{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/64bf3255caa0442d9eae34b641745271\" frameborder=\"0\" width=\"1110\" height=\"832\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":832,"width":1110,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":832,"thumbnail_width":1110,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/64bf3255caa0442d9eae34b641745271-7b18385fbd98a3a3.gif","duration":230.265,"title":"OpenEMR Clinical Copilot with Gemini on GCP","description":"This Loom demos a Clinical Copilot added to a fork of the OpenEMR project, powered by Gemini on GCP, where physicians can chat about a specific patient’s data. The presenter logs in as a physician, searches for a patient named Phil, and asks questions like current medication and adherence to Norvasc, with the assistant synthesizing records and returning answers plus follow-up suggestions and sources used. The copilot also answers questions such as what the doctor needs to know and can summarize what changed since the last visit, limited to the current patient. The Loom highlights full observability via a self-hosted LangFuse instance, showing traces, model usage, and JSON responses."}