<?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/544e617a5a0643d7841c73dcd8930385&quot; frameborder=&quot;0&quot; width=&quot;1728&quot; height=&quot;1296&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1296</height><width>1728</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1296</thumbnail_height><thumbnail_width>1728</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/544e617a5a0643d7841c73dcd8930385-bb3f5894ede668a3.gif</thumbnail_url><duration>246.77</duration><title>Introducing the Drug Discovery Agent: A Multi-Agent Evidence Collection System 🧬</title><description>Hi everyone, in this video, I present a demo of my Drug Discovery Agent, a multi-agent evidence collection project that takes a gene or disease as input and generates a therapeutic report based on collected evidence. I explain the system&apos;s workflow, which includes various agents like the planning agent, evidence collector, normalization agent, scoring agent, and explanation agent, all working together to provide a comprehensive analysis. During the live demo, I showcase how the user interface validates queries, creates plans, and assesses evidence from multiple sources. I also highlight the dashboard that shows the contribution of each source to the evidence report. I encourage you to watch the demo to understand the capabilities of this innovative tool.</description></oembed>