rubb3rDucc

I recently had the same experience with a Show HN thread I posted.

This thread hits very close to home for me. I'm engineering the frontend for a grocery list app as a capstone project right now and I'm handling a lot of the product and feature decisions, and the discussion about "just prompt Claude to build it" versus the reality of those decisions is something my team deals with constantly.

The example of reverse-engineering your grocery store's API and building a custom solution is awesome, and it's exactly the kind of thing that's now possible. But what I've found is that even with AI assistance, there are so many interconnected decisions that make this more than a one-shot prompt project.

I pushed for us to build a mobile app specifically to take advantage of portability (use it at home for planning, at the store for shopping) and the camera (image recognition with OpenAI and scanning barcodes with expo-camera). That sounds simple, but it cascades into hundreds of UX decisions about offline-first architecture, gesture patterns, camera permissions, and more.

The units and quantities problem mentioned in this thread is just the tip of the iceberg. I'm trying to figure out a data model that mirrors how people naturally think about groceries: how they categorize items, how they plan meals versus staples versus impulse buys, how they track what's running low. Modeling those mental models is genuinely hard.

What helps is that I worked as an ecommerce shopper at Whole Foods, and I learned that stores are meticulously organized with numbered bays and predetermined routes optimized for efficiency. Translating that knowledge into a system that can intelligently sort a shopping list based on store layout (which varies by location!) and typical shopping patterns is genuinely complex.

One of my teammates put it well: this is a simple idea, but it requires a level of care, expertise, and experience to get it right. AI's incredibly helpful for implementing solutions once we've made these decisions, but the decisions themselves require domain knowledge, user research, and taste. That's the part that's hard to automate, and it's what makes this a real engineering project rather than a weekend Claude experiment.

You’re right and that’s on me.

The Show HN link went straight to the app instead of the homepage, which makes it look gated. I’m fixing the flow rn so that a homepage explains the idea and then links to the app before sign-up.

I appreciate you for calling it out.

I hadn't heard of Beets until you mentioned it. I took a look at it and yes, it'll work with Beets.

I was using Python to get the bpms and keys on local tracks, and was going to start figuring how to fill in the missing metadata.

Thank you!

so I'm working on side project to make managing and exploring your music library easier.

The idea is you can set a few filters (like bpm, key, decade, genre) and then swipe through random songs, accept or reject them for inspiration or playlists. Kinda like Tinder but for digging through your own tracks.

It also tracks what's trending on TikTok/YouTube/SoundCloud weekly, so you can find stuff that’s blowing up, filterable by region. Plus it can build smart playlists automatically based on rules you set (like “new 90s house under 120bpm” every month).

It is just a tool to make working with your existing local/Apple/Spotify/SoundCloud library faster and more creative.

Here's a demo of it: https://filtered-f.web.app/