Engineering AI for Automated Relationships in Tableau Next

-

 

Engineering AI for Automated Relationships in Tableau Next

Join a head developer for a look under the hood of the revolutionary AI-powered relationship generation within Tableau Semantics.
Roni Ben-Oz, Senior Manager of Software Engineering, heads the development of AI-powered relationship generation in Tableau Next and Data Cloud. Her team is revolutionizing the way users work with structured data by automating the identification of relationships between data objects, eliminating the need for manual configuration.

How is regression testing and AI accuracy validation handled?

Roni: To ensure the accuracy of AI relationship generation across updates, a robust validation pipeline is in place to detect regressions. Unlike traditional software, AI systems introduce stochastic variability, which complicates consistency validation. A dual-layer testing framework has been implemented:

  1. Automated regression testing: The first layer consists of automated regression testing within CI/CD pipelines, helping to ensure new deployments maintain validated relationship mappings. A baseline accuracy threshold is enforced, requiring a minimum of 80% regression test coverage before an update can be released. This prevents unexpected variations in AI-generated relationships.
  2. AI benchmarking and precision/recall tracking: In the second layer, each LLM update undergoes a 40-iteration benchmark test to measure precision, recall, and false positive rates. Given the non-deterministic nature of LLMs, accuracy monitoring extends beyond unit tests into statistical trend analysis. Production logs are analyzed to identify relationships frequently overridden or corrected by users, providing real-world accuracy feedback and enhancing future model iterations

Comments

Post a Comment

Popular posts from this blog

Tableau Next - Agentic analytics that delivers personalized, contextual, and actionable insights everywhere work happens.

-
Image
  The future of analytics has arrived. Meet Tableau Next. Tableau Next is a flexible, API-first analytics experience that integrates the #1 analytics platform with Agentforce, the world’s first digital labor platform. Built on a composable architecture, with a unified data layer and trusted semantics, it delivers personalized, contextual, and actionable insights to every user. Tableau Next. Analytics, now with Agentforce. Tableau Next is now available via Tableau+. Experience the future of data and analytics today. Built on Salesforce with enterprise-grade performance, security, and scalability Powered by Hyperforce and with Data Cloud as the unified data layer, Tableau Next ensures enterprise-grade security, compliance, and agility while seamlessly unifying customer data for analysis. Open, interoperable, and API-first, it takes analytics anywhere. Unlock the power of agentic AI with trusted, unified business data Tableau Semantics is an AI-infused semantic layer that is deeply in...
Read more

Tableau Next LangChain

-
Image
  Tableau LangChain: Build highly flexible AI-applications that extend your Tableau Server or Cloud Environment Learn how to integrate AI with Tableau to build secure AI agents & apps using your trusted data via Tableau LangChain. What is Tableau LangChain? Tableau_langchain implements a collection of Python classes and methods designed to work with the LangGraph framework. These classes and methods wrap Tableau’s APIs with Python functions, which become tools that can be leveraged within LangChain and LangGraph.  You can think of it like a toolkit that helps AI agents, or an LLM, talk directly to your Tableau data. For example, the simple_query_datasource method is implemented using the LangGraph syntax and makes it simple to create a LangGraph agent that can query your Tableau published data sources using the VizQL Data Service tool. Additional tools include search_datasource and get_pulse_insight. Tools are an essential component of an AI agent because they enable agent...
Read more

What to Know About Tableau Next Cloud on Hyperforce

-
Image
What to Know About Tableau Cloud on Hyperforce Tableau Cloud on Hyperforce, Salesforce’s next-generation infrastructure architecture for the public cloud, allows customers to effectively manage data residency and compliance with enhanced security and scalability. How Tableau Cloud on Hyperforce enables greater scalability, security, and compliance With Tableau Cloud on Hyperforce, Tableau Cloud customers see immediate benefits while getting the same user experience and functionality as before. ​​So, what changes with Tableau Cloud on Hyperforce? Everything… and nothing! The next-gen, world-class platform enhances Tableau Cloud’s scalability and security while the product remains the same! Tableau Next empowers enterprises with faster analytics. Post Holdings VP Data & Analytics, Krystin Kim sits down with Tableau's Ed Beaurain and shares her focus on delivering analytics faster across the business to meet the growing demand for analytics—and why she's excited for agentic sk...
Read more