Find answers to commonly asked questions about using Tableau Agent in Tableau Desktop, Tableau Cloud and Tableau Server web authoring. To learn more about Tableau Agent in Tableau Prep or Tableau Catalog, see Build Tableau Prep Flows with Tableau Agent(Link opens in a new window) or Describe projects, workbooks, or data sources(Link opens in a new window).

General Information

What is Tableau Agent?

Tableau Agent is a generative AI feature in Tableau that can help you explore data, create visualizations, and uncover insights using a conversational assistant. It allows you to interact with your data through natural language in Tableau Desktop, Tableau Prep, and when using web authoring in Tableau Cloud and Tableau Server.

Is there a free trial?

Yes. You can sign up for a Tableau Cloud free trial which now includes Tableau Agent features. Simply fill out this form, or contact your Account Executive. You can currently try Tableau Agent in Tableau Desktop (starting in 2025.1), Tableau Cloud web authoring, Tableau Prep Builder (starting in 2025.2), and Tableau Prep on the web as part of a limited trial.

Starting in July 2026, you can also try Tableau Agent in Dashboards. This Beta feature enables you to get an overview about your dashboard, get a summary of insights, viz-by-viz, and ask questions about your data using natural language. For more information, see Tableau Agent in Dashboards(Link opens in a new window).

The trial gives you full access to Tableau Agent functionality but there are some restrictions on the overall experience.

• You can only trial in a new site, not add a trial of Tableau Agent to your existing production site.

• Tableau Agent in Tableau Catalog isn't included in the trial.

• Tableau Agent in Tableau Desktop is supported for Viz Authoring or configuring Tableau Agent in Dashboard settings.

• Tableau Agent is free to use during the trial but limits may apply to the number of requests you can make per hour.

How do I access Tableau Agent?

To access Tableau Agent, click the Tableau Agent icon in the toolbar next to Show Me or at the top of the toolbar while connected to a data source. Availability depends on the application, site connection type, feature settings, and permissions:

• Tableau Desktop: Available in worksheets when signed into:

  • A Tableau Cloud site with Tableau+ or Tableau Cloud+, (or Tableau Cloud free trial) with AI in Tableau turned on for web authoring.

  • A Tableau Server site with AI in Tableau turned on for web authoring.

• Tableau Prep: Available in Prep flows (web or Prep Builder) when signed into:

  • A Tableau Cloud site with Tableau+ or Tableau Cloud+, (or Tableau Cloud free trial) with AI in Tableau turned on for Tableau Prep.

  • A Tableau Server site with AI in Tableau turned on for Tableau Prep.

• Tableau Web Authoring: Available when AI in Tableau is turned on for your site and you are assigned a Creator or Explorer role:

  • Worksheet tabs: Supported on both Tableau Cloud and Tableau Server. Requires Tableau+ or Tableau Cloud+, (or Tableau Cloud free trial).

  • Dashboard tabs: Supported on both Tableau Cloud and Tableau Server version 2026.3 and later (requires Tableau Server+)

    Note: If Tableau Server connects through a Custom Gateway using OAuth authentication, Tableau Agent in Dashboards is not supported.

• Dashboard Viewers (web): Viewers can access Tableau Agent in Dashboards (Tableau Cloud version 2026.2.4 and later and Tableau Server version 2026.3 and later). Tableau Agent in Dashboards must be is turned on in the site settings, the capabilities must be turned on for the dashboard, and the user must be granted both AI Access and Full Data Query permissions.

More information:

• Explore Your Data with Tableau Agent(Link opens in a new window)

• Build Tableau Prep Flows with Tableau Agent(Link opens in a new window)

• Build Views and Explore Data with Tableau Agent(Link opens in a new window)

• Tableau Agent in Dashboards (Beta)(Link opens in a new window)

• Turn on AI in Tableau for your Tableau Cloud Site(Link opens in a new window)

• Turn on AI in Your Tableau Server Site(Link opens in a new window)

Can I limit user access to Tableau Agent?

Yes. You can turn on AI in Tableau features for either a single user group or for all users on your site. Currently this option is only available when configuring AI in Tableau in Tableau Cloud for Viz Authoring and Tableau Prep. This option is not currently available when turning on AI in Tableau in Tableau Server. For more information, see Configure AI in Tableau(Link opens in a new window).

For Tableau Agent in Dashboards (Beta), you can control access using the Permissions settings. For more information, see Permissions(Link opens in a new window).

Why is the Tableau Agent button not available?

Note: Tableau Agent is not supported if you’re using a Salesforce Government Cloud Org.

