# Databricks describes LTAP storage that keeps operational and analytical data together for AI agents

Databricks says LTAP unifies row-based operational data and columnar analytical data at the storage layer, while specialized compute continues to handle each workload separately for AI agents.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-17T15:32:00.000Z
Query date (America/Los_Angeles): 2026-11-17

HTML: https://didcodexreset.com/news/66f705dc1d354b1c976cabe6.html

Content language: en
Localization state: sameLanguage

Source: Databricks · Published 9/28/2026, 07:38:26

Databricks says AI agents need to act on live operational data while also using analytical data. Operational systems have relied on fast row-based access, while analytics has been optimized for columnar storage and broad scans.

LTAP brings the operational and analytical representations of the same data together at the storage layer. A hotter tier keeps data in row format for operational access, and a cooler tier holds it in columnar format for analytical reads. Specialized compute can still handle each workload independently, rather than replacing the engine used for each job.

Databricks explains the design in its article on [how LTAP unifies OLTP and OLAP workloads](https://www.databricks.com/blog/40-year-old-database-rule-agents-just-broke-how-ltap-unifies-oltp-and-olap-workloads?utm_source=twitter&utm_medium=organic-social).

Tags: Databricks, LTAP, OLTP, OLAP, AI agents

[View original post](https://x.com/databricks/status/2104581170230874339)
