<?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/82f41ffde94949beb941cb191f53c3ec&quot; frameborder=&quot;0&quot; width=&quot;1904&quot; height=&quot;1428&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1428</height><width>1904</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1428</thumbnail_height><thumbnail_width>1904</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/82f41ffde94949beb941cb191f53c3ec-97155e55f38600e3.gif</thumbnail_url><duration>322.88</duration><title>Freeplay and the Google ADK</title><description>In this video, I walk you through the integration of Freeplay with the Google ADK, highlighting how they complement each other to optimize agent performance. I demonstrate a practical example where I request a walking trail for my dog, showcasing the research pipeline and the detailed logs that flow into FreePlay. I also explain how we can evaluate agent performance and manage prompts effectively within Freeplay. If you&apos;re interested in using these tools, I encourage you to explore the integration options and the code setup I outline. Overall, this integration provides a robust framework for enhancing your agent&apos;s capabilities while maintaining observability and prompt management.</description></oembed>