/AI
The Report Is Not The Work
A crew of AI agents fixed about eighty findings in one of my apps this week. The rule that made it work: an agent's report is testimony, not evidence.
Topic
AI
9 posts on this topic.
/AIThe Overnight Agent Is A Relay, Not A Marathon
I wanted an audit and fix loop that runs unattended all night. The answer was not a smarter agent. It was a dumber one that runs a single phase and exits.
/AIMy Own Pipeline Served Me Slop
My tool generated a preview website for a real business and it read as generic slop. The fix was not a better prompt. It was encoding my taste somewhere the machine can reach it.
/AIGreen Tests, Red Reality
A backend with 748 passing tests still could not boot on the database it was built to ship on. The tests were never wrong. They just never ran the part that broke.
/AIGive The Robot A Spending Cap
I let AI agents write code while I sleep. This week I made sure they cannot quietly run up a bill while they do it.
/CybersecurityA 12-vector AI security hardening plan
Building ContentForge's AI pipeline meant threat-modelling it properly first. Here is the practical, plain-English checklist of twelve places things go wrong, and how to harden each one.
/ProjectsA factory of one: building a software studio solo with AI agents
I have more projects on the go than one person has any business running. Here is the system that makes that ambitious instead of insane, and the honest catch in it.
/AIWhat I actually use AI for as an engineer (and what I don't)
Past the hype and the doom, the honest daily reality of building with AI: where it genuinely earns its place in my workflow, and where I keep it well away.
/AIThe defender's pivot: why security is an unfair advantage in AI engineering
People treat moving from cybersecurity into AI engineering like a leap. It felt more like turning the same habits around to face the other way.