<?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/b5fe536c089d4f258b4bfabb395bb93c&quot; frameborder=&quot;0&quot; width=&quot;1138&quot; height=&quot;854&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>854</height><width>1138</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>854</thumbnail_height><thumbnail_width>1138</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/b5fe536c089d4f258b4bfabb395bb93c-a066e8255b31df5b.gif</thumbnail_url><duration>181.68</duration><title>Gemini Assistant Stand Alone vs Under HOOPT Connections</title><description>In this video, I demonstrate how the Gemini assistant functions in both standalone and personalized modes using Semih&apos;s account. Initially, the assistant struggles to provide relevant movie suggestions, but once integrated with Hult, it offers tailored recommendations based on Semih&apos;s preferences and location. I highlight the importance of personalization in AI interactions and how it can enhance user experience. Please take a moment to consider how we can further improve our AI systems based on this demo.</description></oembed>