<?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/6d1a5f4619b043f5bbe0ddb6a5299f35&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/6d1a5f4619b043f5bbe0ddb6a5299f35-c658fe3db5b75bf3.gif</thumbnail_url><duration>64.506</duration><title>AgentEye - AI Agent Observability </title><description>This Loom explains the Agent AI project, including its components and how it was built using an AI Assistant with prompts. It shows that the system returns results along with a Trace ID, which can be used to retrieve signals and trace what happened. The speaker emphasizes that the Trace ID supports understanding the workflow by letting viewers click and review the sequence of events.</description></oembed>