<?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/f02616575ef1459a921d8047e31d8af5&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/f02616575ef1459a921d8047e31d8af5-faa079b25012f6db.gif</thumbnail_url><duration>244.767</duration><title>AI Agent Auto-Triages Construction Inbox Emails</title><description>This Loom shows how Brother Solutions built an AI agent to automatically triage a construction company’s shared inboxes. Coordinators manage three shared inboxes by inspection phase, but failed inspection emails can be buried among receipt and marketing messages, requiring manual sorting. The agent runs in Google Workspace every few minutes, using an LLM to assign severity labels (red, yellow, green) and categories, then applies visual labels so urgent items surface first without clicks. The client expects about 10 hours per week saved per coordinator, roughly $75,000 in avoided project delays, faster same day inspection issue detection instead of three days later, and 100 percent inbox triage with zero effort.</description></oembed>