<?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/68f2123e26d1470bb1942794ed11d821&quot; frameborder=&quot;0&quot; width=&quot;1113&quot; height=&quot;834&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>834</height><width>1113</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>834</thumbnail_height><thumbnail_width>1113</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/68f2123e26d1470bb1942794ed11d821-f2a0ec3d125ba684.gif</thumbnail_url><duration>52.649</duration><title>AI Agent - Agent Workflow for Tweet Generation 🚀</title><description>In this video, I explain a straightforward NIAgent workflow that analyzes previous tweets on X.com to generate new ones. We store the sentiment of these tweets as vector embeddings, which helps the AI recreate content using OpenAI&apos;s model. I also highlight the importance of the prompt given to the AI agent in this process. Please take a moment to review the workflow and let me know your thoughts!</description></oembed>