Today Databricks announced new retrieval augmented generation (RAG) tooling for its Data Intelligence Platform to help customers build, deploy and maintain high-quality large language model (LLM) apps ...

Databricks' Adaptive Instructed-Retriever lets AI agents decide how many times to search per question, matching frontier model quality in half the time.

Databricks' KARL agent matches Claude Opus 4.6 accuracy with 33% lower cost and 47% less latency by learning to stop searching when it has enough ...

Databricks says Instructed Retriever outperforms RAG and could move AI pilots to production faster, but analysts warn it could expose data, governance, and budget gaps that CIOs can’t ignore.

With customers asking increasingly complex questions of AI agents, Databricks is launching a model aimed at improving the accuracy of data retrieval systems.

Genie Ontology aims to unify business definitions across systems, but analysts say data quality and governance will make or break adoption. First came vector databases, then RAG. Now, the next ...

Databricks unveiled a new portfolio aimed at helping users customize generative AI applications with their own data through retrieval-augmented generation. Retrieval-augmented generation (RAG) is an ...

Databricks Inc. today announced several enhancements to its Mosaic AI toolset for building and deploying artificial intelligence models that specifically target generative AI applications. The ...