Deepak Swaminathan@s23deepak

PitchSideAI is an AI broadcast companion for football fans, commentators, and sports media teams. The product solves a common live-sports problem: audiences and commentators are flooded with match footage, stats, news, tactical context, and player history, but the most useful insight rarely arrives at the exact moment it matters. PitchSideAI turns that fragmented context into an interactive match companion. Before a match, a seven-agent research workflow gathers squad information, form, head-to-head history, player profiles, weather context, and current news, then synthesizes the results into structured commentary notes and narrative beats. During a match, the Fan Lens interface combines full-screen video, scoreboard state, automatically surfaced trivia, tactical overlays, and hold-to-ask Q&A. The vision path is designed for AMD GPU deployment with ROCm, StreamingVLM, vLLM-compatible Qwen vision-language model serving, and a fallback path that keeps the demo usable across hardware tiers. The result is a practical, end-to-end AI agent workflow that helps fans understand the game faster and gives commentators production-ready context without breaking the flow of live coverage.

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.