To use Tableau Agent, the following must be true:

• You must be connected to a Tableau Cloud site that has Tableau Cloud+ or Tableau+ and AI in Tableau turned on or a Tableau Server site (version 2025.3 or later) with AI in Tableau turned on.

• If you’re using Tableau Desktop, you must be signed into a Tableau Cloud or Tableau Server site. In Tableau Desktop only Tableau Agent in authoring is available.

• You must be on a worksheet or dashboard.

  • For Tableau Agent in Dashboards, you must be connected to a Tableau Cloud site and have opted into the Tableau Agent in Dashboards (Beta). As a viewer, you must also be granted the AI Access and Full Data Query permissions.

  • Starting in version 2026.3, Tableau Agent in Dashboards (Beta) is also available in Tableau Server in web authoring. As an administrator, you must opt into the beta and turn on the feature. Viewers must be granted the AI Access and Full Data Query permissions. For more information, see Turn On AI in Your Tableau Server Site(Link opens in a new window).

• You must be connected to a data source.

  • For Tableau Agent in Dashboards Overview and Insights capabilities, you must be connected to a published data source. The Dashboard Q&A capability supports both published data sources and embedded data sources.

• AI in Tableau must be enabled for your site and, for use in the browser, the option for Tableau Web Authoring must be turned on.

Usage and Capabilities

Can I use Tableau Agent on any type of data?

Tableau Agent is recommended for use on data extract or file-based data for improved performance, but Tableau Agent for viz authoring also works with live connections, or uploaded files with .hyper, .csv, .txt, and .xlsx file types.

Tableau Agent in Dashboards Overview and Insights capabilities work with a published data source. The Dashboard Q&A capability works with both published data sources and embedded data sources.

Cubes are not supported. Also, if you're using data blending, Tableau Agent can only be used with the primary data source.

Can I use Tableau Agent in my language?

Starting in version 2025.1, Tableau Agent supports English (en_US) and a subset of other languages. Tableau Agent in Dashboards Q&A capability only supports English (en_US). If your Cloud site, Server site, or Tableau Desktop application is set to a language that isn't supported, Tableau Agent responses will be in English (en_US). For more information about supported languages, see AI in Tableau supported languages and locales(Link opens in a new window).

Note: If your data source field names and values aren’t in the same language as your user language settings or not the same as the language you’re interacting with Agent in, use the exact field name and values in your requests.

Can I choose which Large Language model (LLM) I want to use in Tableau Cloud?

No. Currently with Tableau Agent, choosing a Salesforce-managed Large Language Model (LLM) isn't supported. Instead, Tableau tests and selects the best model to use, based on performance, accuracy and cost. For more information, see Geo-aware LLM request routing(Link opens in a new window).

Can I choose which Large Language Model (LLM) I want to use in Tableau Server?

Yes, starting in Tableau Server version 2026.2, you can select either OpenAI or Azure OpenAI. Starting in version 2026.3, you can also connect using a Custom Gateway (Beta) to connect to the LLM provider of your choice. For more information, see Turn On AI in Your Tableau Server Site(Link opens in a new window).

What can I ask Tableau Agent to do?

Tableau Agent has several capabilities. It can create vizzes and help you create and understand calculations. If you’ve opted into the Tableau Agent in Dashboards (Beta), it can analyze your dashboard and create overviews and insight summaries for your dashboard users. Dashboard users can also dive deeper into their data and ask questions using natural language.

Tableau Agent can help you build visualizations, choose the best chart types for your data, perform date-based analysis, and manage data filtering and sorting. For example, you can ask it to "show sales data for a specific region" or "compare sales to profit". For more information, see Build and change a viz(Link opens in a new window).

Tableau Agent can also create calculations from natural language. Using the same conversation pane that you would use for generating a viz, you can ask Tableau Agent to create, update, or explain a calculation. For more information, see Create calculations(Link opens in a new window).

Available in Beta starting in July 2026, Tableau Agent in Dashboards can analyze your dashboard and create a quick overview about the dashboard, or create a summary of insights for the charts on the dashboards, helping users find data insights fast so that they can take action on the things that matter most. Users can also query the underlying data source (with the proper permissions) and ask questions about the data, letting them dive deeper into their analysis using natural language. For more information see Tableau Agent in Dashboards (Beta)(Link opens in a new window).

How can I add context for my fields to get the best answers from Tableau Agent?

Add descriptions for your fields. Tableau Agent indexes the field descriptions from comments in Tableau Desktop or Tableau Catalog. Currently there is a limit where Tableau Agent will only index the first 150 characters of each description with an overall limit of 4000 characters. If you have many fields, as a best practice, use short, concise descriptions to get the best results. For more tips, see Tableau Agent Best Practices(Link opens in a new window).

