<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Jules-Api on Mike CK - Electrical Engineer and Developer</title><link>https://www.drmhse.com/tags/jules-api/</link><description>Recent content in Jules-Api on Mike CK - Electrical Engineer and Developer</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 10 May 2026 14:58:58 +0000</lastBuildDate><atom:link href="https://www.drmhse.com/tags/jules-api/index.xml" rel="self" type="application/rss+xml"/><item><title>Your AI Coding Agent Deserves a Real Review Desk</title><link>https://www.drmhse.com/posts/building-jules-flutter-client/</link><pubDate>Sun, 10 May 2026 09:00:00 +0300</pubDate><guid>https://www.drmhse.com/posts/building-jules-flutter-client/</guid><description>&lt;p>AI coding agents are getting powerful enough that the hard part is no longer just &amp;ldquo;can it write code?&amp;rdquo;&lt;/p>
&lt;p>The harder product question is this:&lt;/p>
&lt;blockquote>
&lt;p>Can you keep track of the work, review what changed, respond at the right moment, and trust the interface enough to use it every day?&lt;/p>&lt;/blockquote>
&lt;p>That is the reason I built a Flutter client for Jules.&lt;/p>
&lt;p>Jules already has the interesting primitive: sessions that can plan, ask for approval, work against a repository, report progress, accept follow-up messages, and produce code changes. But an agent workflow quickly becomes messy if the client only feels like a thin chat box.&lt;/p></description></item></channel></rss>