<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>alzr.us writing</title><description>Long-form posts on AI-augmented engineering, the operator&apos;s view, and the founder/CTO arc. By Adam Lazarus.</description><link>https://alzr.us/</link><language>en-us</language><item><title>What 15 years of founder/CTO work taught me about operator-mode</title><link>https://alzr.us/writing/founder-to-operator/</link><guid isPermaLink="true">https://alzr.us/writing/founder-to-operator/</guid><description>The muscle that ships a company from zero is not the muscle that keeps a company aimed. I have shifted between modes more than once. Each time, the habits that worked before were the habits I had to break first.</description><pubDate>Sat, 30 May 2026 00:00:00 GMT</pubDate></item><item><title>A writing-voice guide for your AI assistants</title><link>https://alzr.us/writing/writing-voice-guide-for-ai-assistants/</link><guid isPermaLink="true">https://alzr.us/writing/writing-voice-guide-for-ai-assistants/</guid><description>I stopped giving my AI assistants rules and started giving them reading material. The shift is from instruction to artifact. The em-dash regex is the catchy part. Loading files as books-the-system-reads is the durable one.</description><pubDate>Fri, 29 May 2026 00:00:00 GMT</pubDate></item><item><title>Running candidate background research with parallel Claude Code agents</title><link>https://alzr.us/writing/parallel-agents-for-hiring-research/</link><guid isPermaLink="true">https://alzr.us/writing/parallel-agents-for-hiring-research/</guid><description>I built a parallel-agent workflow to make candidate background research faster. It made the research deeper instead -- because running ten investigations at once turns a noisy classifier into a confident one. The speedup was the bonus.</description><pubDate>Thu, 28 May 2026 00:00:00 GMT</pubDate></item></channel></rss>