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.
UI design


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
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%.
