<?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/c13cd31350cb446994fc167ecc96918b&quot; frameborder=&quot;0&quot; width=&quot;1662&quot; height=&quot;1246&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1246</height><width>1662</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1246</thumbnail_height><thumbnail_width>1662</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/c13cd31350cb446994fc167ecc96918b-6f6b33617469366c.gif</thumbnail_url><duration>88.317</duration><title>Understanding Agent Taste with DefaultTaste Profiling</title><description>In this video, I discuss how our taste is influenced by our agents and introduce DefaultTaste, our Agent Taste Profiling service. By analyzing an agent&apos;s preferences, we can uncover insights into their likes, such as Gemini Lyra&apos;s affinity for hip-hop and a BPM of 125. I also share findings on Gemini 3.1 Flashlight, revealing its color preference evolution from calm clinical to calm and a shift from light mode to dark mode. I encourage you to consider how understanding these tastes can enhance our interactions and decision-making. Let’s explore how we can leverage this information together!</description></oembed>