<?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/b4f8e8f07f8b4704a926faf98d74c449&quot; frameborder=&quot;0&quot; width=&quot;2074&quot; height=&quot;1555&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1555</height><width>2074</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1555</thumbnail_height><thumbnail_width>2074</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/b4f8e8f07f8b4704a926faf98d74c449-ba9eaba8da320726.gif</thumbnail_url><duration>147.7527</duration><title>Understanding Structured Generations in LLMs</title><description>In this video, I discuss the concept of Structured Generations within LLMs at WordWare. I demonstrate how to structure output data formats using a prompt about Italian restaurants in San Francisco, comparing unstructured and structured responses. You&apos;ll see how structured generations provide more detailed and organized information, which can be incredibly useful. Please take a moment to consider how you might apply this in your own work.</description></oembed>