<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Tooling on Girish Shekhar</title><link>https://blog.girishshekhar.com/tags/tooling/</link><description>Recent content in Tooling on Girish Shekhar</description><generator>Hugo -- 0.163.3</generator><language>en-us</language><lastBuildDate>Wed, 20 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.girishshekhar.com/tags/tooling/index.xml" rel="self" type="application/rss+xml"/><item><title>The Harness Is the Agent</title><link>https://blog.girishshekhar.com/posts/harness-is-the-agents/</link><pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate><guid>https://blog.girishshekhar.com/posts/harness-is-the-agents/</guid><description>For two years we have talked about building agents as if an agent were a thing you construct. It isn&amp;rsquo;t. The harness — the loop, the tools, the context discipline — is the artifact you actually build, version, and debug. This post reframes the agent as emergent behavior, explains why agent frameworks now feel wrong-shaped in production, and offers a way to decide when to own the loop and when to rent it.</description></item></channel></rss>