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
Does it keep working if their servers go dark? The one test that should rank every AI dependency
Ask one question of every AI dependency: does it keep working when its vendor cuts you off? This piece answers it with a ranking test that grades each component by cutoff survival, not by where its vendor sits on a map, so migration priority lands on what still needs a live vendor connection.
