Back Issues/Search Home → Calendar → Archive → RSS → Subscribe → Services → Vendors → Blog → Current Issue → Popular → Newsletters (LinkedIn, Substack)

All issues › Volume 344, Issue 2 › IT Vendor News › Databricks

Lakehouse//RT: Scale Real-Time Analytics, Not Your Bill

Databricks, Thursday, November 12th, 2026

Databricks describes how Lakehouse//RT is designed to handle growing real-time and agent query volume without proportional cost increases.

Databricks says AI agents can run hundreds of queries per second around the clock, and most data warehouses scale cost in step with that demand or rely on overprovisioning for spiky workloads.

Lakehouse//RT is built to serve more queries on the same resources through high concurrency support, autoscaling in small increments and a single system instead of a separate real-time serving layer.

Databricks cites sub-100 millisecond latency at 12,000 queries per second.

Customers that chose it over separate serving layers report 6x to 10x lower infrastructure costs, and Aurasell moved from several clusters to one small warehouse sustaining more than 250 queries per second at 10x lower cost.

more →  ·  More from Databricks →