CIRIS — Circuit Image Recognition & Issue Spotter

Every semester, engineering students waste hours in electronics labs debugging simple wiring mistakes, while overstretched teaching assistants can't reach everyone. Around 70% of "it's not working" requests turn out to be avoidable errors like a reversed LED or a missing ground connection. CIRIS solves this. Students select their lab exercise, upload 1–4 photos of their real breadboard from different angles, and receive instant, specific wiring feedback — what's wrong, why, and how to fix it. CIRIS is powered by AI/ML API using a two-step pipeline: GPT-4o analyzes the circuit images against the correct reference wiring, then GPT-4o-mini structures the output into reliable JSON for the interface. It offers two modes — Structured Lab Exercises for high-accuracy reference-based diagnosis, and Free Analysis for any custom circuit. Built entirely with native.builder (React frontend) and Supabase (auth, database, storage, Edge Functions), CIRIS is a real computer-vision product, not a chatbot wrapper — turning a simple phone photo into actionable engineering feedback.