---
schema_version: "1"
id: 9082e9e061934d0970c1d7e4c220015e48ddf208644460425bd11f7cce26a34a
title: Set Up Tableau Agent in Tableau Next
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/analytics/264-0-0/tua_admin_enable_agentforce_templates.md
canonical_url: https://help.salesforce.com/s/articleView?id=analytics.tua_admin_enable_agentforce_templates.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 5698c2c897199a5445b46c8edf36825bcd09a2c9ff9d88f13fa33e7e690c0ff8
description: Configure users, turn on organization features, and create and activate an agent for analytics and visualizations in Tableau Next.
products:
  - Tableau Next
release: "264"
---
# Set Up Tableau Agent in Tableau Next

Configure users, turn on organization features, and create and activate an agent for analytics and visualizations in Tableau Next.

### Required Editions

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small edition"><colgroup><col></colgroup><tbody><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;"><a href="https://help.salesforce.com/s/articleView?id=analytics.tua_editions.htm&amp;language=en_US" target="_blank">View supported editions.</a></td></tr></tbody></table>

Guided setup is available for Tableau Next, including AI features. For more information, see [Guided Tableau Next Setup](https://help.salesforce.com/s/articleView?id=analytics.tua_admin_guided_setup.htm&language=en_US).

![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 June '26, Agentforce for Analytics is now Tableau Agent in Tableau Next, Concierge: Analytics Q&A is conversational analytics, Data Pro is semantic modeling, and Inspector is proactive insights. As we transition to these new terms, you may see a mix of the new and old terms in our documentation and products.

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small permission">
        <colgroup>
          <col style="width:50%">
          <col style="width:50%">
        </colgroup>
        <thead class="slds-text-title_caps ">
          <tr class="">
            <th scope="colgroup" class="slds-cell-wrap" colspan="2" style="text-align:center;vertical-align:top;" id="d4756e62">User Permissions Needed</th>
          </tr>
        </thead>
        <tbody>
          <tr class="">
            <td data-label="User Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d4756e62 ">To enable the query engine setting <strong class="uicontrol">Data Q&amp;A Indexing and Semantic
                Enrichments</strong> in Data 360</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d4756e62 ">One of View Setup and Configuration, Customize Application or System Administrator,
              Access Data Cloud or Access Data Cloud / Genie Platform</td>

          </tr>
          <tr class="">
            <td data-label="User Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d4756e62 ">To assign permission sets, configure organization settings, and enable Einstein,
              Agentforce, Tableau Next, and Agentforce for Analytics:</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d4756e62 ">System Administrator</td>

          </tr>
        </tbody>
      </table>

## Assign User Permission Sets

Users need the following permission sets to access Tableau Agent templates in Agentforce.

- One of Tableau Unmetered Admin or Tableau Next Admin, Tableau Unmetered Platform Analyst or Tableau Next Platform Analyst, Tableau Unmetered Self-Service Analyst or Tableau Next Self-Service Analyst, Tableau Unmetered Self-Service Consumer or Tableau Next Self-Service Consumer, or Tableau Unmetered Consumer or Tableau Next Consumer
- Data Cloud User (required for all users)

1. From Setup, in the Quick Find box, enter Permission, and select **Permission Sets**.
2. Select a permission set: **Tableau Unmetered Admin or Tableau Next Admin**, **Tableau Unmetered Platform Analyst or Tableau Next Platform Analyst**, **Tableau Unmetered Self-Service Analyst or Tableau Next Self-Service Analyst**, Tableau Unmetered Self-Service Consumer or Tableau Next Self-Service Consumer, or **Tableau Unmetered Consumer or Tableau Next Consumer**.
3. Click **Manage Assignments**.
4. Click **Add Assignments**.
5. Select one or more users by checking the box next to their name.
6. Click **Assign**.
7. Perform these steps again for the same users, selecting the **Data Cloud User** permission set.

Repeat this process for users in other roles that need access to Tableau Agent templates in Agentforce.

## Enable Tableau Next, Einstein, and Agentforce

Tableau Agent requires that Tableau Next, Einstein, and Agentforce are set up and configured in your organization. Perform these steps if you haven't yet.

