Turn On AI in Your Tableau Server Site

Applies to: Tableau Server

Supported in Tableau Server version 2025.3 and later.

Use Tableau Agent in Tableau Desktop, Tableau Prep Builder, and on the web when you connect to Tableau Server (all editions) when AI in Tableau is configured and turned on for web authoring and Tableau Prep in the site settings.

For information about how to set up Tableau Agent for Tableau Cloud see Turn On AI in Your Tableau Cloud Site(Link opens in a new window).

AI features in Tableau can help you analyze your data more effectively. When you're using Tableau Prep, AI can suggest steps for cleaning your data and can even create calculations for you. When you're building a visualization, it can recommend insightful questions to explore your data, create calculations, and help you create compelling visualizations directly from your data sets.

For more information about using Tableau Agent to build visualizations or clean your data, see Build Views and Explore Data with Tableau Agent(Link opens in a new window) and Build Tableau Prep flows with Tableau Agent(Link opens in a new window).

AI in Tableau in Tableau Server requires you to connect to your own Large Language Model (LLM) provider. Currently, you can choose either OpenAI or Azure OpenAI for your LLM provider. The LLM provider you select is site specific. Azure OpenAI is available in Tableau Server starting in version 2026.2.

Note: Additional capacity for core-based environments is not required when using Tableau Agent in Tableau Server.

PII, data security, and multi-language support

When using Tableau AI features with your OpenAI provider, your requests don’t use the Einstein Trust Layer and its associated data governance features, including built-in PII masking. Tableau sends your user question and a small random sample of values per field to your OpenAI account.

As this process doesn't use the Einstein Trust Layer's security and PII masking features, you'll be relying on the LLM provider's security measuresto protect sensitive data. For more information, see AI in Tableau and Trust(Link opens in a new window).

Billing considerations

When connecting to Tableau Agent in Tableau Server, you'll use your own LLM instance of OpenAI or Azure OpenAI. Because your data is flowing through this dedicated connection, your requests don't go through the Einstein Trust Layer or incur any associated billing. Your usage will be billed directly, according to your specific LLM provider agreement.

Prerequisites for Enabling AI in Tableau Server

To configure and turn on Tableau Agent for Tableau Server you will need the following:

  • Tableau Server Administrator role. The AI in Tableau site setting is site specific and when turned on, enables all users with access to that site to use the AI feature.

  • An active contract with OpenAI or Azure OpenAI.

  • Your API key. You'll need this to connect Tableau Server to your OpenAI or Azure OpenAI LLM provider. We recommend following standard security best practices and rotating the API key on a regular basis.

  • If you are using Azure OpenAI, a deployed model in Azure.

  • The LLM models that Tableau Agent will use to complete tasks like understanding the user requests and returning relevant output. Tableau recommends the following models for best results:

    • Understand user requests: gpt-5-mini or gpt-4o-mini

    • Perform analytic tasks: gpt-4o or later

    • Process data context: text-embedding-3-small

Available features

The following AI in Tableau features are available in Tableau Server:

  • Tableau Web Authoring: Builds visualizations or completes tasks for you using a conversational UI: Enable users to explore data, create visualizations and calculations, and uncover insights with the assistance of Tableau Agent in Tableau Server web authoring and in Tableau Desktop (version 2025.3 and later). For more information about Tableau Agent, see Explore Your Data with Tableau Agent(Link opens in a new window).

  • Tableau Prep: Suggests steps to clean and transform your data: Enable users to clean their data, create calculated fields, and build flows with the help of Tableau Agent. This feature is available in Tableau Prep web authoring in Tableau Server and in Tableau Prep Builder (version 2025.3 and later). For more information about Tableau Agent in Tableau Prep, see Build Tableau Prep flows with Tableau Agent(Link opens in a new window).

Configure AI in Tableau

The steps for configuring AI in Tableau and the information you need to enter differs, based on the LLM provider you select. Configuring a different LLM provider per site is supported.

When you configure your LLM connection you will need to specify the models that you want the LLM to use to perform tasks.

  • Tableau Agent for Web Authoring: Uses the models specified for all processes.

  • Tableau Agent for Prep: Only uses the model specified for the Perform analytics tasks process.

This setting is universal and applies to all AI in Tableau features that you turn on.

Configure OpenAI

  1. Sign in to Tableau Server as a Server administrator.

  2. On the site where you want to turn on generative AI features, select Settings.

  3. Under AI in Tableau, click Connect.

    The Tableau Server site setting to connect to an LLM provider.

  4. In the Connect to LLM dialog, select OpenAI for the LLM provider, then enter your LLM provider's API key and click Connect.

    Tableau Agent in Tableau Server connect to OpenAI LLM dialog.

    After successfully connecting to your provider, you can also edit, test, or delete your connection as needed.

  5. For each AI in Tableau feature that you want to turn on, select Turn On.

  6. In the Model Settings dialog, select the AI models that Tableau Agent uses to complete it's processes. You must select a model for all processes in the dialog.

    If a model is no longer supported by OpenAI, users will receive errors when using Tableau Agent. Currently, you'll need to update this setting manually.

    Model settings dialog for Tableau Server and OpenAI

    Select the following models, then click Apply. These models are recommended by Tableau for optimal performance.

    • Understand user requests: gpt-5-mini or gpt-4o-mini

    • Perform analytics tasks: gpt-4o or later

    • Process data context: text-embedding-3-small

  7. At the top of the page, click Save.

    AI in Tableau site setting for Open AI.

Configure Azure OpenAI

  1. Sign in to Tableau Server as a Server administrator.

  2. On the site where you want to turn on generative AI features, select Settings.

  3. Under AI in Tableau, click Connect.

    The Tableau Server site setting to connect to an LLM provider.

  4. In the Connect to LLM dialog, select Azure OpenAI for the LLM provider, enter your LLM provider’s API key and your Resource name. You can find your Resource name in your Azure OpenAI portal in your Azure OpenAI endpoint URL. For example if your URL is “https://acme-jsmith.openai.azure.com/” your Resource name is “acme-jsmith”.

    Connect to LLM dialog for Tableau Server and Azure OpenAI.

  5. Click Connect. After successfully connecting to your provider, you can also edit, test, or delete your connection as needed.

  6. For each AI in Tableau feature that you want to turn on, select Turn On.

  7. In the Model Settings dialog, enter the AI models that Tableau Agent uses to complete it's processes. You must select a model for all processes in the dialog.

    If a model is no longer supported by Azure OpenAI, users will receive errors when using Tableau Agent. Currently, you'll need to update this setting manually.

    Model Settings dialog for Azure OpenAI.

    Select the following models, then click Apply. These models are recommended by Tableau for optimal performance.

    • Understand user requests: gpt-5-mini or gpt-4o-mini

    • Perform analytics tasks: gpt-4o or later

    • Process data context: text-embedding-3-small

  8. At the top of the page, click Save.

    AI in Tableau site setting for Tableau Server and Azure OpenAI.

Back to top
Thanks for your feedback!Your feedback has been successfully submitted. Thank you!