Levi Adler@LeviAlbuquerque

Orvex is an AI-assisted inspection copilot for solar operations and maintenance teams. It helps turn photovoltaic panel images and bounded video frame evidence into structured, human-reviewable triage results. The system analyzes visual inputs, identifies possible defects such as hotspots, soiling, shadowing, cracking, vegetation, diode issues, or offline modules, then returns prioritized findings with confidence, risk score, visual evidence, and recommended next actions. The product is designed as a decision-support workflow, not an autonomous diagnostic system. Every result is validated against a strict schema, stored in an inspection job, and routed for human review. Orvex combines a FastAPI backend, a Next.js review interface, supervised solar anomaly baselines, local VLM inference, and an experimental worker queue for bounded video processing. Its goal is to make solar inspection review faster, more traceable, and easier to standardize.

Grab your ideas, spin up compute, and start building what’s next! Start with $100 in AMD Developer Cloud credits and begin building right away. Get access to hands-on tutorials, workshops, and curated learning resources to help you build faster and go further. To unlock credits and join the hackathon, sign up for the AMD AI Developer Program. 🤝 Go solo or team up — ship something real. 💰 $21,500+ total prize pool & 1 × AMD Radeon™ AI PRO R9700 GPU up for grabs. 📍 On-site Venue (May 9-10): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 📍On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.