--- sourceDocument: Australia Enterprise Architecture sourceDocumentLink: https://www.servicenow.com/docs/r/australia/application-portfolio-management Release : - australia ft:locale : - en-US ft:publication_title : - Australia Enterprise Architecture ft:clusterId : - appportman bundleId : - appportman workflow : - Technology --- # Exploring Enterprise Architecture query agent # Exploring Enterprise Architecture query agent {#ariaid-title1} Release version: Australia Updated May 26, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 7 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 Exploring Enterprise Architecture query agent The Enterprise Architecture (EA) query agent is a ServiceNow Otto AI agent designed to help architects and portfolio managers interact with their enterprise architecture data using natural language queries. It provides AI-generated, data-driven answers about your EA portfolio without requiring manual report building or dashboard navigation. This read-only agent accesses and interprets data such as business applications, capabilities, value streams, technology standards, and information objects within your ServiceNow instance. Show full answer Show less Responses are generated by a large language model (LLM) subscribed to your ServiceNow platform, with options for different models including the latest Gemma 4 starting in the September 2026 release. The agent is enabled by default for relevant users depending on your license and role. ## Key Features * **Natural language querying:** Ask questions about your EA data using everyday language. * **Data domains supported:** Business applications, business capabilities, application relationships, technology standards (TRM), information objects, technical debt, lifecycle phases, and impact analyses. * **Impact analysis:** Evaluate effects of decommissioning applications or failures in infrastructure CIs (e.g., databases, servers) on related business capabilities and applications. * **Infrastructure impact tracing:** Traces CMDB relationships from infrastructure items through application services to business capabilities for comprehensive impact insights. * **Interactive responses:** Answers include links to specific EA records for easy navigation within Enterprise Architecture Workspace and suggestions for related follow-up questions. * **Knowledge Graph integration:** Utilizes ServiceNow Knowledge Graph built from your CMDB data to ensure responses are grounded solely in your instance's data. * **Read-only access:** The agent retrieves and analyzes data without creating, modifying, or deleting records. ## Practical Use and Considerations * Ask targeted questions involving one or two relationship types for best accuracy; queries involving multiple complex relationships may require verification against source records. * Use specific record names or identifiers in queries to get the most relevant responses. * Large-scale aggregations (counts, percentages) should be treated as indicative and verified for precision. * The Knowledge Graph must be enabled and fully processed for the agent to access CMDB relationship data. Initial data processing can take days, and the agent is unavailable until completion. * Data completeness and accuracy depend on the quality and currency of your CMDB data; maintaining an up-to-date CMDB ensures reliable answers. * If new tables, relationships, or custom fields are added, the Knowledge Graph refreshes on a schedule to incorporate these changes. ## Access and Setup The agent is accessed via the ServiceNow Otto panel within the Enterprise Architecture Workspace. Administrators must enable the necessary Knowledge Graph system properties and allow time for data processing. To expedite setup, importing enterprise graph descriptions from a sub-production instance is supported. ## What to Expect By using the Enterprise Architecture query agent, ServiceNow customers can efficiently explore and analyze their EA portfolio through conversational AI. This accelerates insights into application ownership, lifecycle status, capability coverage, technical risks, infrastructure dependencies, and impact scenarios without manual data exploration. All answers are directly derived from your ServiceNow instance's data, ensuring governance and data protection within the platform. This AI-powered capability enhances decision-making and portfolio management through intuitive, data-grounded interactions. The Enterprise Architecture query agent answers natural language questions about your enterprise architecture portfolio, returning AI-generated answers grounded into their Enterprise Architecture data. 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=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). Important: This generative AI skill is turned on by default. The skill will be automatically available to appropriate role users for the application. For more information, see [AI agents, skills, and agentic workflows on by default](https://www.servicenow.com/docs/access?context=now-assist-skills-on-by-default&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). The Enterprise Architecture Explorer Query Agent is a ServiceNow Otto agent for Enterprise Architecture. It lets architects and portfolio managers query their EA data using natural language, without navigating dashboards or building reports manually. The agent interprets the structure of your EA portfolio, including business applications, capabilities, value streams, technology standards (TRM), and information objects. It returns structured answers based on your data. When processing a question, the agent searches for relevant data and actions before generating a response. After answering, the agent may display suggestions for related questions to help you explore further. Responses are generated by the