Loot Check

On the App Store with 300+ users and 3,000+ items scanned.

Keywords: Mobile

Role: App Developer

Date: 2026

Problem

Price discovery for used items is time consuming and full of small frictions: identifying the exact item, finding the fair market price, and comparing what you’d keep after platform fees.

Solution

An app that uses Claude to value an item, compare payouts from different marketplaces, and suggest the best option to sell it.

First prototype, 167 items scanned

UI design

Two Loot Check screens with notes. The home screen’s History list of past scans, noted as previous items saved on the device. The screen after a photo of an Akai MIDI keyboard is added, with an empty slot noted as users can add up to 3 photos per scan, and an optional detail field noted as optional user input to guide the AI output.
Two Loot Check result screens with notes. The result for an Akai MPK Mini MK2 keyboard tagged Electronics, Good and Certain, noted as results labeled Certain or Best guess, and an estimated resale value of $65 that resells for $50 to $80, noted as an estimated low to high value range. Further down, Where to Sell recommends Reverb and lists what you’d pocket after fees on Reverb, eBay, Facebook Marketplace, Mercari and OfferUp, noted as AI compares payouts from marketplaces after fees and suggests an option, and a ready-to-post listing with a Copy title button, noted as a title and description for copy and paste.

Reducing inaccurate results

Early testing with friends and family quickly showed the limits of using Claude in the first prototype. When testing items like jewelry and bracelets, the vision model struggled to identify some brands and gave very inaccurate prices. Watching them experience this problem led to two key design decisions:

1. Optional Keyword Hints: Letting users enter a brand or description before scanning to guide Claude.

2. Confidence Ratings (Best guess, Certain): Being open when Sonnet’s confidence is low so users don’t trust a wrong estimate, and allowing them to take another photo and retry.

System architecture

Architecture diagram. The iOS app uploads a photo to a single analyze endpoint on Vercel, which calls Claude Sonnet 5.5 to identify and price the item and Upstash Redis for daily caps and search allowances. A JSON response returns to the app as an item valuation with payouts from marketplaces.

Balancing accuracy and API costs

A key product decision was determining how items were valued. Using a web search for every scan increased accuracy, but because it raised API costs by 3-4x and the total latency from 6 to up to 27 seconds, I chose to rely on Sonnet’s pre-trained data for non-unique items.

Price discovery method

The project started with resale pricing, but the most interesting use case was showing the app something original like a painting. That grew the idea into a price discovery tool for both used and unique items.

This required two separate pricing strategies. Since handmade and unique items lack past transaction data, a search workflow finds the asking prices of visually comparable items to estimate the value.

Results

Data from 2,189 items showed that a small group of users accounted for 55% of total scans and that around 54% of the results were ‘best guess’ versus 46% ‘certain’. Adding another photo improved accuracy by 19% and hints helped a little by 8%.