{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/94308657c2a149d7b332ec1ba8814630\" frameborder=\"0\" width=\"1728\" height=\"1296\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1296,"width":1728,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1296,"thumbnail_width":1728,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/94308657c2a149d7b332ec1ba8814630-0d8e9805daaab152.gif","duration":436.382,"title":"Smart Multi-Agent Hospital Triage System Demo","description":"This Loom explains how the speaker built a smart multi agent AI system to automate hospital intake and eliminate chaos around triage, beds, and doctor assignment. After seeing their grandmother’s final days in a government hospital, they created a workflow where five coordinated agents handle urgency assessment, bed allocation, doctor scheduling, mental health analysis, and conflict resolution. The system includes a weighted priority queue based on severity, age, vitals, and waiting time, and it rolls back allocations to avoid blocking doctors when resources clash. Built with LangGraph orchestration, Grok APIs, PostgreSQL, LangChain, and a Streamlit Python dashboard, it was the second runner up in the Laddie hackathon."}