# Draft with Einstein, Suggest Relationships and Data Pro

*Tableau Next Consultant Study Guide · Agentic Experiences · Last updated November 13, 2026 · https://www.certifyforce.com/study-guide/tableau-next-consultant/agentic-experiences/draft-with-einstein-suggest-relationships-and-data-pro*

How Tableau Next's generative AI authoring tools build semantic model components: Draft with Einstein for calculated fields, AI Semantic Description Generator (Beta) for descriptions, Suggest Relationships for key-based joins, and Semantic Modeling (Beta, formerly Data Pro) for generating and refining whole models through conversation.

- Certification: Salesforce Tableau Next Consultant
- Exam section: Agentic Experiences
- Study guide: https://www.certifyforce.com/study-guide/tableau-next-consultant

**Official exam objective:**

> Understand how generative AI capabilities support the creation of Tableau Next components.

## What the exam expects

- Pick the generative AI tool that produces the component a modeler needs: a calculated field, a description, a relationship or a whole model.
- Write a Draft with Einstein request and explain what happens to the generated calculated field after saving.
- Apply AI Semantic Description Generator (Beta) to objects, fields and calculated fields, including its prerequisites and fallback behaviour.
- Judge which fields and objects Suggest Relationships can use, and act on a recommendation with Review, Apply or Reject.
- Explain what Semantic Modeling (Beta) generates, its scope limits, and the controls in its conversational and single-prompt workflows.

Key terms:
- **Draft with Einstein:** the AI option in the New Calculated Field window that drafts a calculated field from a plain-language description.
- **AI Semantic Description Generator (Beta):** the Generate button in a description field that drafts metadata text for agents.
- **Suggest Relationships:** AI recommendations for relationships between objects in the Semantic Model Builder.
- **Semantic Modeling (Beta):** the agent that generates or refines a semantic model from natural language; older pages call it Data Pro or Semantic Modeler.

## Key facts

| Fact | Detail | Source |
|---|---|---|
| Draft with Einstein prerequisites | Data Pro - Semantic Authoring AI in Data 360 Feature Manager plus Turn on Einstein | [Create a Calculated Field with Einstein](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_calc_fields_create_ai.htm&type=5&language=en_US) |
| Saved Einstein calculated field | Added to the semantic model; usable to create relationships | [Create a Calculated Field with Einstein](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_calc_fields_create_ai.htm&type=5&language=en_US) |
| Calculated field description | Generate works only on a valid calculated field | [Calculated Field Descriptions (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_desc_gen_use_calc.htm&type=5&language=en_US) |
| Standard object, no custom description | Agents use the existing standard description | [Data Object Descriptions (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_desc_gen_use.htm&type=5&language=en_US) |
| Suggest Relationships field types | Numbers and text up to 50 characters; primary and foreign keys only | [Suggest Relationships](https://help.salesforce.com/s/articleView?id=analytics.c360_a_sl_create_rel_with_einstein.htm&type=5&language=en_US) |
| Unsupported objects for suggestions | Logical View and Shared Dimension data objects | [Suggest Relationships](https://help.salesforce.com/s/articleView?id=analytics.c360_a_sl_create_rel_with_einstein.htm&type=5&language=en_US) |
| Reject | That specific recommendation is no longer shown | [Suggest Relationships](https://help.salesforce.com/s/articleView?id=analytics.c360_a_sl_create_rel_with_einstein.htm&type=5&language=en_US) |
| Semantic Modeling scope | Objects, relationships, calculated fields; not metrics, groups, logical views | [Semantic Modeling (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_semantic_modeler.htm&type=5&language=en_US) |
| Recommendation scan limit | Up to 100 tables across the user's workspaces | [Semantic Modeling (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_semantic_modeler.htm&type=5&language=en_US) |
| Ignore in conversation | Cancels generation or the refinement request | [Create with Semantic Modeler (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_semantic_modeler_create.htm&type=5&language=en_US), [Refine with Semantic Modeling (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_semantic_modeler_refine.htm&type=5&language=en_US) |

## Check yourself

- What does Suggest Relationships base its recommendations on?
- When you finish editing an AI-drafted description on a data object field, which button saves it?
- Why might relationship suggestions appear in a model where nobody clicked a separate setting for them?
- When an admin wants to turn on Semantics AI in Tableau Next, which permission sets allow it?

## Sources

- [Create a Calculated Field with Einstein](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_calc_fields_create_ai.htm&type=5&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&type=5&language=en_US)
- [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&type=5&language=en_US)
- [Create a Relationship with Suggest Relationships](https://help.salesforce.com/s/articleView?id=analytics.c360_a_sl_create_rel_with_einstein.htm&type=5&language=en_US)
- [Create and Refine Semantic Models with Semantic Modeling (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_semantic_modeler.htm&type=5&language=en_US)
- [Create a Semantic Model with Semantic Modeler (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_semantic_modeler_create.htm&type=5&language=en_US)
- [Refine an Existing Semantic Model with Semantic Modeling (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_semantic_modeler_refine.htm&type=5&language=en_US)
- [Tableau Agent in Tableau Next](https://help.salesforce.com/s/articleView?id=analytics.tua_ai.htm&type=5&language=en_US)
- [Enable Semantics AI in Tableau Next (Beta)](https://help.salesforce.com/s/articleView?id=analytics.tua_admin_enable_semantics_ai.htm&type=5&language=en_US)

## About the full unit

The "Core concepts", "Exam traps" and "Worked scenario" sections of this unit, its 19 linked practice questions, and unlimited timed mock exams are included with the Tableau Next Consultant pack (USD $19): https://www.certifyforce.com/practice-exams