Skip to main content
Join the Agentforce Hackathon on Nov. 18-19 to compete for a $20,000 Grand Prize. Sign up now. Terms apply.

Get to Know Tableau Agent

Learning Objectives

After completing this unit, you’ll be able to:

  • Describe how Tableau Agent can enhance your data analysis experience.
  • Explain the key features and benefits of Tableau Agent.
Note

Einstein Copilot is now Tableau Agent, as the platform grows to make way for more AI agent functionality. Starting in October 2024, you'll see updates to page sections, field names, and other UI text throughout Tableau Prep, Tableau Catalog, and Tableau Cloud Web Authoring.

Meet Your New Data Companion

Tableau Agent is your own intelligent, conversational, and trustworthy analytics assistant for all of your data analysis endeavors.

With Tableau Agent, you get suggested questions to dive deeper into your data set. And that’s only the beginning. Tableau Agent also helps build visualizations and work with calculations, making it easier for you to see the bigger picture and act on your data more quickly.

Built on the Einstein Trust Layer, you can rest easy knowing Tableau Agent is focused on keeping your data secure and providing accurate, safe insights.

Whether you’re a seasoned data pro or just embarking on your data analytics journey, think of Tableau Agent as your trusted guide—always by your side as you work with your data.

A Trusted Friend

Tableau Agent relies on multiple layers of security to protect your data and ensure that it’s only accessible to those who have permission to access it. We also put safeguards in place to provide relevant, accurate results and protect against harmful content. For more information, see How Can I Trust Tableau Agent?

Get a Jumpstart on Data Exploration

The first step of the journey is always the hardest. Tableau Agent makes it easier to get started by automatically recommending suggestions that you can ask Tableau to help uncover deeper insights.

For example, let’s say you’re just starting out as a data analyst and you’re working with your sales team to uncover important data points related to customer sales. Tableau Agent might nudge you with options like, “Are there any sales patterns across product categories?” to discover seasonal sales patterns, or, “How do loyalty program tiers affect sales?” to uncover the relationship between loyalty tiers and purchase frequencies. If these suggestions don't resonate with you, simply click the Retry with Tableau Agent button to see more options.

A contextual list of questions generated by Tableau Agent on the right side of a Tableau worksheet.

To help you dive deeper into your analysis, Tableau Agent can also suggest next steps you can take on the viz it created. Simply click the Suggestions button to see a list of possible actions. Then, select an action and Tableau Agent applies the change for you.

Alist of possible actions suggested by Tableau Agent.

Use Conversational Language to Explore Data

Tableau Agent lets you interact with your data using natural language prompts (something us humans refer to as “questions” or “requests”). When you ask follow-up questions or request more information, Tableau Agent dynamically adjusts the visualizations and shares relevant insights.

For example, as a regional sales manager, you might look at your sales data and ask, “What are the total sales per product category?” Tableau Agent generates a viz using your data that reveals the answer. You can ask follow-up questions to dive deeper into specific product categories and see the sum of sales per product. All of this analysis is available to you without manually analyzing data or building a viz from scratch.

A user asks Tableau Agent a series of questions asking for more information about data in their Tableau worksheet.

Take Calculations to the Next Level

Available in Tableau Prep and the Tableau Cloud authoring experience, Tableau Agent helps you build and understand calculated fields. Calculated fields are formulas that perform an action on one or more other fields in your data. With an assist from Tableau Agent, you can take your calculations to the next level without extensive data analysis experience or complicated manual work.

For example, you can use guidance from Tableau Agent to write a complex calculation that extracts a piece of information from a field, such as extracting a zip code from a complete mailing address. Think of all the time saved!

An example of the Calculation Assistant functionality in Tableau Agent in Tableau Prep showing AI-generated recommendations for how to build a function that extracts postal codes from the Customer Mailing Address field.

Calculations in Tableau can sometimes be tricky, but not with Tableau Agent as your partner. At any time, you can ask Tableau Agent to explain a calculation in your workbook, even if Tableau Agent created it for you. You can be sure that the calculation is doing what you need while building your Tableau calculations skills at the same time!

An explanation of the Business Days Between Order and Ship calculation provided by Tableau Agent, as requested by the user.

A dialog between a Tableau user and Tableau Agent where Tableau Agent provided a detailed explanation of a calculation in response to the user’s question.

Get the Most Out of Tableau Agent

Tableau Agent does its best to understand your intent and your data. But it’s still learning. To get the best results, remember these tips:

  • Use clean and well-curated data: Hide unnecessary fields, add clear field labels and descriptions, and use correct data types.
  • Be explicit about what you want Tableau Agent to do: Use clues in your request like “show me,” “create a viz,” “build a bar chart,” or “create a calc”.
  • Use specific language in your requests: The more descriptive you are in your request, the better Tableau Agent is at providing the right viz. For example, if you want an aggregation by median, state that in your request.
  • Specify how to evaluate “top”: “Top” can be ambiguous to Tableau Agent. Instead, be more specific. For example, ask for “top products based on profit” or “top products by on sales volume”.
  • Break down complex tasks: To get the best results, break multi-step queries into separate actions. For example, ask for a calculated field to be created, then request a viz that uses the new field.
  • Only ask questions about your data: Tableau Agent isn’t a general purpose chatbot. Instead, ask questions targeted at analyzing your data, and iterating and digging deeper into the viz results.

Summary

Exploring your data, creating visualizations, and uncovering insights is easier than ever thanks to the AI-powered assistance of Tableau Agent.

Want to take Tableau Agent for a spin? Start your free Tableau Cloud trial today!

Resources

在 Salesforce 帮助中分享 Trailhead 反馈

我们很想听听您使用 Trailhead 的经验——您现在可以随时从 Salesforce 帮助网站访问新的反馈表单。

了解更多 继续分享反馈