--- sourceDocument: Brazil Governance, Risk, and Compliance sourceDocumentLink: https://www.servicenow.com/docs/r/governance-risk-compliance Release : - brazil ft:locale : - en-US ft:publication_title : - Brazil Governance, Risk, and Compliance ft:clusterId : - grc bundleId : - grc workflow : - Technology --- # Use agentic AI # Use agentic AI in ServiceNow Otto for Integrated Risk Management (IRM) {#ariaid-title1} Release version: Brazil Updated September 10, 2026 ![](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 Use agentic AI in ServiceNow Otto for Integrated Risk Management (IRM) ServiceNow Otto for Integrated Risk Management (IRM) enables the use of agentic AI through agents within workflows or as standalone entities to automate specific outcomes. Access to generative AI features and agentic workflows depends on your ServiceNow license tier. This functionality supports integration with various large language models (LLMs) and includes important security controls to ensure safe AI execution. Show full answer Show less ## Supported Large Language Models (LLM) You can utilize AI model providers such as Now LLM Service, Azure OpenAI, Google Gemini, or Anthropic Claude on AWS for all generative AI skills and AI agents. Configuration Controls in the AI Control Tower allow administrators to specify available options, and skill-level preferences are managed via the AI Admin Hub console. Azure OpenAI is specifically recommended for agentic workflows in ServiceNow Otto for IRM. ## Security and Access Control Security implementation is critical when executing AI agents and workflows. Access Control Lists (ACLs) provide the Run As capability, enabling agents to perform actions as either a dynamic user or an AI user, ensuring proper authorization and auditing. Administrators should configure these controls to safeguard automated AI operations. ## Running Autonomous AI Agents * By default, agentic workflows and AI agent records are read-only. * To run AI agents autonomously, duplicate and activate the agentic workflow and all included agents. * Activate unique triggers to invoke workflows automatically, unless manual invocation is preferred. ## Standalone AI Agents Some AI agents are available outside of agentic workflows and may be installed with the Now Assist application. You can view all available AI agents in your instance or explore additional agents via the AI Agent Marketplace on the ServiceNow Store. Specific standalone AI agents for ServiceNow Otto for IRM are also available for use. Use agents within an agentic workflow or as standalone agents to achieve specific automated outcomes. Note: Depending on your license, you will have access to certain application features, generative AI skills, agentic workflows, and AI agents. For more information, see [ServiceNow product tiers](https://www.servicenow.com/docs/access?context=ai-native-sku-overview&version=brazil&pubname=brazil-intelligent-experiences&ft:locale=en-US). Find information such as the large language models (LLM) supported in Now Assist and security controls that are important considerations for using agentic AI. For more information on language support, see [Multilingual service for Now Assist](https://www.servicenow.com/docs/access?context=translation-for-now-assist&version=brazil&pubname=brazil-intelligent-experiences&ft:locale=en-US) and [Multilingual support for ServiceNow generative AI products](https://www.servicenow.com/community/now-assist-articles/multilingual-support-for-servicenow-generative-ai-products/ta-p/3099258). ## Supported large language models (LLM) {#use-agentic-ai-in-risk-sustainability__section_pwb_fhk_xgc} Note: * You can use Now LLM Service, Azure OpenAI, Google Gemini or Anthropic Claude on AWS as the AI model provider for all generative AI skills and AI agents. Use the Configuration Controls in [AI Control Tower](https://www.servicenow.com/docs/access?context=ai-model-providers&version=brazil&pubname=brazil-intelligent-experiences&ft:locale=en-US) 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=brazil&pubname=brazil-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=brazil&pubname=brazil-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=brazil&pubname=brazil-intelligent-experiences&ft:locale=en-US). {#use-agentic-ai-in-risk-sustainability__ul_mkc_txv_dhc} ## Security implementation considerations {#use-agentic-ai-in-risk-sustainability__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=brazil&pubname=brazil-intelligent-experiences&ft:locale=en-US). ## Considerations for running the autonomous AI Agents {#use-agentic-ai-in-risk-sustainability__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=brazil&pubname=brazil-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 ServiceNow Otto for IRM agentic workflows. {#use-agentic-ai-in-risk-sustainability__ul_cgc_ffk_h2c} ## Standalone AI agents {#use-agentic-ai-in-risk-sustainability__section_cks_khk_xgc} Looking for an AI agent? * There may be AI agents installed with the Now Assist application that aren't 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=brazil&pubname=brazil-intelligent-experiences&ft:locale=en-US) * To find agents that might not be installed on your instance, visit the [AI Agent Marketplace](https://store.servicenow.com/store/ai-marketplace) on the ServiceNow Store. * For information on the standalone ServiceNow Otto for IRM AI agents, see [Standalone AI Agents in ServiceNow Otto for Integrated Risk Management (IRM)](https://www.servicenow.com/docs/aBq4RiYcoaaqg3bReZ2WKg "Use AI agents in Governance, Risk, and Compliance to complete IT-related tasks autonomously."). {#use-agentic-ai-in-risk-sustainability__ul_y3m_bgv_hhc}