<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/"><channel><title>Architecture on A naive bidder</title><link>https://anaivebidder.com/tags/architecture/</link><description>Recent content in Architecture on A naive bidder</description><language>en-us</language><lastBuildDate>Mon, 15 Jun 2026 18:02:17 +0200</lastBuildDate><atom:link href="https://anaivebidder.com/tags/architecture/index.xml" rel="self" type="application/rss+xml"/><item><title>Tips to Structure Codebases for AI Agents in 2026</title><link>https://anaivebidder.com/posts/tips-to-structure-codebases-for-ai/</link><pubDate>Mon, 15 Jun 2026 18:02:17 +0200</pubDate><dc:creator>Ruben Afonso</dc:creator><guid>https://anaivebidder.com/posts/tips-to-structure-codebases-for-ai/</guid><description>&lt;p&gt;Code in 2026 has become a commodity.&lt;/p&gt;
&lt;p&gt;Anthropic claims that 80% of its new code &lt;a href="https://venturebeat.com/technology/anthropic-says-80-of-its-new-production-code-is-now-authored-by-claude-how-your-enterprise-can-keep-up"&gt;comes from agentic AI&lt;/a&gt;, and then announced &lt;a href="https://www.anthropic.com/news/claude-fable-5-mythos-5"&gt;Claude Fable 5&lt;/a&gt;. OpenAI recently evaluated an internal beta product with &lt;a href="https://openai.com/index/harness-engineering/"&gt;zero lines of manually-written code&lt;/a&gt;. In a world where creating new code is inexpensive, the challenge shifts towards maintainability.&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;A consistent project structure helps both the agent and the development team to validate and navigate change.&lt;/p&gt;
&lt;/blockquote&gt;
&lt;p&gt;So the question remains: how to increase codebases in a way that they can be reused and expanded?&lt;/p&gt;</description></item></channel></rss>