--- sourceDocument: Brazil ServiceNow AI Platform Capabilities sourceDocumentLink: https://www.servicenow.com/docs/r/servicenow-platform Release : - brazil ft:locale : - en-US ft:publication_title : - Brazil ServiceNow AI Platform Capabilities ft:clusterId : - platcap bundleId : - platcap workflow : - Platform --- # Using agentic workflows # Using agentic workflows in ServiceNow Otto for CMDB {#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 Using agentic workflows in ServiceNow Otto for CMDB ServiceNow Otto for CMDB provides agentic workflows that enable users with thesncmdbuserrole to interact with the CMDB using natural language and AI-driven automation. These workflows help create, search, analyze, and govern Configuration Items (CIs) in the CMDB efficiently. The agentic workflows leverage AI agents and large language models to streamline CMDB management tasks, improve data quality, and assist in impact analysis and integration recommendations. Show full answer Show less ## Key Features * **Create configuration item:** Allows users to create a valid CI by providing natural language input. The workflow verifies the CI class, ensures compliance with Identification and Reconciliation Engine (IRE) rules, checks for duplicates, and collects required attributes. * **Provide advice on CMDB governance:** Supports data administrators and owners in improving CMDB data accuracy, completeness, and overall health to foster trust in CMDB data. * **Search CMDB:** Enables natural language-driven searches for CIs using various attributes. The workflow automatically chooses appropriate search methods, including keyword, single-table, multi-table, and relationship navigation searches. * **Analyzing impact of change or incident:** Identifies upstream services and CIs potentially affected by an incident or change, providing structured impact levels and reasoning based on CMDB topology and change nature. * **Data model navigator:** Answers detailed questions about key CMDB data model areas like personal computing devices and server infrastructure with enhanced performance from indexed tables. * **Recommend service graph connector:** Suggests the best data sources or Service Graph Connectors to populate CMDB data for specific CI classes. * **CMDB MCP Server:** Exposes CMDB capabilities to external AI clients via Model Context Protocol (MCP), enabling secure data interactions without direct database access. ## Execution and Security To run agentic workflows autonomously, users must duplicate the read-only workflow records, activate the workflow and associated agents, and optionally activate triggers for automatic invocation. AI agents can operate with appropriate Access Control Lists (ACLs) and user identities, using the Run As capability to execute actions securely. ## AI Model Support and Configuration Agentic workflows support various AI model providers such as Now LLM Service, Azure OpenAI, Google Gemini, and Anthropic Claude on AWS. Administrators can configure model availability and skill-level preferences through AI Control Tower and the AI Admin Hub console to customize the AI capabilities used in workflows. ## Practical Benefits for ServiceNow Customers * Automate and simplify CMDB management tasks using natural language inputs and AI-driven workflows. * Improve CMDB data quality and governance with guided advice and certification support. * Enhance impact analysis and change management through AI-powered dependency reasoning. * Securely integrate external AI clients with CMDB data without direct database access. * Customize AI model usage and access controls to align with organizational policies and security requirements. Users with the sn_cmdb_user role can access several ServiceNow Otto for CMDB agentic workflows. ## Agentic workflows {#now-assist-cmdb-using__section_l23_wny_2hc} 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=brazil&pubname=brazil-intelligent-experiences&ft:locale=en-US). {#now-assist-cmdb-using__table_lxk_lck_h2c__entry__3} | Agentic workflow name | Description | Available AI agents | |-|-|-| | Create configuration item | Occasionally, you might create a CI manually. To help you, the Create configuration item agentic workflow accepts your natural language request and verifies that it understands which class the new CI should belong to. The workflow then checks Identification and Reconciliation engine (IRE) rules to determine the required attributes for the CI and requests that information. After you provide sufficient data, the workflow promotes that the proposed CI includes the attributes that you requested, complies with IRE rules, and is not a duplicate. The workflow then creates the CI. For more information, see [Create a CI using ServiceNow Otto](https://www.servicenow.com/docs/cq2rfn4UjX2AnRIrFTzlIA "The Create configuration item agentic workflow accepts your natural language request to manually generate a valid CI in the class that you specify.") | CI creator | | Provide advice on CMDB governance | Data governance can be an overwhelming task. The Provide advice on CMDB governance agentic workflow supports data admins and owners by methodically working through the many-faceted process of improving CMDB data