<?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/4c96df11ccf9415fa42d04898e5a916a&quot; frameborder=&quot;0&quot; width=&quot;1108&quot; height=&quot;831&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>831</height><width>1108</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>831</thumbnail_height><thumbnail_width>1108</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/4c96df11ccf9415fa42d04898e5a916a-0628f3204207f8df.gif</thumbnail_url><duration>594.473</duration><title>Automated research pt1: feature delivery and product direction</title><description>This Loom explains how the creator uses research agents and a weekly best-practices routine to drive strategic product work with coding agents. They tailor research to their specific audience, such as designers, UX managers, researchers, product owners, and small teams, focusing on out-of-the-box expectations rather than generic UX or accessibility checks. A weekly routine generates competitive landscape and trend briefs to uncover gaps, and the creator used that output to identify missing loop elements around sharing insights and to update MCP parity. They then created two main Linear projects for sharing and collaboration parity and MCP parity plus improvements, and asked a new agent to run the full research plan, implement, and shipable pipeline.</description></oembed>