Remote AI Agent action
Hands a task to a connected Brightspot CMS, whose own AI agent does the work with that CMS's tools. In the action picker it is Remote AI Agent, under AI Actions.
It is not the built-in AI Agent action. That one runs the agent here, on the automation server, drawing tools from whatever MCP servers you give it—so it can combine tools from several systems in one run. This one delegates the whole turn to one CMS's agent. Use it when the task belongs entirely to that CMS.
Fields
| Field | Required | Description |
|---|---|---|
| Connection | Yes | The Brightspot connection whose agent runs the task. |
| Persona | No | An author persona from the connected CMS whose writing style the agent adopts. |
| Prompt | Yes | The natural-language task for the agent. Accepts variables, so it can work on the trigger's data and earlier results. |
| Payload Type | No | An output shape the agent populates as structured data alongside its message—a Content Type, using an existing content type's fields, or a Custom Shape whose fields you define here. |
| Human in the Loop | No | Opt-in. Set it to let the agent pause and ask a person before finishing, and choose the Providers the question is pushed to—for example Slack or Microsoft Teams. Left unset, the agent must finish on its own. |
The node's Description, on its Display tab, falls back to the start of the prompt when you leave it blank.
Pausing for a person
With Human in the Loop set, the agent can stop mid-task to ask a question—a confirmation, a choice among options, or a piece of missing detail. The step waits, the question is delivered to the providers you picked, and the agent resumes with the answer once someone gives it. Every request is also answerable from the approvals inbox, whichever providers are configured.
Output
| Field | Description |
|---|---|
message | The agent's text response. |
payload | The structured result, when a payload type is set. |