<?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/d20ec2f46ff5479e8d5fa9e1e2cc1765&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/d20ec2f46ff5479e8d5fa9e1e2cc1765-31c18402a73866eb.gif</thumbnail_url><duration>216.875</duration><title>Introducing PipelineGuard: Revolutionizing Data Pipeline Triage with AI</title><description>Hi, I&apos;m Venu Madhav, and in this video, I introduced PipelineGuard, an AI agent designed to automatically triage failing data pipelines in seconds, saving engineers between 45 minutes to 2 hours per incident. I demonstrated how it utilizes Elasticsearch tools to analyze logs and search engineering runbooks, providing a complete triage report with root causes and fixed steps. I created two custom tools within the AgentBuilder to enhance its functionality, ensuring it operates efficiently. I encourage you to explore how PipelineGuard can transform messy data operations into reliable automation.</description></oembed>