Mosaic Research Articles

6 articles

Databricks

31 min read

AI•2026-05-19

MemEx: A Programmable Scratchpad for LLM Agents

MemEx enables LLM agents to manage context windows using persistent Python code blocks instead of JSON/XML tool calls.

Pushing the Frontier for Data Agents with Genie

Genie is Databricks' data agent that improves accuracy and reduces costs for complex enterprise data queries using specialized knowledge search, parallel thinking, and multi-LLM strategies.

Agentic Reasoning in Practice: Making Sense of Structured and Unstructured Data

Databricks Agent Bricks Supervisor Agent demonstrates multi-step agentic reasoning across structured and unstructured enterprise data for complex knowledge-intensive tasks.

Memory Scaling for AI Agents

This post introduces memory scaling as a new design axis for AI agents, showing that performance improves as external memory grows.

coSTAR: How We Ship AI Agents at Databricks Fast, Without Breaking Things

This post introduces coSTAR, Databricks' methodology for reliably testing and iterating on AI agents using MLflow.

Meet KARL: A Faster Agent for Enterprise Knowledge, powered by custom RL

Databricks introduces KARL, a custom RL-trained knowledge agent that outperforms frontier models in cost, latency, and quality for enterprise grounded reasoning tasks.

Mosaic Research