<?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/8a03258b6e6b41048ee12055b4724ca2&quot; frameborder=&quot;0&quot; width=&quot;1816&quot; height=&quot;1362&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1362</height><width>1816</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1362</thumbnail_height><thumbnail_width>1816</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/8a03258b6e6b41048ee12055b4724ca2-2e90c066dafc182a.gif</thumbnail_url><duration>393.92</duration><title>Automating Workflows Through Operator Interviews</title><description>This Loom explains how an AI consultant automates business workflows using a two-phase interview process. The first phase starts with a high-level interview to map business operations, systems, people, and processes, then outputs complexity and ROI estimates plus an automation plan with savings and hours saved. It uses two models, a fast model for low-latency responses and a smarter model that extracts information in the background to maintain an evolving operations context. The second phase includes live screen sharing with the workflow operator to produce a detailed step-by-step workflow map grounded in evidence and highlighting exceptions and non-happy-path cases.</description></oembed>