<?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/6792c3bf3cc649ef8d35ecbe5a4c62c5&quot; frameborder=&quot;0&quot; width=&quot;1152&quot; height=&quot;864&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>864</height><width>1152</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>864</thumbnail_height><thumbnail_width>1152</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/6792c3bf3cc649ef8d35ecbe5a4c62c5-07edb2d9addb1ffd.gif</thumbnail_url><duration>124.023</duration><title>Improving TechWatch Automation with Tavily and MuleRun</title><description>This Loom describes how the author is improving a TechWatch news automation pipeline using Tavilli and Mulrun. They currently ingest RSS feeds and emails, summarize articles into a knowledge base, and send a morning digest email and write summaries into an Obsidian vault synchronized with Git. The LinkedIn Portability Explorer can also write to the same vault, but the workflow is not fully connected yet, so a future composer will be able to read those items. Because the planned digest email would be too large, they asked Mulrun for a smarter approach to group related items, pick the most interesting ones, and skip less relevant content, following the OpsGen front matter style for now.</description></oembed>