How to Build Reliable AI Products: A Production Engineering Guide
AI demos are easy. Reliable AI products are an engineering problem.
Technical posts, product decisions, and honest observations — written while building, not after.
The best place to start if you want to understand how I think and work.
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
What shipped, what broke, and what changed — written as it happened.
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.
What AI features look like when regular people use them in real life.
Every AI call has a marginal cost. 'Unlimited' on a fixed price means one of three things: weaker models, hidden limits later, or burning cash.
An MCP tool is not useful because it exists. It is useful when the agent understands when, why, and how to call it.
Practical guides for Manifest V3, privacy-first browser tools, and extension distribution.
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.
Pricing, product choices, and what I've learned trying to make things people actually buy.
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.
Architecture tradeoffs, primitives over complexity, and durable system patterns.
A personal site is not just content. It is a data model.
I rebuilt my personal hub as a three-layer system: website for humans, API for software, MCP for agents.
How I make decisions, stay focused, and keep moving without a team.
You can't skip the ten. Every million starts as ten people who actually stayed.
The right model isn't the trendy one — it's the one your product's costs, users, and habits actually point to. Ten questions get you there.
Sleep, routines, learning, and what actually keeps me at full capacity.
Filter notes by topic and month.
Topic
Month