--- sourceDocument: Australia Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/australia/intelligent-experiences Release : - australia ft:locale : - en-US ft:publication_title : - Australia Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Add tools and information # Add tools and information to an AI agent {#ariaid-title1} Release version: Australia Updated November 23, 2025 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) 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 tools and information to an AI agent This guide explains how to enhance AI agents in ServiceNow by adding tools and information, enabling them to perform specific tasks effectively. Tools equip AI agents with necessary capabilities, while knowledge graphs provide context about relationships between entities, improving output quality. Show full answer Show less ## Key Features * **Tools:** Add discrete, task-specific tools designed to work together, helping AI agents achieve their objectives. Detailed tool descriptions are essential for the AI to understand functionalities and process outputs correctly. * **Knowledge Graphs:** Integrate knowledge graphs to supply AI agents with relational data, such as mapping users to departments or locations, enhancing decision-making and accuracy. * **Execution Modes:** * **Autonomous Mode:** Tools run immediately upon selection by the AI agent without human intervention; suited for read-only or low-risk operations. * **Supervised Mode:** Tools require human approval before execution, providing oversight for sensitive actions like data modification, communication, or budget spending. * **Web Search Tool Notice:** Using Google as a web search provider involves data routing through Google's global infrastructure, which may differ from your ServiceNow instance's data location. Consider organizational data policies before enabling it. ## Practical Application for ServiceNow Customers When configuring AI agents, select and design tools thoughtfully to align with agent goals and ensure they interoperate smoothly. Provide comprehensive descriptions for each tool to maximize AI understanding and effectiveness. Choose execution modes based on risk level---use supervised mode for any tool performing sensitive or critical operations to maintain security and compliance. Incorporate knowledge graphs to enrich agents' contextual awareness, improving the relevance and accuracy of their outputs, such as in approval workflows. Be mindful of data routing implications when enabling web search tools, particularly with Google, to adhere to your organization's data governance policies. After adding tools and knowledge graphs, proceed with the guided setup to finalize AI agent configuration and optimize their performance within your ServiceNow environment. Add a tool to an AI agent to enable different functionalities and help your AI agents achieve their objectives. ## Tool overview Tools give your AI agents the capabilities they need to complete their tasks. When adding tools, think about how the AI agent will use them to achieve its objectives and how those tools will work together. Equipping your AI agents with the right tools helps ensure robust, high-quality performance. Consider the following guidelines when adding and creating tools: * Design tools to work together. Each AI agent should solve a specific, discrete task, and its tools should provide the capabilities needed to reach that goal. * Write detailed tool descriptions. The AI agent uses tool descriptions to understand what each tool does. Clear, thorough descriptions give the AI agent the best chance to succeed. * Plan for tool outputs when creating them. Use the tool description or output transformation strategy fields to explain how to process the tool outputs. For example, if a tool retrieves records from multiple tables, specify how to handle the large volume of results. Note: If you select Google as your web search tool provider, the web search tool leverages [Grounding with Google Search](https://cloud.google.com/vertex-ai/generative-ai/docs/grounding/grounding-with-google-search), offered under a Global Standard deployment. Because grounding isn't [data resident](https://cloud.google.com/vertex-ai/generative-ai/docs/security-controls), Google's global infrastructure routes traffic to a global datacenter for each web search request. This processing may be different than your data processing location chosen for your ServiceNow instance. Consider your organization's data policies before enabling AI agents that use Google web search tools. After you add the tools to your AI agent, scroll down to the next step in the guided setup. ## Knowledge graphs You can also add Knowledge graphs in this step. Knowledge graphs provide the AI agent with information about relationships between real-world entities, which improves its outputs. For example, you could add a Knowledge Graph to an approval AI agent that maps users to their location, company, and department, helping the AI agent apply the correct approval process. ## Supervised vs. autonomous execution mode for AI agents {#add-tool-aia-new__section_ugm_tbp_chc} Autonomous : The tool runs as soon as the agent selects it, with no prompt and no opportunity to intervene. Appropriate for read operations and low-consequence updates. Supervised : The agent pauses and asks a person to approve the action before the tool runs. Nothing happens until someone responds, so a supervised tool in a background or unattended execution stalls rather than proceeds. Use it for anything that writes, deletes, contacts a customer, or spends budget. Execution mode is set per tool and can be changed at any time in the guided setup. A mode set during a build conversation can be set after the initial draft. See [Modify an AI agent](https://www.servicenow.com/docs/17dnfd7g7PiQNr0Rb4XW4w "Modify an AI agent in AI Agent Studio to refine its performance, align with business goals, or enable it to perform new tasks."). You can reduce the risk of an AI agent executing unexpectedly by configuring its tools to run in supervised mode. Supervised mode means that tools use human oversight during execution. Use supervised mode to enhance security for agents that perform sensitive or critical actions. You can set the supervised execution mode when creating a tool in the AI agent guided setup. For example, select Supervised as the Execution mode when adding a catalog item tool. For reference, see [Add a catalog item to an AI agent](https://www.servicenow.com/docs/WterIHI3F4gQWz9dktDh1Q "Add a Service Catalog to an AI agent in AI Agent Studio so that your users can access conversational catalog items.").