Tableau Semantics within Tableau Next gives you the power to create semantic models and then build metrics upon them. You can also use semantic models to create calculated fields in your visualizations.
Required Editions
| View supported editions. |
- Semantic Models in Tableau Next
With semantic models, your data becomes unified into a single source of truth, accessible throughout Salesforce. Semantic models provide a way for your data to be interpreted consistently across Salesforce by mapping it to standardized business terms and logic. Semantic models are first-class Salesforce metadata, so they’re available throughout Data 360 to power analytics and data-driven experiences. - About Metrics
A metric is a business KPI that you can track over time and use to assess performance or business processes. A metric is derived from one or more measures. You can apply a sentiment to a metric (for example, up is good or bad), aggregation (for example, sum, non-cumulative, average, minimum, maximum), and other business contexts. - Semantic Model AI Optimization (Beta)
Semantic Model AI Optimization (Beta) helps data teams prepare their Semantic Models for use with AI agents such as Concierge: Analytics Q&A. It evaluates a semantic model's quality, identifies inefficiencies, and offers guided resolutions to improve model reliability for AI-powered analytics. - AI-Generated Descriptions in Semantic Models (Beta)
Quickly draft comprehensive descriptions for semantic data objects by using Einstein. This input is crucial for conversational analytics, giving AI agents the context they need for accurate discovery and insights. - Use Q&A Calibration to Improve Accuracy in Tableau Agent (Beta)
When Q&A Calibration is enabled in Tableau Next, analysts and data experts can test and verify questions and answers for Tableau Agent with the Data Analysis subagent, based on the selected analytics agent and its associated semantic model. Through evaluating questions to determine if questions are accurate (verified) or inaccurate, analysts can provide valuable input that your analytics agents can use to respond consistently and accurately to semantically similar questions. - Regression Testing for Verified Queries in Q&A Calibration
Regression testing compares a new Tableau Agent answer with the verified query you saved. A match stays Verified. A mismatch becomes Regression.