<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Eugene Kungurov</title><description>Long-form articles on AI tooling, infrastructure, and engineering leadership.</description><link>https://eugenekungurov.com/</link><language>en-us</language><item><title>AI Agents Learn From Your Worst Code First</title><link>https://eugenekungurov.com/articles/ai-agents-learn-from-your-worst-code-first/</link><guid isPermaLink="true">https://eugenekungurov.com/articles/ai-agents-learn-from-your-worst-code-first/</guid><description>AI agents pattern off the code they read, and verbose generated or legacy code has ten times the surface area of clean code. Encapsulation keeps the agent focused on code that reflects the team&apos;s conventions.</description><pubDate>Tue, 14 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Building AI Agents: Short Narrative Beats More Instructions</title><link>https://eugenekungurov.com/articles/building-ai-agents-short-narrative-beats-more-instructions/</link><guid isPermaLink="true">https://eugenekungurov.com/articles/building-ai-agents-short-narrative-beats-more-instructions/</guid><description>Neither narrative nor constraints work alone when building AI agents. Combine them — context first, then directives — and the agent fills gaps with judgment instead of guessing blind.</description><pubDate>Tue, 31 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Role Separation Turns AI Agent Review Into Actual Review</title><link>https://eugenekungurov.com/articles/role-separation-turns-ai-agent-review-into-actual-review/</link><guid isPermaLink="true">https://eugenekungurov.com/articles/role-separation-turns-ai-agent-review-into-actual-review/</guid><description>A single agent writing code and reviewing it isn&apos;t real review. The fix is isolated context, adversarial intent, and agents scoped to one role each.</description><pubDate>Sun, 22 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Anchor AI With Precise Language, Not More Instructions</title><link>https://eugenekungurov.com/articles/anchor-ai-with-precise-language/</link><guid isPermaLink="true">https://eugenekungurov.com/articles/anchor-ai-with-precise-language/</guid><description>The real problem isn&apos;t AI tooling — it&apos;s finding the right place for the right context. A few precise sentences reshape everything downstream.</description><pubDate>Sun, 15 Mar 2026 00:00:00 GMT</pubDate></item><item><title>AI Supply Chain Risk: The Missing Category</title><link>https://eugenekungurov.com/articles/ai-supply-chain-risk/</link><guid isPermaLink="true">https://eugenekungurov.com/articles/ai-supply-chain-risk/</guid><description>We talk about AI alignment risk and AI misuse risk. We&apos;re missing a third category: what happens when AI becomes a supplier in its own infrastructure supply chain.</description><pubDate>Sun, 01 Mar 2026 00:00:00 GMT</pubDate></item></channel></rss>