Latest post
What Apache Polaris 1.9.0 Brings to Low-Egress Multi-Cloud Catalogs
What Apache Polaris 1.9.0 adds for multi-cloud lakehouses: Cloudflare R2 credential vending, a DynamoDB persistence backend, and the Iceberg 1.12 client.
The archive
Writing
652 posts on Apache Iceberg, lakehouse architecture, data engineering and applied AI.
Schema Pruning and Few-Shot SQL Selection for Data Agents Facing Thousands of Columns
How data agents prune enterprise schemas down to the columns that matter, ground filter values, and pick few-shot SQL examples with the right shape.
Upgrading to Apache Iceberg 1.12.0 Without Breaking Your Engines
A platform engineer's upgrade guide to Apache Iceberg 1.12.0: variant and geospatial changes, REST catalog behavior, removed APIs, and rollback.
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.
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.
Release Management for Data Agents: Shipping Prompts, Tools, Models, and Metrics Without Breaking Answers
Ship prompts, tools, models, and metric changes without breaking answers: agent manifests, shadow mode, canaries, and rollback.
Semantic Caching for Data Agents Without Serving Stale or Leaked Numbers
Cache data agent results safely with canonical query keys, Iceberg snapshot freshness checks, and permission-aware cache keys.
Small Language Models for Data Agents: Where They Win and Where They Fail
Where small language models win inside a data agent and where they fail, plus a routing architecture that escalates only when needed.
Stop Calling Everything Made With AI Slop
AI slop means low-quality content, not AI-assisted work. The three markers of slop, and the review habits that separate skilled AI-assisted work from filler.