Case study
An AI deal-finder that spots under-priced auction lots
AI vision and live price comparisons that work out the maximum bid for a target resale profit.
AuctionAgent (my own product)Retail and e-commerce
Built from conceptDelivered
-, delivered in 5 days
The problem
Finding profitable auction lots means reading hundreds of listings and checking prices by hand.
How I approached it
- Seven build waves in five days, each with its own tests
- AI vision to classify and tag lots automatically
What was built
- Auction scraping and resale price comparison
- Maximum-bid calculation for a 30% resale profit
- AI classification, tagging and automatic categories
- Workflow engine and discovery scheduler
Stack
- .NET 10
- React
- Playwright
- Azure OpenAI
Outcomes
- Lot detail load time cut from 16 seconds to 10 milliseconds
- Hours of manual research replaced
Next step
Want the same result on your problem?
In 30 minutes you'll know whether to fix it, buy it, build it or leave it. No pitch deck.