large language model (LLM) that your organization has subscribed to on the ServiceNow® platform. The responses may also differ depending on the selected LLM. Note: Starting with the September 2026 release, Gemma 4 joins our growing portfolio of open-weight models available through Now LLM Service. The latest industry advancements are available alongside sovereignty-focused options. All models are hosted and governed by ServiceNow with the same infrastructure and data protections. Older models will remain available for existing published AI skills, agents, and agentic workflows, but will no longer be available for new development or configuration. For details, see the [KB3066214: ServiceNow Otto Model Upgrades](https://support.servicenow.com/kb?id=kb_article_view&sysparm_article=KB3066214) article in the Now Support Knowledge Base. You can ask questions about individual records, apply multiple filter conditions, compare trends across fiscal periods, or model impact scenarios such as decommissioning an application. Note: The Enterprise Architecture query agent is read-only. It retrieves and analyzes your EA data but does not create, modify, or delete any records in your instance. When a response references a specific record, such as a business application or a capability, the record name appears as linked text. Select the linked text to navigate directly to that record in Enterprise Architecture Workspace. ## What you can ask about {#ea-qna-overview__section_ea_qna_domains} The Enterprise Architecture Explorer Query Agent answers questions across the following EA data domains: {#ea-qna-overview__table_ea_qna_domains__entry__3} | Domain | Topics covered | Example queries | |-|-|-| | Business applications | Ownership, lifecycle phase, application category, CSAT and technical risk scores, retirement candidates | * Get the owner of a business application * Which applications are candidates for retirement? {#ea-qna-overview__ul_ecl_35l_fkc} | | Business capabilities | Hierarchy, scores, capability-to-application coverage | What are the top-level capabilities? | | App capability relationships | Applications supporting a capability, applications with no capability assignments | * List business apps supported by multiple capabilities * Which business applications aren't assigned to capabilities? {#ea-qna-overview__ul_o1y_j5l_fkc} | | Trends | Score comparisons for one or more applications | Compare the quarterly trends for two business applications | | TRM and technology | Software versions, lifecycle phase | * List all versions of a specific software * What is the lifecycle phase of an application? {#ea-qna-overview__ul_erc_l5l_fkc} | | Information objects | Producing and consuming applications, orphaned objects | Which information objects have no producing or consuming applications? | | Impact analysis | Capability and information object impact of decommissioning an application | If a business application is decommissioned, which capabilities and information objects are impacted? | | Infrastructure impact analysis | Business capabilities, business applications, and application services affected by an infrastructure CI such as a database, database instance, server, or storage device. Includes the infrastructure that an entity depends on. | * Which business capabilities are impacted if a specific database fails? * Which entities are affected by a failure of a specific server or storage device? * Which servers and databases support a business application? {#ea-qna-overview__ul-ea-qna-infra-impact-examples} | | Technical debt | Applications flagged for technical debt | Can you share a list of technical debts? | [Table 1. EA data domains supported by the Enterprise Architecture Explorer Query Agent] {#ea-qna-overview__table_ea_qna_domains} ## Infrastructure impact analysis {#ea-qna-overview__section-ea-qna-infra-impact} You can ask the Enterprise Architecture query agent about the impact of an infrastructure configuration item (CI), such as a database, database instance, server, or storage device. The agent follows the CMDB relationships from the CI up through the application services and business applications that depend on it. It then traces those applications to the business capabilities they support. You can also ask what infrastructure a named application service or business application depends on. Infrastructure impact responses work as follows: * If the CI name that you enter is partial or spaced differently from the stored name, the agent searches for similar names. If more than one CI matches, the agent lists the matching CIs with their class so that you can specify the correct one. * If a CI supports multiple application services or business applications, the response includes every impacted record, not only the first match. * The response can include the path from the CI to each impacted record, with the relationship type at each step, so that you can validate the result. * If the CI isn't related to any application service or business application, or the chain stops before the requested entity type, the response names the missing relationship. * If the CI has many relationships, the response indicates that the results may be partial. {#ea-qna-overview__ul-ea-qna-infra-impact-behavior} ## Important information to derive the best results {#ea-qna-overview__section_ea_qna_limitations} To get the most accurate responses from the agent, remember the following: * The agent works best for questions involving one or two relationship types. For queries with three or more relationships, it's recommended to check the results against your source records for completeness. Example of a query with three or more relationships, List all child capabilities, their providing applications, the information objects those applications use, and the services they consume. * Large-scale