AI in Tableau and Trust

Note: Einstein Copilot has been renamed Tableau Agent, as the platform expands to accommodate 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. Help content and Trailhead modules are also being updated to reflect these changes.

It’s important that your data stays safe while you innovate with new technology. With AI in Tableau, we keep Trust as the #1 value, and we strive to make sure your data is secure while also creating experiences that are accurate and safe.

AI in Tableau and your data

To keep your data secure, Salesforce has agreements in place with Large Language Model (LLM) providers, like OpenAI. Organizations can leverage generative AI capabilities without their private data being used to train the LLM.

Geo-aware LLM request routing

With Tableau Agent, choosing a Salesforce-managed Large Language Model (LLM) isn't supported. Instead, the development team at Tableau tests and selects the best model to use, based on performance, accuracy and cost.

Some models may not be available in the region closest to where your Einstein generative AI platform instance is located. If the selected model isn't available in your region, the requests are routed to the United States, where all models are available. For information about which LLM model is currently being used in your version of Tableau Agent, contact your Tableau Account Executive.

For more information about Geo-aware LLM request routing, see Geo-Aware LLM Request Routing on the Einstein Generative AI Platform(Link opens in a new window) in the Salesforce help.

Trusted generative AI

Salesforce’s Einstein generative AI solutions are designed, developed, and delivered based on five principles for trusted generative AI.

  • Accuracy: We prioritize accuracy, precision, and recall in our models, and we back our model outputs up with explanations and sources whenever possible. We recommend that a human check model output before sharing with end users.

  • Safety: We work to detect and mitigate bias, toxicity, and harmful outputs from models used in our products through industry-leading detection and mitigation techniques.

  • Transparency: We ensure that our models and features respect data provenance and are grounded in your data whenever possible.

  • Empowerment: We believe our products should augment people’s capabilities and make them more efficient and purposeful in their work.

  • Sustainability: We strive towards building right-sized models that prioritize accuracy and reduce our carbon footprint.

To learn more about trusted AI, see Salesforce Research: Trusted AI(Link opens in a new window)

The Einstein Trust Layer in action

AI in Tableau is powered by Einstein AI and inherits the Einstein Trust Layer and security controls.

With Tableau Pulse we ground the insight summaries that we generate using templated natural language insights and values calculated using deterministic statistical models. Tableau Pulse is also based on a metric layer that provides a bounded, safe space for insights to be detected.

Tableau Pulse uses generative AI to enhance and synthesize the language of the insights generated by Tableau. The result is summarized insights in easy to understand language that the user can quickly engage with.

To enable Tableau Agent to return a viz, a calculation, or an asset description, we first need to ground Tableau Agent in your data.

When you launch Tableau Agent, we query the data source that you're connected to and create a summary that includes field metadata (field captions, field descriptions, data roles, and data types) and up to 1000 unique field values if the data type is string (text). This summary is sent to the Large Language Model (LLM) to create vector embeddings so that Tableau Agent can understand the context of your data. The summary creation happens within Tableau and the summary context data is forgotten by the LLM as soon as the vector embeddings are created.

When you type a question or request into the conversation pane, a combined prompt consisting of the user's input, metadata describing the current state of the viz (web authoring), and historical context from the conversation pane flow through the Einstein Trust Layer to the LLM. The Einstein Trust Layer can be used to mask Personally Identifying Information (PII) before it is sent to the LLM. Using machine learning and pattern matching techniques, PII in prompts are replaced with generic tokens and then unmasked with original values in the response. For more information about PII masking see Einstein Trust Layer Region Language Support(Link opens in a new window) in the Salesforce help.

The response flows back through the Einstein Trust Layer to check for toxicity and unmask any masked data. Due to our zero data retention policies in place with our third-party LLM providers, any data sent to the LLM isn’t retained and is deleted after a response is sent back.

The result is a viz, a calculation, or an asset description ready for you to review.

Techniques like this ensure our products adopt generative AI in a trusted manner. At the same time, your customer data isn’t used to train any global model.

Want to learn more about the Einstein Trust Layer? See Einstein Trust layer: Designed for Trust(Link opens in a new window) in the Salesforce help, or take the Einstein Trust Layer(Link opens in a new window) module on Salesforce Trailhead.

Reviewing generative AI outputs

AI in Tableau is a tool that can help you quickly discover insights, make smarter business decisions, and be more productive. This technology isn’t a replacement for human judgment. You’re ultimately responsible for any LLM-generated outputs you incorporate into your data analysis and share with your users.

Whether it’s generating calculations to use in a Tableau Prep flow, summarizing insights for metrics you follow, creating visualizations for you from your data, or drafting descriptions for your data assets, it’s important to always verify that the LLM output is accurate and appropriate.

Focus on the accuracy and safety of the content before you incorporate it into your flows, visualizations, and analysis.

  • Accuracy: Generative AI can sometimes “hallucinate”—fabricate output that isn’t grounded in fact or existing sources. Before you incorporate any suggestions, check to make sure that key details are correct. For example, is the proposed syntax for a calculation supported by Tableau?

  • Bias and Toxicity: Because AI is created by humans and trained on data created by humans, it can also contain bias against historically marginalized groups. Rarely, some outputs can contain harmful language. Check your outputs to make sure they’re appropriate for your users.

If the output doesn’t meet your standards or business needs, you don’t have to use it. Some features allow you to edit the response directly before applying it to your data, and you can also try starting over to generate another output. To help us improve the output, let us know what was wrong by using the thumbs up and thumbs down buttons where available and provide feedback.

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