Add a desktop action to an AI agent
Add a desktop action as a tool to an AI agent in AI Agent Studio so that AI agents can perform desktop actions for repetitive tasks.
Antes de Iniciar
Role required: sn_aia.admin
Procedimento
- Navigate to All > AI Agent Studio > Create and manage > AI agents.
-
Open the AI agent that you want to add a desktop action to.
For creating an AI agent, see Create an AI agent.
- Navigate to the Add tools and information step.
- In the Add tool drop-down list, select Desktop action.
-
On the form, fill in the fields.
Tabela 1. Add a desktop action form Fields Description Select a type of desktop action - UI block: These actions include UI interactions, such as clicking buttons, typing into text boxes, selecting from drop-down menus, and more.
Example: Filling in fields on a payroll application, updating inventory in a point-of-sale system, or submitting a request through a desktop insurance claims app.
- Non-UI blocks: These actions are prebuilt components that don’t interact with the UI, but run in the background. Non-UI block actions enable your AI agents to interact
with various applications and system components and offer prebuilt actions for common tasks, reducing the need for complex scripting.
Example: Reading data from Microsoft Excel, extracting emails from Microsoft Outlook, generating a PDF, compressing files into a ZIP, fetching records from a database, or sending a system notification.
Select a desktop action Desktop action that you want to add to the AI agent from the list. Nota:This field appears when UI block is selected as the type of desktop action.Select an application Select an application from the list to use the associated actions. The following applications are supported for non-UI block actions: - Microsoft Excel
- Microsoft Outlook
- Microsoft Word
- PowerShell Connector
- SQL
- SSH
- SystemAction
Nota:This field appears when Non-UI block is selected as the type of desktop action.Desktop action description Read-only. Description of the desktop action or application that you selected. Applications Read-only. Applications that this desktop action interacts with. Nota:This field appears when UI block is selected as the type of desktop action and a desktop action is selected from the list.Created by Read-only. User who created the desktop action. Nota:This field appears when UI block is selected as the type of desktop action and a desktop action is selected from the list.Last updated Read-only. Date when this desktop action was last updated. Nota:This field appears when UI block is selected as the type of desktop action and a desktop action is selected from the list.Inputs Read-only. Input parameters associated with this desktop action. Nota:This field appears when a desktop action or application is selected from the list.Outputs Read-only. Output parameters associated with this desktop action. Nota:This field appears when a desktop action or application is selected from the list.Name Name that you want to specify for your selected desktop action. Tool description Description of the desktop action tool and what it’s going to do to assist your AI agent. Nota:This description is sent to the large language model (LLM).Execution mode Mode of execution for your selected desktop action: - Supervised: Inputs from your live agent are required during the execution of this desktop action while the AI agent runs.
- Autonomous: Doesn't require any input from your live agent during the execution of this desktop action while the AI agent runs.
Display output Permission to display the output of the execution in the Now Assist panel or in Virtual Agent: - Yes
- No
Output transformation strategy Style for the LLM to present the results as it passes information between tools and to other agents. - None
- Concise
- Paragraph
- Verbose
- Custom
Processing message Message to display to users when the tool is running and action is completed in the Now Assist panel. - In-progress message: Describe the action that happens while this tool is running. This message is displayed to end users while the tool is running.
- Completion message: Describe the final action that’s completed. This message is displayed to end users once the tool finishes running.
- UI block: These actions include UI interactions, such as clicking buttons, typing into text boxes, selecting from drop-down menus, and more.
-
Select Add.
The desktop action is added in the Desktop actions list on the Add tools and information page.