<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Codo - Blog</title><description>Engineering essays and case studies on platform foundations, velocity, and architecture that survives success.</description><link>https://codo.tech/</link><language>en-us</language><item><title>Your AI Agent Should Not Grade Itself: Software Self-Verification Crisis</title><link>https://codo.tech/blog/your-ai-agent-should-not-grade-itself-software-self-verification-crisis/</link><guid isPermaLink="true">https://codo.tech/blog/your-ai-agent-should-not-grade-itself-software-self-verification-crisis/</guid><description>I built Boundary-First Engineering around one annoying question: who verifies the code when AI wrote the checks too? My answer is boundaries, contracts, and evidence that came from outside the implementation loop.</description><pubDate>Fri, 15 May 2026 00:00:00 GMT</pubDate><category>AI</category><category>Software Engineering</category><category>Testing</category><category>Architecture</category><author>Omer Morad</author></item></channel></rss>