You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
improvement(docs): drop the preview-gated slack_app page, document managed_agent
- slack_oauth is reachable only through the preview-gated slack_v2 block, so
documenting it published an unreleased surface under its own slack_app page.
Triggers whose every hosting block sets `preview: true` are now excluded from
the docs and the icon map. Triggers no block claims are untouched, so
standalone webhook providers keep their pages.
- Adds the MANUAL-CONTENT intro to managed_agent.mdx, matching the other
integration pages. Verified it survives a regen.
Copy file name to clipboardExpand all lines: apps/docs/content/docs/en/integrations/managed_agent.mdx
+16Lines changed: 16 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -10,6 +10,22 @@ import { BlockInfoCard } from "@/components/ui/block-info-card"
10
10
color="#DA7756"
11
11
/>
12
12
13
+
{/* MANUAL-CONTENT-START:intro */}
14
+
[Claude Managed Agents](https://www.anthropic.com/) 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.
15
+
16
+
With Claude Managed Agents, you can:
17
+
18
+
-**Run a hosted agent**: Send a message to an agent in your Claude workspace and get its final response back
19
+
-**Pick the environment**: Choose the agent and the environment it runs in, so the same workflow can target development or production
20
+
-**Attach credential vaults**: Give the agent scoped access to the credentials it needs for the run
21
+
-**Use a memory store**: Connect a memory store with read or write access and pass instructions for how the agent should use it
22
+
-**Send files**: Attach files to the run for the agent to work with
23
+
-**Tag runs with metadata**: Add key-value tags so runs can be traced and grouped later
24
+
25
+
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.
26
+
{/* MANUAL-CONTENT-END */}
27
+
28
+
13
29
## Usage Instructions
14
30
15
31
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.
0 commit comments