<?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/ab80de32dfa54a08b0e3ccbe283151c2&quot; frameborder=&quot;0&quot; width=&quot;1878&quot; height=&quot;1408&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1408</height><width>1878</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1408</thumbnail_height><thumbnail_width>1878</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/ab80de32dfa54a08b0e3ccbe283151c2-ef6439a395104041.gif</thumbnail_url><duration>2064.997</duration><title>Taproot Saves, Routes, and Retrieves Knowledge</title><description>This Loom explains Taproot’s purpose and demonstrates how it saves and retrieves AI-generated notes in your own knowledge base. The founder shows uploading photos of sticky notes to Claude, saving the synthesized output through Taproot, and then pulling up the same note in a new chat where edits can be made and re-saved. He connects this routing and organization to a local Obsidian vault where notes become real files, placed in the right folders with tags and links that build a knowledge graph over time. He also previews BriefMe, which summarizes the user’s most recently saved work (for example, from yesterday) and can provide project status such as sprint progress and active blockers for a project like Glug.</description></oembed>