<?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/83d3297e40e941b89a7ae2bfb09d70c6&quot; frameborder=&quot;0&quot; width=&quot;2880&quot; height=&quot;2160&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>2160</height><width>2880</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>2160</thumbnail_height><thumbnail_width>2880</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/83d3297e40e941b89a7ae2bfb09d70c6-851c64c2c582ac44.gif</thumbnail_url><duration>189.745</duration><title>Orchestrated AI Event Processing Demo</title><description>This Loom demonstrates a workflow for processing incoming events through an agent orchestration system. Hasan and Ibrahim show how running the feed displays events as they are handled, including reasoning traces, activity logs, and an escalation inbox for escalated items. They highlight labeled agents such as the orchestration, coordinator, supply chain, dealer, customer, and quality agents, along with features like dark mode, a tutorial guidance option, confidence scores per handled event, and summary outputs. They also mention viewing ontology graphs, action and tool calls, and the option to run processing in parallel.</description></oembed>