<?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/" xmlns:dc="http://purl.org/dc/elements/1.1/"><channel><title>AI-Assisted Engineering · a.j.djalali</title><link>https://alexdjalali.github.io/</link><description>a.j.djalali's personal blog</description><language>en</language><managingEditor>a.j.djalali</managingEditor><lastBuildDate>Thu, 05 Nov 2026 05:51:05 +0000</lastBuildDate><atom:link href="https://alexdjalali.github.io/series/ai-assisted-engineering/index.xml" rel="self" type="application/rss+xml"/><image><url>https://alexdjalali.github.io/images/portrait.png</url><title>a.j.djalali</title><link>https://alexdjalali.github.io/</link></image><item><title>Your Docs Are a Corpus Now</title><link>https://alexdjalali.github.io/posts/your-docs-are-a-corpus-now/</link><guid isPermaLink="true">https://alexdjalali.github.io/posts/your-docs-are-a-corpus-now/</guid><pubDate>Sun, 01 Nov 2026 12:00:00 -0400</pubDate><dc:creator>a.j.djalali</dc:creator><description>Why a repository's twelve hundred markdown files now have three readers (people, a wiki and a retrieval index), and what happened when we adopted Google's Open Knowledge Format, turned our READMEs into a company wiki and pointed our own RAG product at our own codebase.</description><category>ai</category><category>software-engineering</category><category>developer-tools</category><category>architecture</category><category>claude</category></item><item><title>Rethinking Agile in the Age of AI</title><link>https://alexdjalali.github.io/posts/rethinking-agile-in-the-age-of-ai/</link><guid isPermaLink="true">https://alexdjalali.github.io/posts/rethinking-agile-in-the-age-of-ai/</guid><pubDate>Wed, 28 Oct 2026 12:30:00 -0400</pubDate><dc:creator>a.j.djalali</dc:creator><description>Agile's values still hold, but its practices were tuned for a world where code was expensive. What six months of AI-driven development suggests about roles, design, review, estimation and the Definition of Done.</description><category>ai</category><category>software-engineering</category><category>process</category></item><item><title>Six Months of Enterprise Development with AI</title><link>https://alexdjalali.github.io/posts/six-months-of-enterprise-development-with-ai/</link><guid isPermaLink="true">https://alexdjalali.github.io/posts/six-months-of-enterprise-development-with-ai/</guid><pubDate>Wed, 28 Oct 2026 12:00:00 -0400</pubDate><dc:creator>a.j.djalali</dc:creator><description>What six months, 1,200 commits and 594 stories of building a production AI platform with agents taught me about what holds, what breaks, and where AI still falls down.</description><category>ai</category><category>software-engineering</category><category>architecture</category><category>process</category></item><item><title>Professional Software Engineering for AI and Distributed Systems</title><link>https://alexdjalali.github.io/posts/professional-software-engineering-for-ai-and-distributed-systems/</link><guid isPermaLink="true">https://alexdjalali.github.io/posts/professional-software-engineering-for-ai-and-distributed-systems/</guid><pubDate>Sun, 01 Mar 2026 00:00:00 +0000</pubDate><dc:creator>a.j.djalali</dc:creator><description>That the gap between writing code and engineering production systems can be taught, given a graduate course built on deliberate technical debt, an architecture defense and AI used as a force multiplier.</description><category>software-engineering</category><category>education</category><category>distributed-systems</category><category>ai</category><category>architecture</category></item><item><title>Anatomy of an AI Engineering System</title><link>https://alexdjalali.github.io/posts/anatomy-of-an-ai-engineering-system/</link><guid isPermaLink="true">https://alexdjalali.github.io/posts/anatomy-of-an-ai-engineering-system/</guid><pubDate>Thu, 26 Feb 2026 00:00:00 +0000</pubDate><dc:creator>a.j.djalali</dc:creator><description>How seventeen slash commands, seven templates and three model tiers, each of them short and single-purpose, turn Claude Code into a full software development lifecycle.</description><category>ai</category><category>software-engineering</category><category>developer-tools</category><category>claude</category><category>architecture</category></item><item><title>How I Learned to Love the Bomb</title><link>https://alexdjalali.github.io/posts/how-i-learned-to-love-the-bomb/</link><guid isPermaLink="true">https://alexdjalali.github.io/posts/how-i-learned-to-love-the-bomb/</guid><pubDate>Sun, 22 Feb 2026 00:00:00 +0000</pubDate><dc:creator>a.j.djalali</dc:creator><description>Why I went from skeptic of AI-assisted programming to building an engineering system around it, and why what won me over was not the models but the discipline you wrap around them.</description><category>ai</category><category>software-engineering</category><category>developer-tools</category><category>claude</category></item></channel></rss>