Lucas Martins do Carmo Borges@devlucasmartins

Pet nutrition questions often reach clinics as incomplete histories: unclear portions, mixed diets, unread labels, treats that are not tracked, uncertain body condition, and behaviour changes around feeding. VetBridge turns that messy owner intake into structured data for dogs and cats. The app validates intake, extracts or normalizes label and feeding details, applies a deterministic red-flag engine, calculates a PawScore risk band with uncertainty, and creates two outputs: clear owner education and a concise veterinary handoff report. VetBridge is intentionally guarded. It is not an AI veterinarian, does not diagnose disease, does not prescribe medication, and does not replace a physical exam. Urgent red flags override routine nutrition guidance, therapeutic diet requests are routed back to the veterinarian, and uncertain photo-supported body-condition signals are labeled as uncertain. The MVP uses FastAPI, Next.js, demo fixtures, mock AI mode, and a Fireworks/Gemma integration path for structured extraction, report drafting, and safety verification, with AMD Developer Cloud planned for fixture evaluation.

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.