--- sourceDocument: Zurich IT Service Management sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/it-service-management Release : - zurich ft:locale : - en-US ft:publication_title : - Zurich IT Service Management ft:clusterId : - itsm bundleId : - itsm workflow : - Technology --- # Important considerations # Important considerations for using ServiceNow Otto for IT Service Management (ITSM) agentic AI {#ariaid-title1} Release version: Zurich Updated November 18, 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 Important considerations for using ServiceNow Otto for IT Service Management (ITSM) agentic AI ServiceNow Otto enables autonomous task completion within IT Service Management (ITSM) by using AI agents embedded in agentic workflows. These AI agents leverage supported Large Language Models (LLMs) to deliver generative AI capabilities, automating and enhancing ITSM processes efficiently. Show full answer Show less ## Key Features * **Supported Large Language Models:** You can utilize Now LLM Service, Azure OpenAI, Google Gemini, or Anthropic Claude as AI model providers. Configuration of available options is managed via AI Control Tower, while skill-level preferences are set in the AI Admin Hub. * **Security Implementation:** Execution of AI agents and workflows is governed by Access Control Lists (ACLs) and user identities, allowing AI agents to operate under dynamic or AI user contexts via the Run As capability. Role masking controls user access to AI agents and workflows, and roles embedded with applications must be configured appropriately if restricting access to specific users. * **Autonomous Operation Setup:** By default, agent workflows and AI agent records are read-only. To activate autonomous AI agents, you must duplicate and activate the agentic workflow and all included agents, then enable unique triggers for automatic invocation (manual invocation is optional without activating triggers). * **Recommended Model Provider:** Azure OpenAI is recommended for ITSM agentic workflows, ensuring optimal performance and integration. * **Standalone AI Agents:** Some AI agents may exist independently of agentic workflows. You can identify all available AI agents on your instance to understand and manage their usage effectively. ## Key Outcomes * Enable autonomous and secure completion of ITSM tasks using AI agents, reducing manual workload and improving service efficiency. * Maintain robust security controls through ACLs and role masking, ensuring AI actions comply with organizational policies and user access requirements. * Configure and manage AI model providers and agent preferences centrally for consistent and optimized AI behavior. * Leverage recommended AI model providers like Azure OpenAI to enhance the reliability and effectiveness of ITSM agentic workflows. * Gain visibility over all AI agents, including those not currently integrated into workflows, to maximize AI resource utilization. Use the IT Service Management AI agents within an agentic workflow to complete tasks autonomously. ## Supported Large Language Models {#important-considerations-itsm-agentic-ai__section_pwb_fhk_xgc} Note: * You can use Now LLM Service, Azure OpenAI, Google Gemini or Anthropic Claude as the AI model provider for all generative AI skills and AI agents. Use the Configuration Controls in AI Control Tower to define which options are available, then set the skill-level preferences in the [AI Admin Hub console](https://www.servicenow.com/docs/access?context=manage-large-language-models&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US). For more information, see [Large language models on the ServiceNow AI Platform®](https://www.servicenow.com/docs/access?context=exploring-large-language-models&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US). * For the Now LLM Service updates, see [Model provider updates](https://www.servicenow.com/docs/access?context=now-llm-model-updates&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US). {#important-considerations-itsm-agentic-ai__ul_mkc_txv_dhc} ## Security implementation considerations {#important-considerations-itsm-agentic-ai__section_tcr_ghk_xgc} Enable security implementation to execute AI agents and agentic workflows through Access Control Lists (ACLs) and user identities. ACLs provide the Run As capability to let agents and agentic workflows execute actions either as a dynamic user or as an AI user. For more information, see [Implement access control in AI agents](https://www.servicenow.com/docs/access?context=aia-security-implementation&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US) Agentic workflows and their AI agents use [role masking](https://www.servicenow.com/docs/access?context=aia-role-masking&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US) to determine which users can access them. Ones installed with your applications have specific roles that come included with the application. If you select Users with specific roles for user access, you must configure the security controls to include these roles. For the instructions to change the security controls, see [Define security controls for an agentic workflow](https://www.servicenow.com/docs/access?context=define-sec-controls-aw&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US). AI agents use [role masking](https://www.servicenow.com/docs/access?context=aia-role-masking&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US) to determine which users can access them. Ones installed with your applications have specific roles that come included with the application. If you select Users with specific roles for user access, you must configure the security controls to include these roles. For the instructions to change the security controls, see [Define security controls for an AI agent](https://www.servicenow.com/docs/access?context=define-sec-controls-aia&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US). ## Considerations for running the autonomous AI Agents {#important-considerations-itsm-agentic-ai__section_bhz_3hk_xgc} Important: By default, all agent workflow and AI agent records are read-only. To run the AI agents autonomously, you must first [duplicate the agentic workflow](https://www.servicenow.com/docs/access?context=clone-aia-usecase&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US), and then proceed with the following steps: * Activate the agentic workflow. * Activate all agents within the agentic workflow. * Activate the trigger to invoke the agentic workflow automatically. The triggers for each agentic workflow must be unique. If you prefer to invoke it manually, activating the trigger isn't necessary. * Azure OpenAI is recommended for ITSM agentic workflows. For information on Large Language Models (LLMs) for AI agents and agentic workflows, see [Large language models on the ServiceNow AI Platform®](https://www.servicenow.com/docs/access?context=exploring-large-language-models&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US). {#important-considerations-itsm-agentic-ai__ul_cgc_ffk_h2c} ## Standalone AI agents {#important-considerations-itsm-agentic-ai__section_cks_khk_xgc} There might be AI agents installed on your instance that are not used in agentic workflows. To learn how to see all agents that are available to you, see [Find AI agents](https://www.servicenow.com/docs/access?context=find-ai-agents&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US).