<?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/10467f69f84b442fbbff9c3d73953e9e&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/10467f69f84b442fbbff9c3d73953e9e-00001.gif</thumbnail_url><duration>300.084</duration><title>Video 1: Custom GPT for Deal Improvement Competition</title><description>In this video, I discuss my approach to the innovators&apos; challenge, specifically the deal improvement competition. I created a custom GPT model that allows us to generate highlights, information about the deal, and details about the merchant. I explain how the GPT model can be used to extract information from merchant websites and generate relevant content. I also mention the importance of setting strict limits for the generated content. Additionally, I ask for knowledge about typical discounts and promotions in the domain. Overall, this video showcases the capabilities of the custom GPT model and its potential for improving deals.</description></oembed>