<?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/49824ebdf35f45e08fe47d3e45eb97d0&quot; frameborder=&quot;0&quot; width=&quot;1326&quot; height=&quot;994&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>994</height><width>1326</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>994</thumbnail_height><thumbnail_width>1326</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/49824ebdf35f45e08fe47d3e45eb97d0-bfa7eacb3f65738d.gif</thumbnail_url><duration>181.4992</duration><title>Automating Generative Engine Queries and Data Processing</title><description>In this video, I discuss a workflow I developed for automating the analysis of queries related to gender optimization across different models, including Charge, Club, Gem, and Perplexity. I demonstrate how the process can handle multiple queries efficiently and format the responses for output, which includes the date, query, and generated response. I&apos;ve also started storing this data in a database to better manage the large volume of information, as Google Sheets has its limitations for dashboard integration. Moving forward, I plan to explore ways to scale this process further. I encourage viewers to think about how we can enhance this workflow together.</description></oembed>