<?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/0f30e021e28049f39a309448222c48d2&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/0f30e021e28049f39a309448222c48d2-feecb5aa6116017e-full.jpg</thumbnail_url><duration>207.633333</duration><title>Deepdive AI Agent Observability with Regal Copilot</title><description>This Loom shows how to use Copilot to explore and investigate an AI agent observability dashboard. It demonstrates asking Copilot for co-observability trends over the last 14 days grouped by agent, revealing metrics like call volume and end to end latency. The video then shows drilling into specific issues such as contact interruptions and high repetition by asking Copilot to list affected calls from the last seven days with links to individual transcript reviews. Finally, it highlights using Copilot to identify repetition patterns to help guide further review and potential behavior changes.</description></oembed>