--- schema_version: "1" id: 2e5058979f5326b818b270fe5165414dca2e4c4e8115d96e9a3c39b91febd9a0 title: Build an AI-Ready Semantic Model collection: admin version: current locale: en-us portal_url: https://docs.salesforce.com/admin/current/en-us/analytics/264-0-0/tua_ai_build_guide.md canonical_url: https://help.salesforce.com/s/articleView?id=analytics.tua_ai_build_guide.htm&release=264.0.0&type=5 source_site: help.salesforce.com content_type: documentation content_hash: 504a3fcf7ea535c750a6d6535e336af48f74e519921ca98d3fe51c2fb8760038 description: A well-designed semantic model helps analytics agents understand data and confidently answer questions. You'll need to make your semantic model AI-ready to provide real-world context and reduce ambiguity for your agents. Success with using Tableau Agent in Tableau Next requires the agent to be grounded with an AI-ready semantic model. products: - Tableau Next release: "264" --- # Build an AI-Ready Semantic Model A well-designed semantic model helps analytics agents understand data and confidently answer questions. You'll need to make your semantic model AI-ready to provide real-world context and reduce ambiguity for your agents. Success with using Tableau Agent in Tableau Next requires the agent to be grounded with an AI-ready semantic model. ### Required Editions
View supported editions.
## Prerequisites - Set up Tableau Next - Connect data in Data 360 - Enable Tableau Agent with Data Analysis and Semantic Modeler (Beta) 1. **[Understand AI-readiness in semantic models](https://help.salesforce.com/s/articleView?id=analytics.tua_ai_build_guide.htm&release=264.0.0&type=5)** Building the semantic model requires following best practices as you design and define it. Tableau Next also provides tools to help you make the semantic model ready for use with Tableau Agent. 2. **[Select a semantic model](https://help.salesforce.com/s/articleView?id=analytics.tua_ai_build_guide.htm&release=264.0.0&type=5)** Create a semantic model or use one that already exists. Add data model objects (DMOs) and define relationships. You can do this manually, or with AI-assistance using Einstein or Data Pro in the Semantic Model Builder. 3. **[Create calculated fields](https://help.salesforce.com/s/articleView?id=analytics.tua_ai_build_guide.htm&release=264.0.0&type=5)** If needed, create calculated fields. You can do this manually, or with AI-assistance using Einstein or Data Pro in the Semantic Model Builder. For example, you might create calculated fields for KPIs of interest or for dimension fields that don't physically exist in your data set. 4. **[Add descriptions](https://help.salesforce.com/s/articleView?id=analytics.tua_ai_build_guide.htm&release=264.0.0&type=5)** Add descriptions to reduce ambiguity in objects and calculated fields. You can do this manually, or use AI-generated descriptions. 5. **[Define business preferences](https://help.salesforce.com/s/articleView?id=analytics.tua_ai_build_guide.htm&release=264.0.0&type=5)** Add business preferences to define business-specific knowledge within the semantic model. You will want to provide tailored business preferences for unique jargon, logic, and concepts in your domain. You can revisit this step during optimization as you test and refine the model more. 6. **[Define metrics](https://help.salesforce.com/s/articleView?id=analytics.tua_ai_build_guide.htm&release=264.0.0&type=5)** Define metrics in the semantic model for high-impact and highly-used calculated fields or field measures. Metrics contain targeted calculations, time-scoped logic, contextual filters, and formatting. They provide context that guides agents in understanding where and when specific logic applies. 7. **[Enable agent readiness](https://help.salesforce.com/s/articleView?id=analytics.tua_ai_build_guide.htm&release=264.0.0&type=5)** Enable the semantic model for use with an agent created from the Analytics and Visualization template. 8. **[Validate model](https://help.salesforce.com/s/articleView?id=analytics.tua_ai_build_guide.htm&release=264.0.0&type=5)** Validate and test the model in the Semantic Model Builder to make sure that it’s complete: all required DMOs, relationships, and calculated fields are included. Also make sure metrics and calculated fields aren't duplicated in the model. ## Understand AI-readiness in semantic models Building the semantic model requires following best practices as you design and define it. Tableau Next also provides tools to help you make the semantic model ready for use with Tableau Agent. Familiarize yourself with the concepts in [Design Semantic Models for AI Readiness](https://help.salesforce.com/s/articleView?id=analytics.tua_ai_sm_design.htm&release=264.0.0&type=5 "A well-designed semantic model is the key to getting accurate and relevant insights with agentic analytics in Tableau Next. It helps your analytics agents understand the data and confidently answer questions. When designing your semantic model, build on a foundation of AI readiness standards and well-established industry best practices for data modeling and data quality."). ## Select a semantic model Create a semantic model or use one that already exists. Add data model objects (DMOs) and define relationships. You can do this manually, or with AI-assistance using Einstein or Data Pro in the Semantic Model Builder. ### How To - [Add a Semantic Model to Tableau Next](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_add_metrics.htm&language=en_US) - [Generate a Semantic Model with Data Pro (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_auto_sm_na.htm&language=en_US) - [Relationships in Semantic Models](https://help.salesforce.com/s/articleView?id=analytics.c360_a_sl_relationship.htm&language=en_US) - [Create a Relationship with Suggest Relationships](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_suggest_rel.htm&language=en_US) ### Related Design Concepts - Structure the data model for agent confidence - Define clear object and field names - Detect and resolve ambiguities - Use and assign explicit semantic field types ## Create calculated fields If needed, create calculated fields. You can do this manually, or with AI-assistance using Einstein or Data Pro in the Semantic Model Builder. For example, you might create calculated fields for KPIs of