Field notes from an AI practitioner.
No sponsored content. No vendor takes. No LinkedIn-bait. Just what I'm building, what broke, and what I learned.
Production AI Is an Engineering Discipline, Not a Demo
Over 25 years in enterprise tech, and more intensely in the last couple of years building AI products and advising teams on agentic systems, I've watched the same pattern repeat itself so many times t…
Your Agent Has More Access Than Your Junior Developer. That's a Problem.
I watched an agent bypass its container and write to the host filesystem.
Prompts Are Code. Treat Them Like It.
There's a pattern I keep seeing in teams building agentic systems. The architecture is solid. The agents work. The critic-falsifier loop catches real problems. Everything looks good in the demo.
Your Agent Broke at 2 AM. Now What?
In my last post, I talked about what makes a system genuinely agentic — the autonomous loop, the critic, the falsifier, the layered memory. If you haven't read it, start there. This post assumes you'v…
What "Agentic" Actually Means — Because Most Agents Aren't
I've spent the last year architecting agentic systems — real ones, in production, tied to actual business workflows. And the more I build, the more I realize how loosely this industry throws around th…