Can I teach Tableau Agent business-specific rules or custom formulas for my organization?

Yes. You can define Business Preferences at two levels to help Tableau Agent provide accurate, organization-specific answers grounded in your business logic (such as defining fiscal years, stock thresholds, or domain terminology):

• Global Business Preferences (Tableau Knowledge): Tableau Cloud sites using Tableau Knowledge can set global business preferences across an entire knowledge graph. Tableau Agent uses these global preferences when responding to user utterances routed through its capabilities.

  Note: Global preferences apply during query processing, but they do not appear in the workbook-level preferences list.

• Workbook Business Preferences: Dashboard authors can upload or manage a Business Preferences file (.txt or .md) directly in a workbook under Configure Settings > Configure Business Preferences in the Tableau Agent pane. These preferences apply to dashboards in that workbook and are visible in the workbook settings. If Tableau Knowledge is enabled, these workbook-level preferences are automatically ingested into the knowledge graph when the workbook is published if the workbook is included as a node in the knowledge graph.

For more information, see Improve response quality for Dashboard Q&A(Link opens in a new window), Tableau Agent Best Practices(Link opens in a new window), and About Tableau Knowledge(Link opens in a new window).

What is Tableau Knowledge and how does Tableau Agent use it?

Tableau Knowledge (requires Tableau Cloud+ or Tableau+) creates connected knowledge graphs that combine trusted Tableau Cloud content (workbooks, data sources, sheets) with organizational context and business preferences.

When a user asks questions, Tableau Agent queries the Knowledge Graph (or default knowledge graph) to retrieve relevant metadata, asset relationships, and global business rules.

This allows Tableau Agent to provide more accurate, grounded, and explainable answers tailored to your organization's terminology and business logic.

For more information see About Tableau Knowledge(Link opens in a new window).

Are there limitations to what Tableau Agent can do?

Yes, Tableau Agent has some limitations. For example, it can't pick a data source for you, do data modeling, build dashboards, suggest relevant content or answer data lineage questions, answer consulting questions (such as “How should I analyze my data?”), or create interactivity with elements like filter controls and parameters. It's primarily aimed at helping novice users and those exploring ad-hoc data questions. For more information, see Tableau Agent limitations(Link opens in a new window).

What is the best way to use Tableau Agent effectively?

Start by working with clean data

• Optimize your workbook and data source using Tableau Agent Best Practices(Link opens in a new window)

• Make sure field names are descriptive and unique

• For Dashboard Q&A, upload Business Preferences(Link opens in a new window) to help Tableau Agent better understand your business

• When you start a Tableau Agent session, if you see similarly named fields in a data source, hide the ones that aren't relevant. Tableau Agent won't ground its answers on hidden fields

• Specify the aggregation function for a measure if you know what you want

• Make sure fields have the correct field role (measure or dimension) and data type (location, string, boolean, etc.)

• Like traditional Tableau, Tableau Agent performs better with extracts. When using live data sources, the time it takes to initiate your Tableau Agent session might be longer and viz load time will be slower

Only ask about analyzing your data. Tableau Agent isn't a general-purpose chat-bot. When it comes time to ask questions, start each request as if Tableau Agent is only aware of the current state of the visualization. Ask questions about what you want to see. For example, “What are my sales over time in California?".

Be specific and descriptive in your requests to help Tableau Agent better understand and respond to your data analysis needs. Break your request into discrete tasks. For example, first request a calculation, then ask for a viz that uses that new field, instead of asking for a viz and a new calculated field at the same time. For more information, see Tips for getting the best results from Tableau Agent(Link opens in a new window).

Can I use Tableau Agent for dashboards or stories?

Tableau Agent is still not available for stories, but starting in July 2026, Tableau Agent is now available in Beta for dashboards in Tableau Cloud and on the Tableau Cloud Trial site. Starting in version 2026.3, Tableau Agent in Dashboards is also available in Beta on Tableau Server. For more information see Tableau Agent in Dashboards (Beta)(Link opens in a new window).

Technical Details

How does Tableau Agent handle data privacy and security?

Tableau Cloud

Tableau Agent in Tableau Cloud ensures data privacy and security by adhering to a zero data retention policy with third-party LLM providers. It respects all existing permissions and data policies within Tableau Cloud, ensuring only authorized users have access. Additionally, it can also employ pattern-based data masking techniques to protect personally identifiable information (PII) before it is processed by LLMs.

For more information, see AI in Tableau and the Einstein Trust Layer(Link opens in a new window) and Select What Data to Mask(Link opens in a new window) in the Salesforce help.