1. [Enable Tableau Next](https://help.salesforce.com/s/articleView?id=analytics.tua_admin_enable_tableau.htm&release=264.0.0&type=5 "Turn on Tableau Next. This also assigns you a Data Cloud Architect and Tableau Unmetered Admin permission set.").
2. [Enable Agentforce](https://help.salesforce.com/s/articleView?id=ai.agent_setup_enable.htm&language=en_US).
3. [Enable Einstein Generative AI for Tableau Next](https://help.salesforce.com/s/articleView?id=analytics.tua_admin_enable_ai.htm&release=264.0.0&type=5 "Einstein Generative AI provides summaries and automated visuals in Tableau Next. Tableau requires Einstein generative AI and the Einstein Trust Layer to access AI features. You also need to turn on Einstein generative AI data collection to save feedback and auditing data.").
    1. [Set up Einstein Generative AI](https://help.salesforce.com/s/articleView?id=ai.generative_ai_enable.htm&type=5&language=en_US).
    2. [Set up Einstein Trust Layer](https://help.salesforce.com/s/articleView?id=ai.generative_ai_trust_setup.htm&type=5&language=en_US).
    3. [Turn on Einstein Generative AI data collection and storage](https://help.salesforce.com/s/articleView?id=ai.generative_ai_feedback_enable.htm&type=5&language=en_US).

## Confirm Data Q&A Indexing and Semantic Enrichments is Enabled in Data 360

The Data Q&A Indexing and Semantic Enrichments setting must be enabled in Data 360 for the Home org before you can turn on the Data Analysis setting in Tableau Next Features > Settings.

To access Data Cloud Setup > Feature Manager and turn on the Data Q&A Indexing and Semantic Enrichments setting, you'll need one of the following permission sets:

- View Setup and Configuration
- Customize Application or System Administrator
- Access Data Cloud or Access Data Cloud / Genie Platform

1. Go to **Data Cloud Setup**.
2. Under Feature Management, click **Feature Manager**.
3. Confirm the **Data Q&A Indexing and Semantic Enrichments** setting is enabled.
4. Agree to the terms and service, and then confirm that you want to enable it.

Enabling the Data Q&A Indexing and Semantic Enrichments setting in Data 360 updates semantic models for new agent capabilities in the Home org and all Companion orgs. Depending on your data, this operation can take up to several hours. For [Q&A Calibration](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_qa_calibration.htm&type=5&language=en_US), questions in Verified Question lists for preexisting agents will be marked as Needs Verification. These questions can be revalidated with existing and new agents.

The Data Q&A Indexing and Semantic Enrichments setting must be enabled in Data 360 for the Home org. If you are using Companion orgs, the Data Q&A Indexing and Semantic Enrichments setting must be enabled on the Home org but the Tableau Agent and Data Analysis settings must be enabled on the Companion org.

## Activate Tableau Agent in Tableau Next

Tableau Agent is a collection of pre-built agentic capabilities made available through the Analytics and Visualization agent template. Turning these settings on in Tableau Next makes the Analytics and Visualization agent template and its subagents and actions available to you in Agentforce Builder and Agentforce Studio.

1. In Tableau Next, click **Administration**, and then click **Settings**.
2. Under General Settings, click **Tableau Next Features**.
3. Turn on **Tableau Agent** to enable the **Analytics and Visualization** template in Agentforce Builder and Agentforce Studio.
4. Turn on **Data Analysis** to enable the **Data Analysis** subagent in Agentforce Builder or Agentforce Studio.
5. Optional: Turn on **Q&A Calibration (Beta)**. You can access this tool in the Tableau Next menu to test questions in an agent that uses Data Analysis, and then verify and calibrate results. For more information, see [Use Q&A Calibration to Improve Accuracy in Tableau Agent](https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_qa_calibration.htm&type=5&language=en_US).
6. Optional: Turn on **Semantic Model Curation (Beta)** and other semantic layer AI-readiness features to build and refine semantic models. This setting isn't required for Tableau Agent, but it enables useful tools for improving AI readiness in semantic models used by agents. <table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small ">
            <tbody><tr class="">
              <th style="vertical-align:top;" headers="d4756e460-option" id="d4756e464">Semantic Model Curation (Beta) </th>

