Page 2 of 6
Thoughts on AI engineering, responsible automation, and building systems that matter.
The hard part of automation is not making a script work once. The hard part is building a workflow that keeps behaving when APIs are slow, data is weird, humans are busy, and nobody is watching the terminal.
Read more →
A dashboard that helps people make the same decision correctly every morning is more valuable than a demo that looks impressive for five minutes and teaches the team nothing about production reality.
Read more →
The first time I had to fire someone, I rehearsed the conversation for three days. They were a friend. They were also three weeks behind on every deadline. Nobody prepares you for that when you are fourteen.
Read more →
The visible magic of an AI agent is the answer it gives. The engineering work is everything that happens before that answer: what context it receives, what it is allowed to remember, which tools it can use, and when it should stop and ask for help.
Read more →
Debugging an AI agent is not like debugging a normal function. The failure can live in the prompt, the retrieved context, the tool result, the memory layer, or the model's confident interpretation of all of it.
Read more →
The question I keep coming back to is not whether an AI agent will make mistakes. It will. The useful question is whether the system around it makes those mistakes visible, contained, and reversible.
Read more →
The third time a broken test made it to the remote repository because a developer forgot to run the test suite locally, I decided to solve the problem permanently.
Read more →
I used to start every morning with three browser tabs, three inboxes, and a growing sense of dread. Now an AI agent reads them all before I wake up. The journey from inbox chaos to automated calm took six months and changed how I think about attention.
Read more →