<?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/27a3bbf46869495ca7226f8dd702e38a&quot; frameborder=&quot;0&quot; width=&quot;2560&quot; height=&quot;1920&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1920</height><width>2560</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1920</thumbnail_height><thumbnail_width>2560</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/27a3bbf46869495ca7226f8dd702e38a-3289f206eb87a43f.gif</thumbnail_url><duration>1550.252</duration><title>Introducing the Multi-Agent AI Shopping Assistant</title><description>Hi everyone, in this video, I’m excited to showcase the multi-agent product assistant I’ve been developing, which acts as an AI shopping assistant using Amazon Electronics data. I walk you through the architecture, highlighting how user requests are processed through a Streamlit UI and FastAPI, with a robust orchestration layer managed by Langref. We have specialized agents for product QA, shopping cart, and warehouse management, all working together to ensure a seamless shopping experience. I also touch on the reliability and scalability of the system, including our CI-CD processes with GitHub Actions. Please stay tuned for the live demo at the end!</description></oembed>