A Wine App
A personal sommelier that lives on the phone, not in the cloud.
A wine app for iOS and Android that inverts the usual architecture: the intelligence — taste profiling, recommendations, scanning a restaurant wine list and picking the bottle — runs on-device. The backend stays deliberately thin: it syncs user state and ships a static catalog, and the heavy lifting (scraping shops, enriching data) happens in batch on local hardware. The interesting bet: modern phones are smart enough that the cloud-brain + dumb-client split is optional.
- Gems recommendation engine v2 lands
- Catalog pipeline and app baseline ship
- Alex assistant goes fully LLM-driven
- Bottle scan rebuilt, Swedish stores added
- Full design system replaces ad-hoc UI
- On-device and cloud LLM strategy lands
- Decision: the heavy AI jobs live on a Mac Mini, not in the cloud
Decision. For my wine app, all heavy batch work — scraping a dozen shops with Playwright, deduplicating a 100k+ bottling catalog (a full…
- NULL beats a plausible guess
What I learned. When an AI-extracted field can't be grounded in the source text, NULL beats a plausible guess. Where it bit me: the batch…
- On-device AI is free per call — that's the trap
What I learned. On-device LLM calls cost $0 per call — so nothing in my stack ever flagged that I was making way too many of them. Why it…