<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Documentation on NotNil Blog</title><link>https://notnil.org/en/tags/documentation/</link><description>Recent content in Documentation on NotNil Blog</description><generator>Hugo</generator><language>en-US</language><copyright>© Matthieu Moreau</copyright><lastBuildDate>Sat, 07 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://notnil.org/en/tags/documentation/index.xml" rel="self" type="application/rss+xml"/><item><title>.MD vs .DOCX FINAL FIGHT</title><link>https://notnil.org/en/posts/29-markdown-first-docx-once/</link><pubDate>Sat, 07 Nov 2026 00:00:00 +0000</pubDate><guid>https://notnil.org/en/posts/29-markdown-first-docx-once/</guid><description>&lt;figure&gt;&lt;img src="https://notnil.org/images/posts/29-markdown-first-docx-once/feature-final-fight.jpg"&gt;&#10;&lt;/figure&gt;&#10;&#10;&lt;p&gt;One of my favorite topics in agentic work is how to build the most efficient context layer possible for our collaboration with agents.&lt;/p&gt;&#10;&lt;p&gt;What I call the &amp;ldquo;context layer&amp;rdquo; is all the shared knowledge that agents will consume and produce. Back when it was just us humans, the context layer was pretty simple: a Drive or a SharePoint, and office files passed around by email: &lt;code&gt;.docx&lt;/code&gt;, &lt;code&gt;.xlsx&lt;/code&gt;, &lt;code&gt;.pptx&lt;/code&gt;. For now I&amp;rsquo;m leaving out the other parts of the human context layer, like Jira, Confluence and Notion. They&amp;rsquo;ll get their own post.&lt;/p&gt;</description></item></channel></rss>