Category
Practitioner Lessons
5 posts
Ten Scheduled Jobs, Zero Runs: The Four Proofs an Automation Actually Ran
An automation audit is a check of every job you believe runs on a schedule against evidence that it actually ran, because the file where you declare a schedule and the system that...
The Four Constraints That Decide Whether AI Output Is Usable
Usable AI output is a constraint problem because the model is already capable enough for most of the work you hand it. The gap between a result you ship and a result you delete is...
The Loop Stack, or How to Stop an AI Agent From Gaming Its Own Goal
A single AI agent loop is a trap because you give it one number to chase and no second number to keep it honest. The loop does exactly what you asked. What you asked for was a...
What Ten Days Off the Grid Taught Me About Running Always-On AI Systems
An unplug is a system test, not a holiday. When you remove the operator from a set of automated workflows for ten days, the work that keeps running tells you what you built well...
An Essay Every Week: What I'll Write About Here, and Why
This site is the home of my weekly longform writing on enterprise AI, agentic systems, and the human side of what we are all building right now. Every Monday at 8 AM IST, I will...