---
schema_version: "1"
id: 8b1060ae25dc9d932534d8590978ace3f3131013b834df0f9fa6212eb08c464d
title: Select a Model Response Type for Tableau Agent
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/analytics/264-0-0/tua_admin_agent_settings_model_response.md
canonical_url: https://help.salesforce.com/s/articleView?id=analytics.tua_admin_agent_settings_model_response.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 23345fdad39dc3dbec8b8753f5d612c48f26c703ce635b6b19986e96aa559932
description: Admins can select an LLM model response setting for each agent using Agent Settings in Tableau Next. Applies to agents based on the Analytics and Visualization template or a custom agent that uses the Data Analysis subagent.
products:
  - Tableau Next
release: "264"
---
# Select a Model Response Type for Tableau Agent

Admins can select an LLM model response setting for each agent using Agent Settings in Tableau Next. Applies to agents based on the Analytics and Visualization template or a custom agent that uses the Data Analysis subagent.

### Required Editions

Admins can choose between response speed and reasoning quality for different business scenarios.

- Best Accuracy (Default): Advanced reasoning for complex queries, multi-step analysis, and mission-critical insights.
- Best Performance: Optimized for speed—ideal for simple aggregations and high-volume queries.

For example, an agent used for Sales analytics could use Best Performance for fast answers to questions like "top deals this month" during live calls, while an agent used for Finance analytics could use Best Accuracy for complex fiscal calendar and hierarchy analysis.

The setting applies to all interaction surfaces of Tableau Agent.

<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>

<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="d41293e72">User Permissions Needed</th>
          </tr>
        </thead>
        <tbody>
          <tr class="">
            <td data-label="User Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d41293e72 ">To select the model response in Agent Settings:</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d41293e72 ">Tableau Unmetered Admin or Tableau Next Admin permission set</td>

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

1. In Tableau Next home, click **Agent Settings**.
2. Select the agent you want to configure. Only active agents in the org that use the Data Analysis topic are available.
    
    Agents can be based on the Analytics and Visualization agent template or a custom agent based on the Agentforce Employee Agent template.
3. Click the **LLM Model Selection** tab.
    
    - Select a response option:
    
    - Best Accuracy (Default): Advanced reasoning for complex queries, multi-step analysis, and mission-critical insights.
    - Best Performance: Optimized for speed—ideal for simple aggregations and high-volume queries.
4. Click **Save**.

Tableau Agent default settings use models from multiple vendors. The mix of vendors (such as OpenAI, Anthropic, and others) and models may change over time to optimize accuracy and performance.

If your organization has regulatory, data residency, or other data governance requirements, custom model configurations are available on request. Contact your account team or submit a request during the onboarding process, and a Salesforce representative will work with you to configure your environment to meet your requirements.