<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/9bd207eb9d0246a189beb02fa7a99222&quot; frameborder=&quot;0&quot; width=&quot;1250&quot; height=&quot;937&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>937</height><width>1250</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>937</thumbnail_height><thumbnail_width>1250</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/9bd207eb9d0246a189beb02fa7a99222-0de58be94a6e8cba.gif</thumbnail_url><duration>182.942</duration><title>AI Discharge Copilot for Medication Reconciliation</title><description>This Loom explains a discharge co-pilot that helps doctors reconcile medication and test information to prevent errors at discharge. It notes that many medical errors occur when turning four specialists prescriptions into a single clean discharge list, often done from memory without pharmacist double-checking. The co-pilot previews and grounds discharge packet decisions in evidence, showing whether medications should be continued, discontinued, or modified, and cites reasons such as home-med continuation, drug-drug interactions, renal dose conflicts, and adverse drug events. The demo shows the doctor using the grounded sources while clicking to quickly access the supporting information.</description></oembed>