Add a tool to an AI agent

  • Release version: Xanadu
  • Updated July 31, 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 Add a tool to an AI agent

    Adding tools to AI agents in ServiceNow empowers them with the necessary functionalities to complete specific tasks effectively. Thoughtful tool integration ensures that AI agents can achieve their objectives with robustness and quality. Tools must be designed to work cohesively, providing all capabilities required for the agent's goals.

    Show full answer Show less

    Key Guidelines for Adding Tools

    • Design Tools to Work Together: Ensure that each tool supports discrete, specific tasks that collectively enable the AI agent to succeed.
    • Write Detailed Tool Descriptions: Provide thorough explanations of each tool's purpose and operation to guide the AI agent’s usage effectively.
    • Consider Tool Outputs: Define how to process outputs, especially when dealing with large data sets, by using tool descriptions or output transformation strategies.
    • Data Privacy Considerations: When using web search tools, particularly Google, be aware of data routing and compliance with organizational data policies.

    Supervised Execution Mode

    Configure tools to run in supervised mode to maintain human oversight, reducing risks from unexpected AI agent actions. This is particularly important for sensitive or critical operations. Supervised mode can be enabled during tool creation in the AI agent guided setup.

    Types of Tools You Can Add

    • Catalog Items: Enable users to access conversational catalog offerings directly through the AI agent.
    • Conversational Topics: Add virtual agent topics to collect additional user input during interactions.
    • File Uploads: Allow AI agents to analyze uploaded documents for specialized knowledge.
    • Flow Actions: Incorporate reusable automation steps without coding to streamline AI platform features.
    • Knowledge Graphs: Utilize structured and unstructured ServiceNow data to enhance AI agent intelligence.
    • Now Assist Skills: Add customizable generative AI capabilities tailored to user workflows.
    • Record Operations: Perform create, update, lookup, or delete actions on records.
    • Scripts: Leverage scriptable APIs and integrations to extend AI agent functionality.
    • Search Retrieval: Use Retrieval-Augmented Generation (RAG) to fetch relevant external information.
    • Subflows: Embed reusable sequences of process steps within flows.
    • Web Search: Integrate third-party search APIs like Microsoft Bing or Google for web-based queries.

    Next Steps

    After adding all desired tools, save your configuration and proceed with the guided setup to finalize your AI agent’s capabilities.

    Add a tool to an AI agent to enable different functionalities and help your AI agents achieve their objectives.

    Tool overview

    Tools provide your AI agents with the capabilities necessary to complete their tasks. When adding tools, consider how the AI agent will use them to achieve its objectives as well as how those tools interact with each other. Providing your AI agents with the appropriate tools help ensure the robustness and quality of their performance.

    Some additional guidelines for adding and creating tools are the following:

    • Design tools to work together. Your AI agent should solve a specific, discrete task, and the tools should give the AI agent all of the capabilities necessary to achieve its goal.
    • Write detailed tool descriptions. Tool descriptions are used by the AI agent to determine a tool's function. Thorough descriptions about what the tools are and how they work will give the AI agent the best chance to succeed.
    • Consider the outputs of tools when creating them. Use the tool description or output transformation strategy fields to describe how to process the tool outputs. For example, if you have a tool that gathers records from a large number of tables, provide the tool with plans for how to handle the amount of records that the query could return.
    Note:
    If you select Google as your web search tool provider, the web search tool leverages Grounding with Google Search, offered under a Global Standard deployment. Because grounding is not data resident, Google's global infrastructure routes traffic to a global data center for each web search request. This processing may be different than your data processing location chosen for your ServiceNow instance. Please consider your organization's data policies before enabling AI agents that use Google web search tools.

    Once you have added all of the tools to your AI agent, you can select Save and continue to move to the next step in the guided setup.

    Supervised execution mode for AI agents

    You can minimize potential negative impact of an AI agent not executing as expected by configuring AI agents' tools to run in supervised mode. This will ensure human oversight for the tool's actions. You can use the Supervised mode to enhance security for agents with the capability to perform sensitive or critical actions.

    You can set the supervised execution mode when creating a tool in the AI agent guided setup. For example, choose Supervised as the Execution mode when adding a catalog item tool. For reference, see Add a catalog item to an AI agent.