AI in production fails in three ways: a vendor goes dark, a job fails silently, data leaves your control. This is the record of the rulings I made against each one, on my own stack, with what they cost and what broke. Where something is still untested at scale, I say so.
Build automations with AI
Keep AI output deterministic: let the model decide, let code render
Model output you cannot reproduce is output you cannot sign: the same input comes back different, and nothing in it can be diffed. The rule here takes rendering away from the model, which returns JSON while code renders all a reader sees, and names the model swap that fixed French regressions.
Reliable Agent Systems
Your digest knows it saw that article before. It cannot tell it already told you that story
An automated digest promises never to serve the same thing twice, and keeps that promise only for the article. Two shipped passes catch one article under a second URL; the same story from a second source, or one an earlier digest already told, still arrives as new.
Sovereign & local AI
Dictation without eavesdropping: on-device speech-to-text as a hard privacy line
Your dictation audio either stays on the device or it does not, and that line picked the stack. This piece follows the on-device choice once audio egress became the one disqualifying criterion, and what ruling out the cloud apps gave up without pricing.
