AI Desktop Actions Execution workspace
Summarize
Summary of AI Desktop Actions Execution workspace
The AI Desktop Actions Execution workspace in ServiceNow enables you to test, run, and monitor desktop automations in a virtual environment. It provides visibility into how your automations interact with desktop applications, including managing scenarios that require human input. The workspace launches automatically when you test or run desktop actions and operates in isolation, allowing you to continue other desktop work without interference.
Show less
Access to this workspace is role-based: users with the AI Agent Admin (snaia.admin) role can create and test desktop actions, triggering the workspace, while users with the Now Assist panel user (nowassistpaneluser) role can run automations via the Now Assist panel, which also launches the workspace automatically.
Important: Avoid running the Execution workspace simultaneously with RPA Attended Desktop mode to prevent conflicts.
Key Features
- Desktop-in-Desktop (DiD) mode: A virtual desktop environment where automations run and can be monitored, showing interaction with desktop apps.
- Step in/Step out controls: Allows manual intervention by stepping into the automation to provide input (e.g., OTP, CAPTCHA) and then stepping out to resume automated execution. Automations must be designed to wait for user input when needed.
- Single execution: Only one automation can run at a time within the workspace, ensuring clear, isolated execution sessions.
- Smart sizing: Automatically adjusts the desktop session display for optimal visibility across different screen resolutions and scaling settings, with options to fit the window or view at original resolution.
Execution Statuses
The workspace provides clear execution status updates to track automation progress:
- Ready: Waiting to start execution.
- Initiated: Execution plan received and setup in progress (initial launch may take longer).
- Running: Automation is actively executing steps.
- Success: Automation completed successfully, with results displayed in the Now Assist panel.
- Failed: Execution encountered an error and did not complete.
- Canceled: Execution was manually stopped by the user.
Practical Benefits for ServiceNow Customers
This workspace empowers ServiceNow users to confidently develop and validate desktop automations by providing a controlled environment to test execution and handle manual inputs. Monitoring and status indicators help quickly identify and resolve issues, while smart sizing ensures usability across devices. Integration with user roles streamlines workflow by launching the workspace automatically when needed, enhancing efficiency and reliability of desktop automation deployments.
Execution workspace enables you to test, run, and monitor your desktop actions. It enables you to observe how your automations interact with desktop applications, including handling situations where human input is needed.
- When users with the AI Agent Admin (sn_aia.admin) role sign in from their desktop, they can access the Home page and Design workspace to create desktop actions. When they test a desktop action, the Execution workspace launches automatically.
- When users with the Now Assist panel user (now_assist_panel_user) role trigger an automation from the Now Assist panel, the Execution workspace launches automatically to run the desktop action.
You don’t open the Execution workspace directly. It launches automatically when you test or run a desktop action.
This session acts as a virtual environment where the automations run in isolation. While desktop actions run in the Execution workspace, you can continue working on other desktop tasks.
To avoid conflicts, do not run the AI Desktop Actions Execution workspace and RPA Attended Desktop mode at the same time.
Execution workspace features
Execution workspace offers the following features:
- Desktop-in-Desktop (DiD) mode
- A virtual environment where your automation executes. You can monitor the execution of your desktop actions and how they interact with desktop applications.
- Step in/Step out
- You can manually take control to provide an input by selecting Step in. Once done, you can leave the control by selecting Step out.Note:If your automation requires manual inputs, such as entering an OTP or CAPTCHA, you must provide instructions the AI Agent to wait for user input during execution. Otherwise, the automation cannot proceed.
- Single execution
- The system supports one automation execution at a time within the workspace.
- Smart sizing
- Smart Sizing enables your desktop sessions automatically adapt to your display. This ensures each captured desktop session is fully visible, readable, and usable, regardless of the device resolution and
scaling.
Fit to window: Automatically scales the desktop session to fit within the Execution workspace while keeping it fully visible and readable.
Original resolution: Displays the desktop session at its original resolution. Scroll bars appear if the desktop session is larger than the Execution workspace.
Execution statuses
Execution workspace shows the following statuses throughout the execution process.
| Execution status | Description |
|---|---|
| Ready | Automation execution is ready to be initiated. The workspace is waiting for instructions from AI Agent Studio. |
| Initiated | Automation execution is initiated. The workspace has received the execution plan from AI Agent Studio. Note: When you launch Execution workspace for the first time, it takes longer to move to the Running state because it is setting things up for you. |
| Running | Automation execution is running. The workspace executes the steps defined in the desktop actions. |
| Success | Automation execution is completed successfully. The workspace executed the steps defined in the desktop actions and the outcome is shown on the Now Assist panel, such as the automation execution completed successfully and incident created successfully. |
| Failed | Automation execution is failed. The workspace couldn't execute the automation due to an error. |
| Canceled | Automation execution is canceled. The user canceled the execution manually. |