SASHIKUMAAR S J@iamsk003

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.

CLARIS AI is an end-to-end explainable multimodal video captioning system designed to generate accurate, natural, and context-aware captions from short video clips. It combines visual scene understanding, speech recognition, OCR, motion analysis, and multimodal AI reasoning to build a unified understanding of a video before generating four distinct caption styles that remain grounded in the same evidence. Unlike conventional captioning systems that often produce generic descriptions, CLARIS AI first constructs an evidence ledger from multiple perception modules and then performs a single multimodal reasoning step to generate all caption styles consistently. This design preserves factual consistency while allowing different writing styles—including formal, sarcastic, tech humor, and everyday humor—without changing the underlying facts.

🌎 Online Hackathon | 📅 August 3–10, 2026| 💻 Powered by native.builder The official native.builder hackathon, hosted by NativelyAI and lablab.ai. Join founders, developers, designers, and builders to create real AI-native applications powered by native.builder: from idea to deployed product, fully in the cloud. 💻 This hackathon is fully online. No travel required.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.