--- sourceDocument: Australia Platform Analytics sourceDocumentLink: https://www.servicenow.com/docs/r/australia/now-intelligence Release : - australia ft:locale : - en-US ft:publication_title : - Australia Platform Analytics ft:clusterId : - par bundleId : - par workflow : - Platform --- # AI Data Explorer implementation checklist # AI Data Explorer implementation checklist {#ariaid-title1} Release version: Australia Updated March 25, 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 AI Data Explorer implementation checklist This checklist guides ServiceNow customers through the essential steps to enable and verify AI Data Explorer for their organization. It ensures that the semantic layer and related AI configurations are correctly set up to provide meaningful, data-driven insights via natural language queries. Show full answer Show less ## Prerequisites and configuration * Confirm installation of the AI Data Explorer application. * Activate required AI skills, including AI Data Explorer skills and Record Level Analysis within the Analytics Exploration skill for enhanced insights. * Use the Query Generation Health page to verify the health of Query Generation components. * Ensure AI Search is active. * Verify that the Semantic Layer is built with entities and dimensions properly populated (not zero). ## Testing and validation * Access AI Data Explorer from the main menu and test simple queries like "Open incidents" to confirm end-to-end functionality. * Test more specific queries that target indicators or tables to validate data accuracy and semantic layer integration. * Confirm required tables are included and active in the semantic layer via Query generation \> Entities. Add custom, non-task-based tables manually if needed. * For protected data scopes, configure Access Control Lists (ACLs) and Restricted Caller Access (RCA) to grant AI Data Explorer access. ## User access Assign the **now-assist-explorer-user** role to users who require access to AI Data Explorer functionality. ## General usage guidelines * Use short, simple questions focused on single charts or data sources for best results. * Complex or comparative questions across multiple data sources are not supported; break these into multiple queries. * When asking follow-up questions, use referencing terms like "these" to maintain filters and context. Complete these steps to enable AI Data Explorer and verify that the semantic layer is configured correctly for your organization. Use this checklist to verify that AI Data Explorer is properly configured and ready for use in your organization.{#ai-data-explorer-implementation-checklist__ai-data-explorer-implementation-checklist-para-1} ## Prerequisites and configuration * Verify that the AI Data Explorer application is installed. For more information, see [Install AI Data Explorer](https://www.servicenow.com/docs/Im4vPvFzp3E_zLte0izAXg "Verify that AI Data Explorer is installed, and install it if it is not."). * Verify that required AI skills are activated. * Verify that the AI Data Explorer skills are activated. For more information, see [Activate AI Data Explorer skills](https://www.servicenow.com/docs/h~eo~h5PkKWqD_CjIKOZHg "Enable AI Data Explorer skills under AI skills for Data and Analytics to give users AI-assisted, shared spaces to explore data."). * Enable Record Level Analysis in the Analytics Exploration skill to get better insights. For more information, see [Configure record level analysis in AI Data Explorer](https://www.servicenow.com/docs/iiOLxfH75lsAzecO7Gf6jA "Get more detailed answers based on the content of individual records to provide more meaningful insights."). * Check the base health of Query Generation using the [Query Generation Health page](https://www.servicenow.com/docs/oyW7zLXpEP5ef5YiPhWQTA "The health page shows the state of the Now LLM and AI Search, along with the states of Query Generation system properties, enabled products, and dependency plugins."). * Confirm that AI Search is active. * Verify that the Semantic Layer is built. Entities and dimensions should not be 0. For more information, see [Tables installed](https://www.servicenow.com/docs/aK39momxE_OECDBz6aOoiA#tables-sched-jobs-query-gen__section_hsw_xm3_cgc). ## Testing and validation 1. Navigate to AI Data Explorer from the main menu. 2. Try a simple question such as "Open incidents" to verify end-to-end functionality. 3. Force indicator or table selection with a few questions, such as "What do indicators show us about the number of open incidents for the last 60 days" or "What is the current number of incidents?" 4. Verify that tables you want to use are added to the semantic layer and that semantic generation is turned on for them. Task extended tables and some base tables are added by default, but custom tables that are not task-based might have to be added manually. 5. To check if a table is already in the semantic layer, navigate to Query generationEntities. If the table is in the list and marked as active, it is already configured. 6. If you want to access data in a protected scope, configure ACLs and Restricted Caller Access (RCA) records to grant access to the scope to AI Data Explorer. ## User access Grant users who need access to AI Data Explorer the now-assist-explorer-user role.{#ai-data-explorer-implementation-checklist__ai-data-explorer-implementation-checklist-para-2} ## General usage guidelines * Use short, simple questions for best results. * Only simple analytical questions are supported. Questions should be answerable with a single chart or single data source. * AI Data Explorer cannot answer general definition questions or questions requiring comparison across multiple data sources. Break down complex analysis into multiple questions. * When asking follow-up questions, use words like "these" to ensure that filters are not dropped. For example, "Of these incidents, how many are critical?" **Related concepts** * [Enabling access to protected scope applications for AI Data Explorer and Query Generation](https://www.servicenow.com/docs/KX8pB2qZXRSxQV9Oi~mx8g "AI Data Explorer and Query Generation require additional security configuration to access tables in protected scopes such as Human Resources or Employee Profile scopes.") **Related tasks** * [Add a table to the semantic data layer](https://www.servicenow.com/docs/DnI5HK_x_33jozN_85GrWQ#add-table-semantic-layer "Add more tables to the Query Generation semantic layer so that users can use ServiceNow Otto for Platform Analytics applications to ask questions about the data in those tables.") **Related reference** * [Query Generation Health page](https://www.servicenow.com/docs/oyW7zLXpEP5ef5YiPhWQTA "The health page shows the state of the Now LLM and AI Search, along with the states of Query Generation system properties, enabled products, and dependency plugins.") * [Roles, tables, and scheduled jobs included with Query Generation](https://www.servicenow.com/docs/aK39momxE_OECDBz6aOoiA "Several types of components are installed with Query Generation, including tables and scheduled jobs.") *[\>]: and then