<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>azrod.me — Tech Blog</title><description>Technical articles about development, DevOps, and tech in general.</description><link>https://azrod.me/</link><item><title>Your agents don&apos;t need memory</title><link>https://azrod.me/en/articles/agent-memory-antipattern/</link><guid isPermaLink="true">https://azrod.me/en/articles/agent-memory-antipattern/</guid><description>In a codebase that serves as the source of truth, everything an agent needs to &apos;know&apos; should be mechanically verifiable. Giving your agents memory is patching in prose what should be encoded in the harness.</description><pubDate>Thu, 02 Apr 2026 00:00:00 GMT</pubDate><category>agents-ia</category><category>architecture</category><category>devops</category></item><item><title>Harness engineering: what Anthropic and OpenAI are actually doing with their agents</title><link>https://azrod.me/en/articles/ai-agent-harness/</link><guid isPermaLink="true">https://azrod.me/en/articles/ai-agent-harness/</guid><description>Anthropic and OpenAI published their harness engineering post-mortems weeks apart. Different problems, same conclusions — here&apos;s what to take away.</description><pubDate>Thu, 02 Apr 2026 00:00:00 GMT</pubDate><category>agents-ia</category><category>architecture</category><category>llm</category></item><item><title>Introduction to AI agents: beyond simple LLMs</title><link>https://azrod.me/en/articles/introduction-aux-agents-ia/</link><guid isPermaLink="true">https://azrod.me/en/articles/introduction-aux-agents-ia/</guid><description>Understanding what an AI agent is, how it works, how it differs from a plain language model, and how to architect a first agent with tools.</description><pubDate>Wed, 01 Apr 2026 00:00:00 GMT</pubDate><category>agents-ia</category><category>llm</category><category>architecture</category><category>typescript</category><category>ia-generative</category></item></channel></rss>