<?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>Software-Engineering on selamy.dev</title><link>https://selamy.dev/tags/software-engineering/</link><description>Recent content in Software-Engineering on selamy.dev</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 09 Jun 2026 01:13:55 +0000</lastBuildDate><atom:link href="https://selamy.dev/tags/software-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>Agents Need Situational Awareness</title><link>https://selamy.dev/posts/agents-need-situational-awareness/</link><pubDate>Tue, 09 Jun 2026 01:13:55 +0000</pubDate><guid>https://selamy.dev/posts/agents-need-situational-awareness/</guid><description>Useful agents need more than task execution. They need current state, memory, approval boundaries, and enough context to know what the task means.</description></item><item><title>Agents Need Boring Infrastructure</title><link>https://selamy.dev/posts/agents-need-boring-infrastructure/</link><pubDate>Wed, 13 May 2026 21:20:00 -0400</pubDate><guid>https://selamy.dev/posts/agents-need-boring-infrastructure/</guid><description>The hard part of agent systems is not getting a model to take an action. It is making that action safe, repeatable, inspectable, and useful over time.</description></item><item><title>Why I Write Specs Before Prompts</title><link>https://selamy.dev/posts/why-i-write-specs-before-prompts/</link><pubDate>Mon, 06 Apr 2026 01:19:00 +0000</pubDate><guid>https://selamy.dev/posts/why-i-write-specs-before-prompts/</guid><description>Prompts are requests. Specs are coordination systems. If you want reliable output from AI agents, start with the spec.</description></item></channel></rss>