How to Build a Golden-Question Benchmark for Your Data Agents
Build a golden-question benchmark for data agents: frozen Iceberg tags, execution-based scoring with Arrow, and CI gates.
Data engineering · Lakehouse · AI
Data Engineering, Lakehouses, and the Future of AI
Alex talks technology, data, software development and AI
649published posts
520topics covered
77published books
Welcome to my digital garden. This is where I share my deep dives, tutorials, and thoughts on the evolving data landscape.
As the Head of Developer Relations at Dremio and author of Apache Iceberg: The Definitive Guide, Apache Polaris: The Definitive Guide, and Architecting an Apache Iceberg Lakehouse, my mission is to make complex data architectures accessible to everyone.
What You'll Find Here
- Apache Iceberg & Polaris: Comprehensive guides on open table formats and catalogs.
- Data Lakehouse Architecture: Strategies for building cost-effective, high-performance data platforms.
- AI & RAG: Exploring the intersection of data engineering and Large Language Models.
- Dremio: Tips and tricks for using the Agentic Lakehouse Platform.
Latest writing
All 649 posts →
When a Data Agent Gives a Wrong Number: Incident Response for Agentic Analytics
A plan for when a data agent gives a wrong number: severity levels, containment, Iceberg time travel reproduction, and blast radius queries.
Multi-Tenant Data Agents: Serving Many Customers From One Lakehouse
Serve many customers from one lakehouse without leaking between them: isolation models, Polaris grants, and tenant-scoped agent state.