Most AI demos look impressive—until you ask a simple question: “Would this actually work inside a real mobile app, on a real device, for a real user?” I’ll walk through how I built a fully on-device intent classifier using a Small Language Model (SLM), why smaller models behave very differently than large ones, and what actually breaks when you try to ship this in production. In most retail or marketplace apps, intent is inferred after the user does something:  They browse →

Any application that can be written in JavaScript will eventaully be written in JavaScript. Nope, nope, maybe, nope... Buckle up, folks!...