstructions`	string	No	Per-attachment guidance for how the agent should use the memory store.
`files`	array	No	File attachments (cloud envs only), as [{fileId, mountPath?}].
`sessionParameters`	object	No	Key/value session metadata forwarded to the session.
`modelInput`	string	No	No description

Output

Parameter	Type	Description
`content`	string	Final assistant text from the Managed Agent session.
`sessionId`	string	Anthropic session id (for logs / linking).
`inputTokens`	number	Cumulative input tokens for the session.
`outputTokens`	number	Cumulative output tokens for the session.

Managed Agent Create Session

Create a Claude Platform Managed Agent session and return its id without waiting for a reply.

Input

Parameter	Type	Required	Description
`agent`	string	Yes	Managed-agent id inside the linked Claude workspace.
`environment`	string	Yes	Environment id inside the linked Claude workspace.
`environmentType`	string	No	Environment execution model hint ('cloud' \| 'self_hosted').
`userMessage`	string	No	Optional first message; seeds initial_events and starts the agent immediately.
`vaults`	array	No	Zero or more vault ids for MCP tool auth.
`vaultsAck`	boolean	No	Acknowledgement that the author may use the attached vaults.
`memoryStoreId`	string	No	Optional Agent Memory Store id.
`memoryAccess`	string	No	Memory store access mode: 'read_write' (default) or 'read_only'.
`memoryInstructions`	string	No	Per-attachment guidance for how the agent should use the memory store.
`files`	array	No	File attachments (cloud envs only), as [{fileId, mountPath?}].
`sessionParameters`	object	No	Key/value session metadata forwarded to the session.

Output

Parameter	Type	Description
`sessionId`	string	Anthropic session id (sesn_...).
`started`	boolean	True when a first message was seeded, so the agent is already running.

Managed Agent Send Message

Send a user message to an existing Claude Platform Managed Agent session.

Input

Parameter	Type	Required	Description
`userMessage`	string	Yes	The user message to send to the session.

Output

Parameter	Type	Description
`sessionId`	string	The session the message was sent to.
`sent`	boolean	True when the event was accepted by the API.

Managed Agent Get Session

Read a Managed Agent session: status, stop reason, token usage, metadata, and any tool calls awaiting approval.

Input

Parameter	Type	Required	Description

Output

Parameter	Type	Description
`sessionId`	string	The session that was read.
`status`	string	Session status — 'idle', 'running', 'rescheduling', or 'terminated'.
`stopReason`	string	Why the session last stopped, e.g. 'end_turn' or 'requires_action'.
`requiresAction`	boolean	True when the session is waiting on a tool confirmation or custom tool result. If this is true while pendingTools is empty, the session is blocked but the API named no blocking events — surface it rather than treating the session as done.
`pendingTools`	json	Blocking tool calls — [{id, eventType, kind, name, input}]. Route by kind: 'confirmation' ids go to Respond To Tool Confirmation, 'custom_tool_result' ids go to Respond To Custom Tool.
`metadata`	json	Session metadata.
`title`	string	Session title.
`inputTokens`	number	Cumulative input tokens.
`outputTokens`	number	Cumulative output tokens.

Managed Agent List Events

Read a Managed Agent session's event history and the agent's reply text.

Input

Parameter	Type	Required	Description
`eventTypes`	array	No	Optional event-type filter, e.g. ['agent.message']. Omit to return every event.
`limit`	number	No	Maximum events to return, keeping the most recent (default 500).

Output

Parameter	Type	Description
`sessionId`	string	The session that was read.
`events`	json	Session events, oldest first.
`count`	number	Number of events returned.
`assistantText`	string	Concatenated text of every persisted agent.message, in order.
`truncated`	boolean	True when the limit was hit and older events were dropped.

Managed Agent Update Session

Update a Managed Agent session's title or metadata.

Input

Parameter	Type	Required	Description
`title`	string	No	New session title.
`sessionParameters`	object	No	Replacement metadata map (replaces all stored metadata, not merged). Leaving it empty leaves the stored metadata unchanged — use clearMetadata to remove it.
`clearMetadata`	boolean	No	Removes all of the session's stored metadata. Overrides any map supplied above.

Output

Parameter	Type	Description
`sessionId`	string	The session that was updated.
`updated`	boolean	True when the update was accepted.
`metadata`	json	Metadata after the update.
`title`	string	Title after the update.

Managed Agent Interrupt Session

Stop a running Managed Agent session; it stays usable afterwards.

Input

Parameter	Type	Required	Description

Output

Parameter	Type	Description
`sessionId`	string	The session that was interrupted.
`interrupted`	boolean	True when the interrupt was accepted.

Managed Agent Respond To Tool Confirmation

Allow or deny the tool calls a Managed Agent session is waiting on before it can continue.

Input

Parameter	Type	Required	Description
`toolUseIds`	array	Yes	Blocking tool-use EVENT ids, from Get Session pendingTools[].id where kind is 'confirmation' (not toolu_ ids).
`decision`	string	Yes	'allow' to let the tools run, or 'deny' to reject them.
`denyMessage`	string	No	Reason surfaced to the agent. Only sent when the decision is deny.

Output

Parameter	Type	Description
`sessionId`	string	The session that was answered.
`decision`	string	The decision applied — 'allow' or 'deny'.
`confirmedToolUseIds`	json	The tool-use event ids that were answered.

Managed Agent Respond To Custom Tool

Return the result of a custom tool a Managed Agent session is waiting on so it can continue.

Input

Parameter	Type	Required	Description
`customToolUseId`	string	Yes	The custom tool-use EVENT id being answered, from Get Session pendingTools[].id where kind is 'custom_tool_result'.
`result`	string	Yes	The tool's output, returned to the agent as text.
`isError`	boolean	No	Mark the result as a failure so the agent can adjust its approach.

Output

Parameter	Type	Description
`sessionId`	string	The session that was answered.
`answeredToolUseId`	string	The custom tool-use event id that was answered.

Managed Agent Archive Session

Archive a Managed Agent session, preserving its history. Not reversible.

Input

Parameter	Type	Required	Description

Output

Parameter	Type	Description
`sessionId`	string	The session that was archived.
`archived`	boolean	True when the archive was accepted.

Managed Agent Delete Session

Permanently delete a Managed Agent session, its events, and its sandbox. Not reversible.

Input

Parameter	Type	Required	Description

Output

Parameter	Type	Description
`sessionId`	string	The session that was deleted.
`deleted`	boolean	True when the delete was accepted.

Claude Managed Agents

Usage Instructions

Actions

Managed Agent Run Session

Input

Output

Managed Agent Create Session

Input

Output

Managed Agent Send Message

Input

Output

Managed Agent Get Session

Input

Output

Managed Agent List Events

Input

Output

Managed Agent Update Session

Input

Output

Managed Agent Interrupt Session

Input

Output

Managed Agent Respond To Tool Confirmation

Input

Output

Managed Agent Respond To Custom Tool

Input

Output

Managed Agent Archive Session

Input

Output

Managed Agent Delete Session

Input

Output

On this page