// On the blog
Notes from the field.
Concrete reports on what actually breaks, and what actually works, when you really ship systems to production.
- AI · Security · May 27, 2026 · 9 min read
Giving an AI agent real power without handing it the keys
Validating an agent's work doesn't stop it from wrecking your prod. Those are two different guardrails. Here's the one almost nobody talks about: the perimeter.
- AI · Architecture · May 20, 2026 · 11 min read
What a production AI agent actually looks like
Everyone pictures an agent as a model and a clever prompt. I built one that runs my own engineering work end to end. The model is maybe a tenth of it. Here are the other nine.
- AI · Production · Apr 22, 2026 · 8 min read
Why most AI projects die between POC and production
The dirty secret of enterprise AI: the models work. The systems around them don't. A field report on the gap, with the symptoms and the fixes.