Full talk · edited transcript

Why Data-Intelligent Agents Win: A Side-by-Side Benchmark

Austin Choi, Dan Pechi18 Jun 2026

Austin Choi (Delivery Solutions Architect) and Dan Pechi (Sr. Generative AI Product Specialist), Databricks.

The session description: vibe coding is fun until it hits production. Two agents run the identical LLM on identical enterprise workloads. One is armed with raw SQL and good intentions. The other is grounded in the Databricks Data Intelligence stack: a Unity Catalog semantic layer, governed metric views, UC functions with LLM-readable docstrings, and Vector Search over enriched business context.

Continue reading — it's free

Google or a one-time email code. No password.