              <td style="vertical-align:top;" headers="d4756e460-desc d4756e464">
                <p>Enables the Semantic Modeling template in Agentforce Builder and Agentforce Studio. Also
                  enables other non-agentic AI capabilities in the Semantic Model Builder. For more
                  information, see <a href="https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_semantic_modeler.htm&amp;type=5&amp;language=en_US" target="_blank">Create and Refine Semantic Models with Semantic
                    Modeling</a> and <a href="https://help.salesforce.com/s/articleView?id=analytics.tua_data_sdm_semantic_modeler_setup.htm&amp;type=5&amp;language=en_US" target="_blank">Set Up Semantic Modeling (Beta)</a>.</p>
              </td>

            </tr>
            <tr class="">
              <th style="vertical-align:top;" headers="d4756e460-option" id="d4756e484">Semantic Built-In AI</th>

              <td style="vertical-align:top;" headers="d4756e460-desc d4756e484">Accelerates and streamlines semantic model creation and maintenance.</td>

            </tr>
            <tr class="">
              <th style="vertical-align:top;" headers="d4756e460-option" id="d4756e493">Semantic Model AI Optimization (Beta)</th>

              <td style="vertical-align:top;" headers="d4756e460-desc d4756e493">Anables automated checks on semantic data models to detect optimization
                opportunities. This tool surfaces issues with guided resolutions to improve model quality
                and reliability for AI-powered agents and analytics.</td>

            </tr>
            <tr class="">
              <th style="vertical-align:top;" headers="d4756e460-option" id="d4756e502">Semantic Description Generator (Beta)</th>

              <td style="vertical-align:top;" headers="d4756e460-desc d4756e502">Drafts descriptions for your semantic model entities with AI. Accurate descriptions
                boost agent response accuracy. Be sure to review and edit suggestions before
                saving.</td>

            </tr>
          </tbody></table>

![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

Tableau Agent requires well-designed semantic models to understand data and confidently answer questions. AI-readiness features add context, enrich, and calibrate semantic models so you can actively test, refine, and deepen an agent's understanding of your business.

## Create an Agent with the Analytics and Visualization Template

Use the Analytics and Visualization V2 template to create a new agent and assign it to users.

- To build and manage Tableau Agent, which is an Agentforce Employee Agent, you'll need the Manage AI Agents or Customize Application system permission.
- To update Tableau Next settings, you'll need the Tableau Next Admin permission set.

![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 July '26, to create a Tableau Agent with conversational analytics, you must use the new Analytics and Visualization V2 template and its Data Analysis subagent. Admins must start in the Agentforce Studio app to create a new agent.

To enable conversational analytics in Tableau Agent, follow the steps in [Create a Tableau Agent for Conversational Analytics in Tableau Next.](https://help.salesforce.com/s/articleView?id=analytics.tua_admin_data_analysis_subagent.htm&type=5&language=en_US)

## Verify the New Agent in Tableau Next

Verify that users can select the new agent from Agentforce in Tableau Next, ask questions in the agent, and receive a response.

1. Open a metric or dashboard in Tableau Next.
2. Click the Agentforce button ![Agentforce icon](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-tua-264-0-0-production-enus/d794334f-d174-49d3-a4d2-a615bd2e54aa/tua/images/agentforce_icon.png) to open the Agentforce panel.
3. In the Select Agent list, choose the new agent.
4. Ask a question about the data and verify a response is generated.

If a semantic model isn’t configured for use with Tableau Agent, you may be prompted to complete Analytics Agent Readiness enablement. For more information, see [Enable Analytics Agent Readiness](https://help.salesforce.com/s/articleView?id=analytics.c360_a_sl_agent_readiness_enable.htm&language=en_US&type=5).

Set up [Agent Scoping](https://help.salesforce.com/s/articleView?id=analytics.tua_admin_enable_agent_scoping.htm&language=en_US&type=5) to specify a fallback list of semantic models to serve as context for the agent in situations where the context is ambiguous. Click the LLM Model tab to configure the model mode as Best Performance (offers faster responses) or Best Accuracy (offers enhanced reasoning).