Databricks Says It Solved the Decades-Old Data Pipeline Problem That's Been Slowing AI Agents
VentureBeat, Wednesday, June 17th, 2026
Databricks unveils Lakehouse//RT and LTAP to eliminate ETL pipelines between operational and analytical data for AI agents.
At the Data + AI Summit, Databricks announced Lakehouse//RT and LTAP (Lake Transactional/Analytical Processing) to collapse infrastructure barriers between operational and analytical databases.
Agents made the problem structural, as a system reasoning continuously on live data cannot tolerate a pipeline between itself and the information it needs.
LTAP stores Postgres-native transactional data in Delta and Iceberg format from the point of write, removing decades-old ETL pipelines.
Lakebase, the serverless PostgreSQL service, handles latency via a caching layer that performs row-to-column conversion before data lands in object storage. Lakehouse//RT delivers millisecond query latency directly on governed Delta and Iceberg tables, eliminating the dedicated real-time serving tier.