Databricks has released KARL, an RL-trained RAG agent that it says handles all six enterprise search categories at 33% lower cost than frontier models.

People's decisions are known to be influenced by past experiences, including the outcomes of earlier choices. For over a century, psychologists have been trying to shed light on the processes ...

Databricks' KARL agent uses reinforcement learning to generalize across six enterprise search behaviors — the problem that breaks most RAG pipelines.