<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Productivity on Zachary Loeber's Blog</title><link>https://blog.zacharyloeber.com/tags/productivity/</link><description>Recent content in Productivity on Zachary Loeber's Blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 25 May 2026 10:00:00 -0600</lastBuildDate><atom:link href="https://blog.zacharyloeber.com/tags/productivity/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent Entrypoints</title><link>https://blog.zacharyloeber.com/article/agentic-entrypoints/</link><pubDate>Mon, 25 May 2026 10:00:00 -0600</pubDate><guid>https://blog.zacharyloeber.com/article/agentic-entrypoints/</guid><description>&lt;p>AI agents entering a repository cold waste large amounts of context reconstructing repository intent, topology, and authoritative workflows. Humans do this naturally through exploration. Agents pay for it directly in tokens, latency, and incorrect assumptions.&lt;/p>
&lt;p>An &lt;strong>agent entrypoint&lt;/strong> is a compact machine-oriented routing layer embedded at the top of a repository &lt;code>README.md&lt;/code>. Its purpose is to minimize exploratory context spend and direct agents toward authoritative operational paths immediately.&lt;/p>
&lt;p>The goal is not to teach the agent the repository. The goal is to route the agent toward the correct sources of truth as quickly as possible.&lt;/p>
&lt;p>This distills into a single question:&lt;/p>
&lt;blockquote>
&lt;p>“How do I compress the minimum viable understanding of a repository into the fewest tokens possible while preserving reliable navigation and correct usage?”&lt;/p>&lt;/blockquote></description></item></channel></rss>