<?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/1ff1c0f241dc452ea820196995a29393&quot; frameborder=&quot;0&quot; width=&quot;1728&quot; height=&quot;1296&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1296</height><width>1728</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1296</thumbnail_height><thumbnail_width>1728</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/1ff1c0f241dc452ea820196995a29393-73deff30b38688aa.gif</thumbnail_url><duration>95.474</duration><title>Automated FAQ Email Replies with AI</title><description>This Loom explains an automation that auto-answers specific support and FAQ emails using an AI agent and a Pinecone vector database. It classifies incoming spot emails, and if an email is not an FAQ or support inquiry, it does nothing. When it is an FAQ/support email, the agent retrieves embedded FAQ policy data from Pinecone as memory, uses an OpenAI model to draft a reply, and classifies the response. The speaker demonstrates the workflow using a recent inbox email, showing the automated reply after refresh.</description></oembed>