Three AI products, three different AI architectures

Why

AI changes what one person can ship — and it changes what "good AI product judgment" means. Reading about that is one thing. To pressure-test it, I set out to ship three complete consumer products, each built on a deliberately different AI architecture: cloud LLM, fully on-device AI, and no model at all. Every one is live today with its own brand, website, and users' data to protect.

Cleared — an opinionated AI to-do app

clearedfirst.com · "Clear what matters. First."

Most to-do apps are lists; Cleared has an opinion. Say a goal and AI plans the steps. Your tasks then compete — you judge them head-to-head in a bracket, or AI referees — producing a ranked tier list with one task spotlighted as clear next. Work in order until the app says "All clear."

• The AI bet — cloud LLM economics as a product constraint. The entire ranking runs in a single cost-optimized Gemini request, and app attestation ensures only the real app can spend model quota. Latency and unit cost were designed, not discovered.
• React 19, TypeScript, Tailwind, Firebase (auth, sync, App Check), Gemini — shipped as a PWA and an iOS app via Capacitor.

IronProof — proof over motivation

ironproof.org · "The scale lies. Proof doesn't." · live on the App Store

A fitness progress tracker built on a simple insight: photos reveal what scale weight can't. IronProof turns progress photos into a timeline of transformation — weight and measurements overlaid on every shot, dates read automatically from photo metadata, synced across devices.

• The bet — breadth of shipping. One codebase runs on the web, iOS, Android, and desktop. It went through Apple's review and is live on the App Store.
• The hard parts were unglamorous product engineering: HEIC photo decoding, EXIF date extraction, offline-first storage with cross-device sync.

Grava — calorie counting, without the counting

gravacal.com · "Snap. Confirm. Eat."

A native iPhone calorie tracker that removes the logging that kills every diet app: photograph a meal, a menu, a nutrition label, or a delivery screenshot, and AI estimates calories and macros. Estimates come back as honest ranges, and the app biases toward the top, middle, or bottom of the range depending on whether you're cutting, maintaining, or bulking — protecting the user's goal instead of faking precision.

• The AI bet — fully on-device. Built in SwiftUI on Apple Intelligence: the Vision framework for food recognition and OCR, and the on-device foundation model for estimation. Nothing you photograph ever leaves the device — privacy as the differentiator.

What building all three taught me

• Architecture is a product decision. Cloud models buy capability and cost you unit economics; on-device models buy privacy and cost you capability. Choosing per product — not per hype cycle — is the actual skill.
• AI compresses build time, not judgment time. The models wrote a lot of code. Deciding what each product refuses to do — Cleared's single-request budget, Grava's ranges instead of false precision — was still the work.
• Shipping is the credential. Brands, websites, App Store review, auth, sync, data protection — the last 20% is where product managers earn the title.