aggregations --- For counts and percentages across large data sets, treat results as indicative figures. For precise values, verify against your source records. * The agent queries your enterprise architecture data using the Knowledge Graph, which is updated through scheduled jobs. If new relationship types, tables, or custom fields are added to your instance, the Knowledge Graph does a scheduled refresh to generate updated descriptions. Some specialized or less common data points may not be fully represented yet, which could lead to partial responses for certain queries. * For questions about a specific record, include the record name or identifier in your query to help the agent return the most relevant response. For example, Is Order Management a leaf capability? {#ea-qna-overview__ul_gzk_nfw_ljc} ## Access {#ea-qna-overview__section_ea_qna_access} The Enterprise Architecture query agent is available through the ServiceNow Otto panel across Enterprise Architecture Workspace. Select the ServiceNow Otto icon to open the panel and start a conversation with the agent directly. ## ServiceNow Knowledge Graph dependency {#ea-qna-overview__section_h3x_hgn_ljc} The Enterprise Architecture query agent uses the ServiceNow Knowledge Graph to answer questions about CMDB relationships and infrastructure data. An administrator must enable the required Knowledge Graph system properties before the agent can access this data. After the system properties are enabled, Knowledge Graph runs scheduled jobs to process your CMDB data. The time required for initial processing varies by the volume of data in your instance and may take several days or longer. During this period, responses that rely on CMDB relationship data may be incomplete. Results improve progressively as processing continues. If the Knowledge Graph data processing is in progress, the Knowledge Graph Designer displays a notification. This means that the scheduled jobs required to set up the enterprise graph are still running. The Enterprise Architecture query agent is not available until this process is complete and the notification is no longer displayed. To speed up the process, you can import enterprise graph descriptions from a sub-production instance where setup has already completed. For more information, see [Enterprise Graph initial setup in production instance](https://www.servicenow.com/docs/access?context=initial-setup-for-enterprise-graph-schema&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). For enable the Knowledge Graph system properties, see [Enable Knowledge Graph system properties for the Enterprise Architecture query agent](https://www.servicenow.com/docs/eEupGLRhEEx7Ot20K3h1nw "Enable the Knowledge Graph system properties to allow the Enterprise Architecture query agent to generate accurate answers based on your Configuration Management Database (CMDB) data."). All data displayed by the Enterprise Architecture query agent is sourced directly from the ServiceNow® Knowledge Graph, which is built from and continuously updated by your instance's CMDB data. When you submit a question, the agent queries the Knowledge Graph to identify relevant records, relationships, and attributes before generating a response. This means the agent does not draw on general knowledge or external sources. Every answer is grounded in the data that exists in your instance --- such as CI relationships, application ownership, capability mappings, and lifecycle information stored in your CMDB. If a record does not exist in your CMDB, the agent will not surface it. Note: The accuracy and completeness of the agent's responses depend on the quality and completeness of your CMDB data. Keeping your CMDB up to date ensures the most reliable answers. For information on the ServiceNow Knowledge Graph see the links. * [Exploring Knowledge Graph](https://www.servicenow.com/docs/access?context=exploring-knowledge-graph&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) * [Setting up Enterprise graph in sub-production instance](https://www.servicenow.com/docs/access?context=setting-up-global-graph-in-production-instance&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) * [Configuration item relationships and Knowledge Graph](https://www.servicenow.com/docs/access?context=ci-relationships-knowledge-graph&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) {#ea-qna-overview__ul_r2v_x3d_mjc} **Related concepts** * [Working with AI agent agentic workflow in ServiceNow Otto for Enterprise Architecture (EA)](https://www.servicenow.com/docs/QpEmg2RR578~hda_nviDVA "Use the AI agents in Enterprise Architecture to help complete tasks autonomously.") **Related tasks** * [Working with Enterprise Architecture query agent](https://www.servicenow.com/docs/uHOQWDO8sKFddk92CRJpQQ "You can ask the Enterprise Architecture query agent natural language questions about your enterprise architecture portfolio using the ServiceNow Otto panel in Enterprise Architecture Workspace.") * [Enable Knowledge Graph system properties for the Enterprise Architecture query agent](https://www.servicenow.com/docs/eEupGLRhEEx7Ot20K3h1nw "Enable the Knowledge Graph system properties to allow the Enterprise Architecture query agent to generate accurate answers based on your Configuration Management Database (CMDB) data.") * [Access Enterprise Architecture data using MCP tools](https://www.servicenow.com/docs/kvIcVfwF5IORun_jRK5t8g "Use MCP (Model Context Protocol) tools to query live Enterprise Architecture data—including business application insights, capability mappings, and rationalization data—from any MCP-compatible AI assistant.") **Related topics** * [Activate the ServiceNow Otto panel standard chat](https://www.servicenow.com/docs/access?context=activate-now-assist-panel&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US)