accuracy, completeness, and health. The objective is to help users to trust the data that they use for their work. For more information, see [Getting advice from ServiceNow Otto on CMDB governance](https://www.servicenow.com/docs/QD0Pw3aOK6WxYRvUqkisHA "Data governance can be an overwhelming task. The Provide advice on CMDB governance agentic workflow supports data admins and owners by methodically working through the many-faceted process of improving CMDB data accuracy, completeness, and health. The objective is to help users to trust the data that they use for their work."). | * CMDB data manager * CMDB data certification and attestation manager * CMDB data ownership manager * CMDB health metrics manager * CMDB life cycle manager * CMDB principal class manager {#now-assist-cmdb-using__ul_azg_r4y_2hc} | | Search CMDB | The Search CMDB agentic workflow enables you to search for CIs by specifying any of several attributes of the CIs of interest. The workflow accepts your natural language request, verifies your search goal, and then, depending on the information you provided, generates a keyword search, a single-table search with dot walks, or a multi-table search that involves relationship navigation. The workflow can infer CI relationship data to generate an appropriate query. For more information, see [Use ServiceNow Otto to search the CMDB](https://www.servicenow.com/docs/R2ziq7f8YFsmfjL8kOcOFg "The Search CMDB agentic workflow enables you to search for CIs by specifying any of several attributes of the CIs of interest. The workflow accepts your natural language request, verifies your search goal, and then, depending on the information you provided, generates a keyword search, a single-table search with dot walks, or a multi-table search that involves relationship navigation. The workflow can infer CI relationship data to generate an appropriate query."). | CI search | [Table 1. Available agentic workflows for ServiceNow Otto for CMDB] {#now-assist-cmdb-using__table_lxk_lck_h2c} 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). 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) ## Running AI agents autonomously {#now-assist-cmdb-using__section_prl_4tf_pgc} Important: By default, all agentic workflow and AI agent records are read only. To run the AI agents autonomously, you must first duplicate the agentic workflow 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. If you prefer to invoke it manually, activating the trigger isn't necessary. {#now-assist-cmdb-using__ul_cgc_ffk_h2c} * **[Create a CI using ServiceNow Otto](https://www.servicenow.com/docs/cq2rfn4UjX2AnRIrFTzlIA)** The Create configuration item agentic workflow accepts your natural language request to manually generate a valid CI in the class that you specify. * **[Use ServiceNow Otto to search the CMDB](https://www.servicenow.com/docs/R2ziq7f8YFsmfjL8kOcOFg)** The Search CMDB agentic workflow enables you to search for CIs by specifying any of several attributes of the CIs of interest. The workflow accepts your natural language request, verifies your search goal, and then, depending on the information you provided, generates a keyword search, a single-table search with dot walks, or a multi-table search that involves relationship navigation. The workflow can infer CI relationship data to generate an appropriate query. * **[Analyzing the impact of a change or incident](https://www.servicenow.com/docs/4GTRJbMqTVci1y_MJKp2kg)** The Impact analysis agentic workflow identifies the upstream services and CIs that are likely to be affected by an incident or by a proposed change. The workflow reasons about propagation likelihood based on CMDB dependency topology and the nature of the change. The workflow returns a structured list with impact levels and the reasoning. * **[Data model navigator](https://www.servicenow.com/docs/qpwEE59Idep~1sVHUwfLYA)** ServiceNow Otto can answer deep questions about Personal Computing devices, Server infrastructure, IP Address Management, and Core CMDB tables in the CMDB data model. Search results are pulled from the Data Model Navigator tables, which are indexed to increase performance. * **[CMDB MCP Server](https://www.servicenow.com/docs/zXz3H8wOrkyRDkf5eb9G4Q)** The CMDB MCP Server exposes CMDB capabilities to external AI clients using the Model Context Protocol (MCP), so those clients can work with your configuration data without direct database access. * **[Recommend service graph connector agentic workflow](https://www.servicenow.com/docs/q67qebUeCFozaetA_vPVyA)** Sometimes you're not sure which integration to use to capture CI data. When you provide ServiceNow Otto with the name of a particular CI class, it can recommend the data sources or Service Graph Connectors and ingestion sources that can best populate CMDB data. * **[Getting advice from ServiceNow Otto on CMDB governance](https://www.servicenow.com/docs/QD0Pw3aOK6WxYRvUqkisHA)** Data governance can be an overwhelming task. The Provide advice on CMDB governance agentic workflow supports data admins and owners by methodically working through the many-faceted process of improving CMDB data accuracy, completeness, and health. The objective is to help users to trust the data that they use for their work.