- 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
We understand the risks associated with using LLM-based applications with business data, and we have implemented multiple safeguards to ensure compliance and security.
-
Admin-controlled Autopilot functions
All Autopilot capabilities can be configured by admins through the AI Trust Layer. Admins can enable, disable, or modify LLM settings as needed.
-
Private, browser-local conversations
Individual conversations persist only in the user’s local browser and are unique to that user. No other user can view these conversations, and they are not stored in the backend. Users may delete them at any time.
-
Governed access to traces
Agent traces are governed at the AI Trust Layer. Trace summaries are generated on the fly by the LLM and are not stored outside the conversation. A user can view a trace summary only if they have access to the corresponding task.
-
Protection against inappropriate or harmful prompts
NSFW, unrelated, or destructive prompts are explicitly restricted. Users are prevented from performing such actions.
-
Configurable tools and prompts
All tools and prompt capabilities can be enabled or disabled at the Autopilot settings level.
