<?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/273ecb75bbff4ff39ee194dea37b46ca&quot; frameborder=&quot;0&quot; width=&quot;1280&quot; height=&quot;960&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>960</height><width>1280</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>960</thumbnail_height><thumbnail_width>1280</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/273ecb75bbff4ff39ee194dea37b46ca-7537a1678c568125.gif</thumbnail_url><duration>285.285</duration><title>Demonstrating an AI Support Agent for GitHub Issue Resolution</title><description>In this Loom video, I demonstrated an agent I kicked off about four minutes ago to address an unanswered GitHub issue in the post-doc-js-rate repo. The agent utilized 26 tools, including the post-hog mcp for customer telemetry and live documentation searches. It concluded that the issue is likely a reverse proxy or WAF configuration problem rather than an SDK bug, and it provided a draft response for the customer. I encourage you to review the agent&apos;s findings and the proposed response, which we can further refine or share via Slack.</description></oembed>