Agentic Experiences25% of the exam
Analytics Agent Readiness and semantic model optimization
How to mark a semantic model ready for the Analytics Agent (Tableau Agent), set Primary Name Fields, respect the model features agents support, and use Semantic Model AI Optimization (Beta) and Similar Meanings (Beta) to find and fix description gaps, disconnected objects and ambiguous definitions.
Explain how to assess and ensure Agentic readiness.
~7 min read · 19 practice questions
What the exam expects
- Explain what the Analytics Agent Readiness property does, how a modeler enables it, and what happens to models without it.
- Configure a Primary Name Field on a table or logical view and tell it apart from the primary key.
- Recognise model features agents cannot use and the description practices that make data values interpretable.
- Enable and read Semantic Model AI Optimization (Beta): the scan, the Optimize Model label, Model Health checks and recalculation.
- Run and resolve Similar Meanings (Beta), including its statuses, review details and scope limits.
Key terms:
- Analytics Agent Readiness: a model property marking a semantic model mature and usable by the Analytics Agent.
- Primary Name Field: the field that names each record for display in agent answers.
- Model Health: the overall AI-readiness rating, Low, Moderate or High, from AI Optimization checks.
- Similar Meanings (Beta): an AI scan for definitions that are "two names for one thing" or "the same name for different things".
Key facts
Model not enabled for the agent
- Detail
- The agent displays an error message
Readiness checklist
- Detail
- Modeler checks every item by judgment; Enable activates only then
After enabling readiness
- Detail
- Development continues, aligned with the guidelines
Primary Name Field vs primary key
- Detail
- Display name vs unique identifier; settable on tables and logical views
Calculated Insights
- Detail
- Not currently supported in agentic semantic models
Enabling AI Optimization
- Detail
- Scans all semantic models; adds the Optimize Model label
Strength recalculation
- Detail
- Automatic on publish or save draft; manual from model, panel or management page
Similar Meanings statuses
- Detail
- Unresolved; Pending Evaluation once acted on
Similar Meanings scope
- Detail
- Names and descriptions; no parameters; no extended models
PDS-based models in the scan
- Detail
- Only Description and Field Visibility editable
Sources for this section (8)
- Analytics Agent Readinesshelp.salesforce.com (opens in a new tab)
- Enable Analytics Agent Readinesshelp.salesforce.com (opens in a new tab)
- Primary Name Fieldhelp.salesforce.com (opens in a new tab)
- Set a Primary Name Fieldhelp.salesforce.com (opens in a new tab)
- Design for AI Readinesshelp.salesforce.com (opens in a new tab)
- Enable AI Optimization (Beta)help.salesforce.com (opens in a new tab)
- Using AI Optimization (Beta)help.salesforce.com (opens in a new tab)
- Similar Meanings (Beta)help.salesforce.com (opens in a new tab)
- What confirms in the builder that a model was enabled for the agent?
- When you choose Clarify Field Description for a flagged pair, which existing feature can draft the new text?
- When a reviewer faces a long list of pairs, which tip narrows it to pending work?
- Why does Help call a meaningful Primary Name Field essential?
The questions are free to read. Answers with their sources and self-grading are included with the pack.
Keep reading with the Tableau Next Consultant pack
- Core concepts
- Exam traps
- Worked scenario
The pack includes:
- All 21 lessons of the Tableau Next Consultant guide, with reading progress
- Interactive decision walks and step-by-step sequence steppers
- Practice exams purchase adds inline bank questions and topic practice (19 questions for this lesson)
- An official source cited for every claim
- An AI tutor that answers from the guide
- Choose guide-only, practice-only, or save $4 with both