<?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/1d950f1f342d462c8ba4d4e0af751905&quot; frameborder=&quot;0&quot; width=&quot;1954&quot; height=&quot;1465&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1465</height><width>1954</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1465</thumbnail_height><thumbnail_width>1954</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/1d950f1f342d462c8ba4d4e0af751905-00001.gif</thumbnail_url><duration>375.06666666666666</duration><title>Exploring AI Features in Reconciliation</title><description>Hey everyone, in this Loom, I share some concepts on reconciling our AI features. I discuss different treatments, from separating them to integrating them in a chat UI. I focus on the question of whether we should allow users to open all features at once. No action is requested, but it&apos;s important to understand the possibilities.</description></oembed>