How to Build Reliable AI Products: A Production Engineering Guide
AI demos are easy. Reliable AI products are an engineering problem.
Post tecnici, decisioni di prodotto e osservazioni oneste, scritti mentre costruisco, non dopo.
The best notes if you want to understand how I think, build, and ship.
AI demos are easy. Reliable AI products are an engineering problem.
MV3 is four moving parts, manifest, service worker, content scripts, and UI, not a single script tag anymore.
Stop presenting projects. Start shipping a system that compounds trust.
Build in public
Cosa è stato rilasciato, cosa si è rotto e cosa è cambiato, scritto mentre succedeva.
Shipped a popup refresh focused on first-glance clarity: the popup now states the job plainly, the current-tab shortcut says exactly what it does, and the empty state lost its duplicate copy. Small release, but every session starts at the popup.
Rebuilt the Amethyst popup around one question: where did today go? It now opens with the daily total, top sites, and a single button into the full dashboard. Removed the tracking badge, comparison chip, sync button, and feedback card, the glance view answers fast, then gets out of the way.
A run of notes on making this site readable by AI agents: the MCP server, the public API, the data model, and the security lessons from exposing it all. Personal sites are becoming APIs, this series documents doing it for real.
Come si comportano le funzionalità IA quando le usano persone reali, non demo controllate.
You fine-tune the voice, not the perception. Perception is a commodity you rent; voice is the thing you cannot buy.
The expensive failures were not training failures. They were infrastructure failures that produced plausible output instead of an error.
Guide pratiche per Manifest V3, strumenti browser e distribuzione di estensioni.
The Web Store review is a product gate, privacy policy, assets, and MV3 compliance matter as much as your code.
Real products need friction by design, ResistGate makes you type before distraction, not just block URLs.
Prezzi, scelte di prodotto e cosa ho imparato cercando di creare cose che le persone comprano davvero.
Game monetization splits cleanly into predictable-and-fair and random-and-manipulative. Regulators are banning the second, and the same line runs through how any product charges.
Retention won through dark patterns is debt. It builds regulatory and reputational liability and makes every future price increase impossible.
Compromessi architetturali, primitive invece di complessità e pattern di sistema duraturi.
Predict locally, decide centrally, and make rejection a first-class state.
The transport moves messages. Your protocol decides whether the product stays coherent.
Come prendo decisioni, resto concentrato e continuo ad avanzare senza un team.
You can't skip the ten. Every million starts as ten people who actually stayed.
The right model is the one your product's costs, users, and habits actually point to, not the trendy one. Ten questions get you there.
Sonno, routine, apprendimento e ciò che mi mantiene davvero a piena capacità.
Filtra le note per tema e mese.
Tema
Mese