<?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/de4853ca1d8c443eaa62014bc06b4b36&quot; frameborder=&quot;0&quot; width=&quot;1854&quot; height=&quot;1390&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1390</height><width>1854</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1390</thumbnail_height><thumbnail_width>1854</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/de4853ca1d8c443eaa62014bc06b4b36-5a654c9e3cfd98ad.gif</thumbnail_url><duration>249.032</duration><title>Citycare Video AI for Signs and Potholes</title><description>This Loom demonstrates CityCare’s new video AI feature for inventorying road signs and detecting road anomalies in real time. The system scans signs and captures screenshots with certitude percentages plus five seconds before and after each sign is created, flagging missing signs when foliage prevents visibility. It also creates tasks for detected issues such as potholes, showing a June 10 task created at 7:59 AM with 31% accuracy and providing the exact image and surrounding video context for remote review. The author emphasizes that results appear within seconds via an edge and server-side AI pipeline.</description></oembed>