Tableau Server (version 2025.3 and later)

When using Tableau Agent in Tableau Server, you'll connect to your own LLM provider. Your requests don’t use the Einstein Trust Layer and its associated data governance features, including built-in PII masking. Instead, you'll be relying on the LLM provider's security measures to protect sensitive data.

Does Tableau Agent in Tableau Server use the Einstein Trust Layer when I connect to my own LLM provider?

No. When you connect to your LLM provider in Tableau Server, all requests from Tableau Agent are sent directly to the LLM provider. This process doesn't use the Einstein Trust Layer's security and PII masking features. You will be relying on the LLM provider's security measures to protect sensitive data. For more information, see AI in Tableau and Trust(Link opens in a new window).

What is a Custom Gateway for Tableau Server, and why would I use one?

A Custom Gateway is a proxy that sits between Tableau Server and your LLM provider that lets you use the models of your choice. It also lets you add policies to your Tableau AI traffic, such as:

• Maintain strict network security perimeters, such as, keeping traffic inside a private VPC/VPN.

• Avoid distributing long-lived vendor API keys to Tableau Server administrators by managing authentication centrally.

• Audit, log, rate-limit, and track AI usage and cost across your organization.

• Support enterprise authentication protocols, such as IP allowlisting.

For more information, see Turn on AI in Your Tableau Server Site(Link opens in a new window).

What authentication modes are supported when connecting via a Custom Gateway?

When configuring a Custom Gateway in Tableau Server, you can choose from three authentication modes:

• No Authentication: Used when the gateway is already secured inside a zero-trust network perimeter (such as an internal VPC/VPN with IP allowlisting).

• API Key: Tableau authenticates against your internal API gateway using an API token generated by your proxy management system.

• OAuth: Tableau authenticates against an Identity Provider (IdP) using client credentials (Client ID and Client Secret) to issue short-lived access tokens.

For more information, see Turn on AI in Your Tableau Server Site(Link opens in a new window).

What end-user experience should I expect when OAuth is configured on a Custom Gateway?

If a Custom Gateway is configured using OAuth authentication, end users will be prompted to log in when opening Tableau Agent. A Sign in to LLM Gateway button will appear in the Tableau Agent pane. When clicked, it opens your organization's Identity Provider (IdP) login screen in a browser window. Once authenticated, users can begin using Tableau Agent.

Note: In Tableau Prep (version 2026.3) users will need to first open a workbook in web authoring to authenticate, then go back to Tableau Prep to begin using Tableau Agent.

Which Tableau Agent features are supported when using a Custom Gateway?

Configuring and using a Custom Gateway is currently only available in Tableau Server. Tableau Server currently supports the following Tableau Agent features:

• Tableau Agent in Authoring for viz authoring

• Tableau Agent in Tableau Prep for building flows to clean and transform your data

• Tableau Agent in Dashboards (Beta) to get overviews, insights and ask questions about your data

Tableau Agent in Authoring and Tableau Agent in Prep are supported for all authentication methods when using a custom gateway. Tableau Agent in Dashboards (Beta) is not available when using the OAuth authentication method.

How does Tableau Agent know what is in my data?

Tableau Agent indexes your data source at the start of each session to understand what data is present. Indexing takes in the data type, field name, and samples 1000 unique values for a field. This ensures responses are grounded in your data. Remember that Tableau Agent respects data masking if it is enabled, and might not be able to respond to requests that involve masked data.

If you have fields with high cardinality (many distinct values for a single field), Tableau Agent might not have indexed all the values. If you try to filter on a high cardinality field, Tableau Agent creates a filter for the field but might prompt you to select the values you want to include or exclude.

What if the viz created by Tableau Agent isn’t correct?

As with all AI, it's important to review the results you get when using Tableau Agent. Although Tableau Agent can scan your data source for the field names and data in those fields, it doesn't truly understand the data the way a human can. Always review the results from Tableau Agent. If a viz doesn't meet your expectations, try clarifying your request or asking Tableau Agent to recreate it. You can also interact directly with the viz to adjust the analysis to meet your needs. Think of the viz created by Tableau Agent as a starting point to jump start your analysis.

You can also always provide feedback using the thumbs up and thumbs down icon in the conversation pane.

Does Tableau Agent remember previous interactions?

Tableau Agent is a per-sheet experience, meaning it doesn't retain conversation history across different sheets. It has limited memory based on the information in the conversation pane of the current sheet. If you close and reopen the conversation pane while still in your same session, your conversation history persists. If you close your workbook, this clears the conversation with Tableau Agent. The conversation history isn’t saved and doesn’t appear the next time you open the published or saved workbook.