<?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/b108bd9b782d48cb975f9c770749e96c&quot; frameborder=&quot;0&quot; width=&quot;1670&quot; height=&quot;1252&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1252</height><width>1670</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1252</thumbnail_height><thumbnail_width>1670</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/b108bd9b782d48cb975f9c770749e96c-ea052dea02d9428e.gif</thumbnail_url><duration>311.211</duration><title>sagy_investigator_agent_complete</title><description>This Loom demonstrates how Sagey builds an AI agent to execute end to end technical support workflows. The example covers a client unable to log in, where an agent reads the Slack issue, investigates using Jira, GitHub, and the database, and determines it is a platform wide authentication incident rather than a user specific problem, referencing an existing incident titled Authentication failure broken login for active users. The workflow details show the tools used and the agent’s step sequence. The author notes the time improved from about 10 minutes for a human to 1.28 minutes for AI, saving 1.08 minutes, and mentions the ability to provide feedback.</description></oembed>