AI EngineeringJuly 23, 20264 min read
Why A Frontier Data Agent Outperforms General Coding Agents in Quality and Cost
We evaluate Genie Code against three leading coding agents on 400+ tasks from real internal sessions.
Recent posts
- AI Engineering
Why A Frontier Data Agent Outperforms General Coding Agents in Quality and Cost
4 min read - AI Engineering
How we keep GPUs reliable across Databricks AI
8 min read - AI Engineering
Introducing Omnigent: A Meta-Harness to Combine, Control and Share Your Agents
5 min read - AI Engineering
Reliable LLM Inference at Scale
8 min read - Product
How Superhuman and Databricks built a 200K QPS inference platform together
8 min read - AI Engineering
Using MemAlign to Improve Evaluation of Traditional Machine Learning in Genie Code
11 min read - AI Engineering
coSTAR: How we ship AI agents at Databricks fast, without breaking things
16 min read - AI Engineering
SOTA Embedding Model for Agentic Workflows Now in Public Preview
3 min read - AI Engineering
Decoupled by Design: Billion-Scale AI Search
14 min read - AI Engineering
Streamline AI Agent Evaluation with New Synthetic Data Capabilities
8 min read
Get the latest posts in your inbox
Subscribe to our blog and get the latest posts delivered to your inbox.