--- sourceDocument: Brazil Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences Release : - brazil ft:locale : - en-US ft:publication_title : - Brazil Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Using Enterprise graph schema # Using Enterprise graph schema {#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 Enterprise Graph schema Enterprise Graph is a preconfigured Knowledge Graph schema in ServiceNow that maps all instance tables and their relationships, enabling comprehensive natural language queries across the entire database. It simplifies the Knowledge Graph setup by eliminating the need for custom schema creation and supports enhanced query accuracy through tagging. Show full answer Show less ## Key Features * **Comprehensive Data Coverage:** Maps all tables in the instance to enable natural language queries across the full database, unlike custom or out-of-the-box schemas that limit queries to specific tables. * **Preconfigured Schema:** Ready-to-use, reducing setup complexity for admins when configuring Knowledge Graph for AI agents, ServiceNow Otto for Virtual Agent, or the Otto panel. * **Tagging Support:** Uses tags to prioritize and focus queries on important tables, improving response relevance and accuracy. * **Two Operational Modes:** * **Enterprise Graph (Regular):** Supports large-scale searches across more than 50 tables, prioritizing tagged tables for efficient responses. * **Enterprise Graph (Small):** Restricts searches to tagged tables only (max 50 tables), ideal for latency-sensitive scenarios where focused data access is required. ## Benefits for ServiceNow Customers * **Virtual Agent Integration:** ServiceNow Otto for Virtual Agent can handle a wide range of user queries about enterprise data, improving user experience and deflecting routine questions. * **Otto Panel Enhancement:** Fulfiller productivity is boosted by allowing natural language queries that yield insights from structured data directly within the instance. * **AI Agents Enablement:** AI agents gain direct access to relevant contextual information from structured data, improving task accuracy and efficiency. ## Practical Application Notes * Admins select Enterprise Graph as the schema when configuring Knowledge Graph for AI agents or Virtual Agent. * Tagging is mandatory, especially in the Enterprise Graph (Small) mode, and ensures queries target the most relevant tables for the use case. * Choosing between regular and small modes depends on the number of tables involved and latency requirements. Use Enterprise Graph for accurate natural language query responses, across the entire database. Enterprise graph is a pre-configured Knowledge Graph schema that maps all instance tables and their connections, enabling natural language queries for data across all tables. To see some examples of the Natural Language query responses, refer [Natural language queries use cases and examples](https://www.servicenow.com/docs/hEA0o0XcFZ5RkUv933M0UQ "View example use cases of some natural language queries used in Knowledge Graph and Enterprise Graph."). Enterprise graph schema simplifies Knowledge Graph setup by providing a preconfigured schema, eliminating the need for custom schema creation in Knowledge Graph designer. Admins can choose Enterprise graph as the Knowledge Graph schema when using AI agents, ServiceNow® Otto for Virtual Agent, or ServiceNow Otto panel admin and add tags to enhance accuracy. By mapping all tables, the Enterprise graph schema expands query capabilities to cover the entire database, whereas a custom or out-of-the-box (OOTB) schema limits queries to only the tables included in its specific schema. ## Benefits of Enterprise Graph on Prebuilt integration {#global-graph-schema__section_hkt_vyx_mhc} Now Assist ServiceNow® Otto for Virtual Agent- With Enterprise Graph integration, ServiceNow® Otto for Virtual Agent can respond to a wide range of questions about their enterprise data from requester, helping to deflect queries. ServiceNow Otto panel- With Enterprise Graph enabled, ServiceNow Otto panel allows fulfillers to obtain insights from the structured data in instance by asking natural language questions, which boosts their productivity. AI agents- With Enterprise Graph enabled, AI agents can access relevant information from structured data in ServiceNow instance directly from the Knowledge Graph, giving them essential context for tasks. ## Modes of Enterprise Graph {#global-graph-schema__section_asg_hw4_jhc} Enterprise Graph has two modes: * Enterprise Graph- regular mode * Enterprise Graph (Small) {#global-graph-schema__ul_i4r_hzx_mhc} Regular mode is used for use cases with large number of tables (more than 50 tables), to: * Searches across all tables, but gives more priority to tables which are included in the tag added at time of configuring Enterprise Graph in the consuming app (AI agent or VA). * Useful for scenarios where answer is expected from large number of tables. {#global-graph-schema__ul_tqk_kzx_mhc} Enterprise Graph (Small) is a version of Enterprise Graph that limits the search to only the tables tagged with specific labels. This means it can only answer queries related to those tables. It's useful for: * Searches only within tables which are included in the tag added at time of configuring Enterprise Graph (Small) in consuming app (AI agent or VA). Tagging is mandatory in this mode. * Useful for latency-sensitive use cases with limit of 50 tables {#global-graph-schema__ul_vbt_szx_mhc} ## Tags in Knowledge Graph {#global-graph-schema__section_ulm_h5s_ghc} Tags are lists of key tables that are important for answering natural language questions in a specific use case. They are required to be used with Enterprise Graph and Enterprise Graph (Small).