đŸª© Party Guide is Live! View Here

Go Back

Agents Are Eating the Semantic Layer

  • Analytics & Data Sci

When LLMs first hit the scene, the consensus was clear: you need a semantic layer for reliable, accurate results. The benchmarks proved it. The research confirmed it. I believed it too (and was one of the first voices saying so).

Then the models got better. And the consensus stopped being true.

Today, a semantic layer doesn't give your agent accuracy. It gives your agent a ceiling. It limits flexibility, constrains the questions your agent can answer, and forces you to anticipate every question in advance. That's not how data in enterprises actually works.

This talk covers where the semantic layer falls short, what we built instead, and how to architect agents that gather and create business context dynamically, without sacrificing governance or trust.

Paul Blankley

Co-founder & CTO

Paul Blankley

Zenlytic

Paul is the Co-founder / CTO of Zenlytic, an analytics agent platform that uses LLMs to provide an easy interface to complex business data. 

Paul founded Zenlytic after working as a consultant setting up analytical systems for companies from startups to the Fortune 500.  While consulting, Paul experienced the impact of legacy data tools on a business’s ability to make important decisions and saw a huge opportunity to re-architect last-mile analytics for the AI era.  He has worked in data for over 9 years and is passionate about all things data and AI.

Paul has a master's degree from Harvard in Computational Data Science, where he also worked with the Minor Planet Center on algorithms to detect if previously untraceable asteroids were going to hit the Earth.  He lives in Denver, CO, where he spends his free time snowboarding, running, and rock climbing.

The AI Conference for Humans Who Ship

While other conferences theorize, AI Council features the engineers shipping tomorrow's breakthroughs today.

Subscribe for Updates