<?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/7028b33f85d34bc29ae21a8d283f744f&quot; frameborder=&quot;0&quot; width=&quot;3024&quot; height=&quot;2268&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>2268</height><width>3024</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>2268</thumbnail_height><thumbnail_width>3024</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/7028b33f85d34bc29ae21a8d283f744f-d3b3c6fe414c3e22.gif</thumbnail_url><duration>812.351</duration><title>Supervise AI Agents with Twilio Conversations</title><description>This Loom explains how to supervise AI agents using Trello Conversations in a simpler way than production traces, logs, cores, and dashboards. The speaker notes that watching agents in production can be complicated and still makes it hard to know what the agent actually experienced. With Trello Conversations, conversations flow into Conversation Orchestrator, and when a conversation ends, Conversation Intelligence runs operators on it, including a focus on detecting hallucinations. The discussion emphasizes using conversation data to see where agents went wrong.</description></oembed>