<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Blog on Javi — Data Engineer &amp; Agentic Loops</title><link>https://recursivejay.com/blog/</link><description>Recent content in Blog on Javi — Data Engineer &amp; Agentic Loops</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 02 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://recursivejay.com/blog/index.xml" rel="self" type="application/rss+xml"/><item><title>How AI has shifted the bottleneck in the development cycle</title><link>https://recursivejay.com/blog/bottleneck-shift-ai-development-cycle/</link><pubDate>Mon, 02 Nov 2026 00:00:00 +0000</pubDate><guid>https://recursivejay.com/blog/bottleneck-shift-ai-development-cycle/</guid><description>&lt;p&gt;Until recently, what consumed the most time in the agile development cycles was implementation, along with the stages that follow it: QA, testing and the corresponding feedback before starting the next iteration.&#10;Now, with LLMs and the new techniques that have grown out of them (autonomous loops, agent graphs, vibe coding), in my experience implementation time has stopped being a problem, but it hasn&amp;rsquo;t disappeared: &lt;strong&gt;it has spread across two points, planning and verification.&lt;/strong&gt;&lt;/p&gt;</description></item></channel></rss>