Feature · Platform

Triggers

Agent can start work on your own Claude routine or ChatGPT Workspace Agent while you are away. You save its trigger in Agent.

Last changed

Generated from commit be57775 ·

How it works

How it works

  1. Add the Agent connector in Claude or the Agent app in ChatGPT. See Use Agent from Claude, ChatGPT or Codex.
  2. Create a Claude routine, or a ChatGPT Workspace Agent (Business and Enterprise), with the Agent connector and the setup text Agent gives you.
  3. Copy its trigger address and token. Select Save a trigger on Triggers.
  4. Turn on Let the platform fire it for my work.

Agent then fires the routine for your own work items. The routine reads the brief through the connector and reports the result.

Limits and safety

  • Only you see, fire or change your triggers.
  • The token is sealed in the vault and sent only to the address you saved.
  • You set how often it may fire in an hour and in a day. The vendor's own limits apply too.
  • An admin can turn triggers off for the organization on Connections.

From the help article Background runs on your own plan, checked against the product on .

What you can do

The operations this feature's screens call. Each one is POST /api/<name>, and the badge says who may call it.

  • listVendorTriggers

    ViewerNo API tokens

    Lists vendor triggers.

    Types: EmptyRequest returns ListResponse<VendorTriggerDto>

  • listConnectorRuns

    Viewer

    Lists connector runs.

    Types: ListConnectorRunsRequest returns PageResponse<ConnectorRunDto>

  • getPlanUsage

    ViewerNo API tokens

    Gets plan usage.

    Types: GetPlanUsageRequest returns PlanUsageDto

  • deleteVendorTrigger

    ViewerNo API tokens

    Deletes the vendor trigger.

    Types: VendorTriggerIdRequest returns OkResponse

  • saveVendorTrigger

    MemberNo API tokens

    Saves the vendor trigger.

    Types: SaveVendorTriggerRequest returns VendorTriggerDto

  • listMembers

    Viewer

    Lists members.

    Types: EmptyRequest returns ListMembersResponse

Screens

What it records

The feature writes these events to the audit log, the permanent record of what happened.

  • Connector run reported
  • Connector run started
  • Policy changed
  • Vendor trigger fired
  • Vendor trigger removed
  • Vendor trigger saved

Generated from code at commit be57775 ·

Turn the numbers into shipped work.

Agent runs these choices for you: a persistent AI worker with memory and rules, on your Claude and Codex subscriptions.