<?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/a33ce9cc55544159bb34719ce0878f96&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/a33ce9cc55544159bb34719ce0878f96-b0c1dcd1d95f5783.gif</thumbnail_url><duration>290.411</duration><title>Voice AI Agent for Presentations Demo</title><description>In this Loom, I demo a real time voice interactive presentation agent with three built features. First, voice Q and A with slight navigation, then a margin interruption mode, and finally a fully autonomous auto presentation mode. I walk through drug discovery as a slow, high stakes gamble, noting it typically takes over a decade and costs more than two billion dollars, and that more than 90 percent of compounds fail in clinical trials. I cover how AI speeds target identification, explains CRISPR screens, and then moves into generative molecular design and ADMET optimization. I do not ask viewers to take any action.</description></oembed>