<?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/aefb4cd5a0eb4157ac4453db43f1649f&quot; frameborder=&quot;0&quot; width=&quot;1664&quot; height=&quot;1248&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1248</height><width>1664</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1248</thumbnail_height><thumbnail_width>1664</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/aefb4cd5a0eb4157ac4453db43f1649f-5604582b96013467.gif</thumbnail_url><duration>111.872</duration><title>Forethought critique UI</title><description>In this video, I walk through the process of getting a new critique by selecting one of my drafts, specifically the bottlenecks one. I demonstrate how to run two fast models in the background and check the progress of critiques from different sources like Claude and GeminiPro. I highlight the importance of reviewing the top critiques and the run details to gain insights. I also mention that I haven&apos;t fully considered the user interface yet and invite thoughts on what summaries would be most helpful at the top. Please share any feedback or suggestions you have on this process.</description></oembed>