<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai-Is on korchasa@*ops</title><link>https://korchasa.dev/tags/ai-is/</link><description>Recent content in Ai-Is on korchasa@*ops</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 28 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://korchasa.dev/tags/ai-is/index.xml" rel="self" type="application/rss+xml"/><item><title>A personal cli for every agent</title><link>https://korchasa.dev/posts/a-personal-cli-for-every-agent/</link><pubDate>Tue, 28 Apr 2026 00:00:00 +0000</pubDate><guid>https://korchasa.dev/posts/a-personal-cli-for-every-agent/</guid><description>&lt;p&gt;I moved my agents off raw external cli tools and onto a personal cli wrapper built per agent. My personal second-brain and my work second-brain each get their own utility with subcommands for reading the world and acting on it: jira, github, gitlab, prometheus, running specific commands on servers, cloud providers, internal utilities, and so on.&lt;/p&gt;
&lt;p&gt;Upsides:&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;restricting what the agent can do&lt;/li&gt;
&lt;li&gt;hiding keys, tokens and the rest from the agent&lt;/li&gt;
&lt;li&gt;shortcuts for popular processes and combinations&lt;/li&gt;
&lt;li&gt;shaping output formats for the agent, error messages included&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;It also makes it much easier to do interesting things on top. For example, the agent has a command to list containers, ssh into them and read their logs. But:&lt;/p&gt;</description></item></channel></rss>