Creating AI agents for AI Desktop Actions

  • Release version: Australia
  • Updated November 2, 2025
  • 2 minutes to read
    • Summarize
    Summarized using AI
    This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.

    Summary of Creating AI agents for AI Desktop Actions

    ServiceNow’s AI agents in AI Agent Studio enable customers to automate repetitive desktop and web tasks by mimicking human-like intelligence. These agents use large language model (LLM) instructions and tools to process natural language commands, generate execution plans, and autonomously or semi-autonomously run desktop actions across legacy systems, thick client applications, and web apps without APIs or backend integrations.

    Show full answer Show less

    AI agents translate user goals into executable desktop actions using metadata about capabilities, inputs, and outputs. They can coordinate subtasks, handle human input during execution, and collaborate with users when human judgment is needed. A default AI agent called the Web Automation Agent and its workflow are provided for adaptive web-based desktop actions when the AI Desktop Actions application is installed.

    Creating and Configuring AI Agents

    • Define agent specialty: Assign a clear name, description, role, and list of steps the AI agent must perform. Specify supported LLMs, enable third-party access if needed, and configure long-term memory. The LLM interprets the specialty based on your wording.
    • Add desktop action tools: Equip AI agents with specific desktop or web automation tools by adding defined or adaptive desktop actions. Clear tool names and descriptions help the AI agent select the right capabilities to complete tasks effectively.
    • Set security controls: Control user access through Access Control Lists (ACLs) determining who can discover or invoke the agent. Define what data the AI agent can access once invoked, ensuring secure and compliant operation.
    • Triggering and availability: AI agents for desktop actions must be manually triggered from the system hosting AI Desktop Actions as automatic trigger conditions are unsupported. You can activate agents for use in ServiceNow Otto for Virtual Agent and select channels where the AI agent can engage users.

    Practical Benefits for ServiceNow Customers

    • Automate complex, repetitive tasks spanning multiple legacy and modern applications without needing backend integrations.
    • Leverage natural language instructions to create flexible, intelligent automation workflows.
    • Integrate AI agents with conversational interfaces like Virtual Agent for interactive user engagement.
    • Maintain strong security controls over agent invocation and data access to meet enterprise compliance requirements.
    • Use default AI agents and workflows as starting points for adaptive web automation, accelerating deployment.

    Create an AI agent in AI Agent Studio to mimic human-like intelligence while executing desktop actions for repetitive tasks in web and desktop environment.

    Overview of AI agents for AI Desktop Actions

    In the ServiceNow agentic ecosystem, an AI agent is a set of large language model (LLM) instructions and tools that can perform specific tasks. The AI agents can perform specific tasks and functions, often using natural language instead of traditional code. For more information, see Create an AI agent.

    AI agents process instructions, generate execution plans, and run desktop actions autonomously and semi-autonomously across legacy systems, thick client applications, and web applications lacking APIs or backend integrations. AI agents can interpret your goal and map them to one or more desktop actions via metadata (capabilities, inputs, and outputs).

    Use AI agents to do the following tasks for your organization:
    • Generate a dynamic execution plan for desktop or web-based tasks
    • Coordinate with other AI agents to complete subtasks
    • Process human input during task execution when required
    • Collaborate with users to resolve issues that require human judgment

    For adaptive desktop actions, an AI agent named Web Automation Agent and agentic workflow named Web Automation are provided by default when you install AI Desktop Actions.

    1. Define the specialty of an AI agent

      Write a clear name and description of the AI agent, define role, and list of steps this AI agent must complete, define supported LLMs, enable third-party access, and manage long-term memory. The LLM analyzes the specific wording that you use to understand the specialty of this AI agent.

    2. Add a desktop action to an AI agent.

      Add a desktop action as a tool to the AI agent to enable desktop and web automations. Tools provide your AI agents with the capabilities necessary to complete their tasks. Providing your AI agents with the appropriate tools help with the robustness and quality of their performance. An AI agent selects a tool based on the tool’s name and description, which must be clearly written.

    3. Define security controls for an AI agent
      Define security controls for who can access the AI agent and what data the AI agent has access to. The Define security controls step is divided into two parts:
      • Define user access: Creates an ACL that determines which users can discover or invoke the AI agent.
      • Define data access: Defines the data that the AI agent has access to once it’s invoked.

      Trigger conditions aren't supported for AI agents that execute desktop actions. You must manually trigger these agents from the system where the AI Desktop Actions application is installed.

    4. Select channels and status for an AI agent

      Activate the AI agent to use in an assistant in ServiceNow Otto for Virtual Agent and set the processing message. This AI agent can engage with users who initiate an interaction when it’s available for use in channels. Select channels where you want this AI agent to be available to engage with users.