Build trust in AI analytics with research-backed methods to evaluate and verify results. Learn practical guidelines and design patterns to catch errors, validate insights, and use AI with confidence.
Sessions
Hundreds of sessions now live. More on the way.
This year’s lineup is stacked with hands-on trainings, product deep dives, and real-world strategies you can apply right away.
Register now and we’ll notify you when it’s time to build your agenda and reserve your seat.
New sessions are added daily and subject to change. Learn more about
session types. Hands-on training sessions coming soon!
Sessions
Snag your seat.
New this year, you can now reserve your seat at most sessions. Register now to get first-access to hands-on learning and expert-led sessions.
Tip: Use " " around your search terms to find an exact phrase.
Tip: Use " " around your search terms to find an exact phrase.
Community Speaker
Reserved Seating
Video On Demand
Verify Your AI: The Analyst’s Guide to Trust and Quality
, Senior Research Staff, Salesforce
, Product Management Director, Salesforce
Role: Data Analyst
Product: Tableau
Tableau Product: Nonprofit, Tableau Next, Tableau Pulse
Session Level: Beginner
Session Type: Theater
- Tuesday, May 51:00 PM - 1:20 PM PDT(8:00 PM - 8:20 PM GMT)Theater 1 | Data Village, Ground LevelFIRST COME FIRST SEATED
Session Summary: The session highlighted the growing importance of AI in analytics, with Gartner predicting that by 2027, half of all business decisions will be augmented or made by AI. However, trust in AI remains fragile, as errors in AI-generated visual analytics can be subtle and hard to detect, potentially leading to costly mistakes. Tableau unveiled a new framework with 13 specific checks to systematically evaluate AI outputs in visual analytics, addressing issues like incorrect metrics, mismatched text and charts, and dropped filters. Additionally, Tableau demonstrated its integration capabilities with various AI models through a customizable gateway, allowing businesses to bring their own models and validate them using Tableau's robust testing tools and embedded evaluation framework to ensure accuracy and reliability in AI-driven workflows.
Key Takeaways:
• Tableau introduced a framework with 13 structured checks to help users systematically evaluate AI outputs in visual analytics, ensuring higher trust and accountability.
• Errors in AI analytics, such as mismatched metrics or contradictory text and charts, can be subtle yet impactful, emphasizing the need for robust evaluation tools like Tableau's framework.
• Tableau's latest updates include integration with customizable AI gateways, enabling enterprises to connect and validate their preferred models, ensuring flexibility and control over AI implementations.
Session Summary Feedback : Report a Concern
Available Now on Salesforce+: Watch now
