- Release notes Cloud Action Center
- Getting started
- Activities
- Designing long-running workflows
- Start Job And Get Reference
- Wait For Job And Resume
- Add Queue Item And Get Reference
- Wait For Queue Item And Resume
- Wait For Form Task And Resume
- Resume After Delay
- Assign Tasks
- Create External Task
- Wait For External Task And Resume
- Complete Task
- Forward Task
- Get Form Tasks
- Get Task Data
- Get App Tasks
- Add Task Comment
- Update Task Labels
- Create App Task
- Wait For App Task And Resume
- Configure task timer
- Actions
- Autopilot in Action Center - Preview
- Processes
- Notifications
- Audit
Action Center
To see the available tools, access the Settings > Available Tools > Framework Tools section.
The steps performed by an agent are recorded as traces. Autopilot summarizes these traces and makes them available for review.
When you select the "Why was the task escalated?" system prompt, or if you type "Why is this task here?", Autopilot triggers the Get Execution Trace call and presents the summarized trace information.
The summary focuses on explaining why the escalation occurred. It provides the following details:
- the agent involved
- the tools used
- any relevant context-grounding documents
The trace and its summary provide a consolidated view of the steps the Agent or Maestro process took before escalating. You can now give both objective and subjective feedback on the trace.
To make the Submit Trace Feedback call and store your feedback in Agent memory, write "Provide feedback on the task that …". The feedback can be as detailed or as objective as you prefer. It is fed back into Traces and used to improve Agent Memory in future runs.
