Field notes from the AI frontier

What we're shipping, reading, and learning. Updated when we have something worth saying.

Sep 02, 2026 RAG · 8 min read

Why 80% of RAG systems fail in production — and how to avoid it

The hard part of RAG isn't the embedding model. It's the chunking, the metadata, and the eval loop. Here's what we learned from 14 production deployments.

Aug 18, 2026 Agents · 12 min read

Designing tool-using agents that don't go off the rails

Five guardrails we now ship with every agent — based on production incidents we wish we'd caught earlier.

Jul 30, 2026 MLOps · 10 min read

A pragmatic MLOps stack for a 5-engineer team

You don't need a platform team of 20. Here's what we ship for early-stage teams that still want production-grade monitoring.

Jul 12, 2026 Strategy · 6 min read

The "AI strategy deck" is dead. Here's what replaced it.

Boards don't want a 40-slide deck anymore. They want a 90-day execution plan with measurable outcomes.

Get these posts in your inbox.

Subscribe to the newsletter