Jongmin Lee@Jo_9m_n1

HealthVet is a multi-agent system that automates the vendor vetting process for U.S. health systems. When a hospital is evaluating a new clinical AI tool or EHR platform, procurement teams normally spend 2-6 weeks manually verifying certifications, checking for data breaches and lawsuits, reviewing SOC 2 reports, and cross-referencing compliance standing. HealthVet compresses that into under 90 seconds. Six specialized AI agents coordinate through Band, each owning a distinct layer of the vetting pipeline: Scout searches the web for customer references, breach history, and legal issues; Forensics analyzes certifications and flags anomalies; Compliance checks FDA, ONC, HIPAA, and SOC 2 standing; Gap maps every evidence category with severity ratings; Risk makes the final adversarial verdict and if evidence is too thin, it issues a veto and sends Scout back for a targeted re-investigation before making a final non-negotiable call; Synthesis delivers the full auditable trust report. The system is powered by AI/ML API for the reasoning-heavy agents, giving us access to gpt-4o and gpt-4o-mini through a single OpenAI-compatible endpoint, with each model tier matched to the cognitive demands of the task. The final vendor trust report is generated by Qwen2.5-72B running on Featherless AI, a deliberate choice: in a regulated industry, the compliance artifact needs to be produced by an open-weight model so hospitals and their legal teams can fully audit what generated their vendor report. Featherless makes running a 72B parameter model serverless and instant, with no GPU infrastructure required. HealthVet also includes a hospital onboarding wizard that captures each institution's specific priorities, weighted scoring across 9 categories, configurable deal-breakers, and risk appetite, so every verdict is calibrated to the hospital and not a generic rubric.

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. 💰 $10,000+ total prize pool Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.

📅 June 12–19, 2026 • June 12: Kick-off Stream • June 12–19: Online Build Phase • June 19: Project Submissions Ends 🌍 Fully online hackathon. Join and build from anywhere in the world. 🤝 Build practical enterprise workflows where AI agents communicate, coordinate, exchange context, and complete work together. 🧠 Powered by Band and Codeband, built for collaborative AI systems and agent orchestration. 🏆 Prize Pool: $10,000+ 🧑‍💻 Apply now to build the next generation of enterprise multi-agent systems.