<?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/3fc56006bf744f7693ebdbd44d3160aa&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/3fc56006bf744f7693ebdbd44d3160aa-00001.gif</thumbnail_url><duration>170.3</duration><title>Expanding Sightglass Functionality</title><description>Hey guys, in this video, I want to show you how we&apos;ve expanded the functionality of Cyclass. It&apos;s not just about transcription and subtitles anymore. We can now process the entire workflow after audio is finished. I&apos;ll demonstrate with an example of a podcast, where we can summarize, create show notes, and extract quotes from the transcript. We&apos;re building infrastructure around language models to make this possible. Let&apos;s run through it and see what happens!</description></oembed>