interest or for dimension fields that don't physically exist in your data set. ### How To - [Create a Calculated Field](https://help.salesforce.com/s/articleView?id=analytics.c360_a_sl_calc_fields_create.htm&language=en_US) - [Create a Calculated Field with Einstein](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_calc_fields_create_ai.htm&language=en_US) ### Related Design Concepts - Manage similar calculated fields - Use predefined calculated fields strategically ## Add descriptions Add descriptions to reduce ambiguity in objects and calculated fields. You can do this manually, or use AI-generated descriptions. ### How To - [Draft Data Object Descriptions With AI Semantic Description Generator (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_desc_gen_use.htm&language=en_US) - [Draft Calculated Field Descriptions With AI Semantic Description Generator (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_desc_gen_use_calc.htm&language=en_US) ### Related Design Concept - Provide informative, balanced descriptions ## Define business preferences Add business preferences to define business-specific knowledge within the semantic model. You will want to provide tailored business preferences for unique jargon, logic, and concepts in your domain. You can revisit this step during optimization as you test and refine the model more. For example, if you know that the term "ROI" is referring to Advertising Spend, you can write a business preference to let the agent know ROI means Advertising Spend. ### How To - [Add Business Preferences](https://help.salesforce.com/s/articleView?id=analytics.c360_a_sl_biz_preferences_set.htm&language=en_US) ### Related Design Concepts - [Best Practices for Adding Business Preferences](https://help.salesforce.com/s/articleView?id=analytics.c360_a_sl_biz_preferences_bestp.htm&language=en_US) - Detect and resolve ambiguities ## Define metrics Define metrics in the semantic model for high-impact and highly-used calculated fields or field measures. Metrics contain targeted calculations, time-scoped logic, contextual filters, and formatting. They provide context that guides agents in understanding where and when specific logic applies. Any calculated field that appears frequently in analysis or decision-making is a good candidate to be upgraded to a metric. ![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-tua-264-0-0-production-enus/d794334f-d174-49d3-a4d2-a615bd2e54aa/images/icon_note.png) Note As part of this step, also review related visualizations and dashboards you’ve created based on the semantic model. Make sure the data makes sense and names of fields are understandable for your users. ### How To - [Add a Metric to a Semantic Model](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_add_metrics.htm&language=en_US) - [Build Insightful Visualizations in Tableau Next](https://help.salesforce.com/s/articleView?id=analytics.tua_create_viz.htm&language=en_US) - [Create Effective Dashboards With Tableau Next](https://help.salesforce.com/s/articleView?id=analytics.tua_create_dashboard.htm&language=en_US) ### Related Design Concepts - Enrich semantic models with focused semantic components - Metrics act as semantic anchors ## Enable agent readiness Enable the semantic model for use with an agent created from the Analytics and Visualization template. Analytics Agent Readiness is a setting that marks a semantic model as mature and ready for use by an analytics agent. This step is required to be able use the analytics agent. ![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-tua-264-0-0-production-enus/d794334f-d174-49d3-a4d2-a615bd2e54aa/images/icon_note.png) Note Admins can create fallback lists of semantic models per agent for scenarios where the semantic context isn't clear. For more information, see [Set Up Agent Scoping for Tableau Agent](https://help.salesforce.com/s/articleView?id=analytics.tua_admin_enable_agent_scoping.htm&language=en_US). ### How To - [Enable Analytics Agent Readiness](https://help.salesforce.com/s/articleView?id=analytics.c360_a_sl_agent_readiness_enable.htm&language=en_US) ## Validate model Validate and test the model in the Semantic Model Builder to make sure that it’s complete: all required DMOs, relationships, and calculated fields are included. Also make sure metrics and calculated fields aren't duplicated in the model. Use [Semantic Model AI Optimization (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_model_opt.htm&language=en_US) to gain clear visibility into your semantic model's health and AI-readiness, and see suggested recommendations to improve it. This tool runs a series of automated checks against your semantic model and calculates an overall model health for AI-readiness. Use [Q&A Calibration (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_qa_calibration.htm&language=en_US) in Tableau Next to improve accuracy in Tableau Agent. Test questions in Tableau Agent and validate the agent’s answers against your specific data and rules. The list of Verified questions that you compile and save improves agent accuracy for similar questions. When you mark a question as Inaccurate, you can further fine-tune business preferences, update fields and metadata, and update calculations to improve accuracy and performance. After you make the changes, you can retest the questions until they are accurate. ![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-tua-264-0-0-production-enus/d794334f-d174-49d3-a4d2-a615bd2e54aa/images/icon_note.png) Note After using Q&A Calibration, you can also use manual testing to determine if the model is complete and generates the queries you are expecting. ### How To - [Test a Semantic Model](https://help.salesforce.com/s/articleView?id=analytics.c360_a_sl_testing_smodel_test.htm&language=en_US) - [Semantic Model AI Optimization (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_model_opt.htm&language=en_US) - [Use Q&A Calibration to Improve Accuracy in Tableau Agent (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_qa_calibration.htm&language=en_US) - [Optimize and Test the Semantic Model](https://help.salesforce.com/s/articleView?id=analytics.tua_ai_optimize_model.htm&language=en_US) ### Related Design Concepts - Detect and resolve ambiguities - Use and assign explicit semantic field types