<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Developer-Tools on David R. Longnecker - Converting Coffee to Code</title><link>https://drlongnecker.com/tags/developer-tools/</link><description>Recent content in Developer-Tools on David R. Longnecker - Converting Coffee to Code</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 14 Jul 2026 09:00:00 -0600</lastBuildDate><atom:link href="https://drlongnecker.com/tags/developer-tools/index.xml" rel="self" type="application/rss+xml"/><item><title>The Review Bottleneck</title><link>https://drlongnecker.com/blog/2026/07/review-bottleneck-ai-code-review-trust-capacity/</link><pubDate>Tue, 14 Jul 2026 09:00:00 -0600</pubDate><guid>https://drlongnecker.com/blog/2026/07/review-bottleneck-ai-code-review-trust-capacity/</guid><description>&lt;p&gt;AI-coauthored pull requests average 10.83 issues apiece against 6.45 for presumed human-only ones, according to &lt;a href="https://www.coderabbit.ai/blog/state-of-ai-vs-human-code-generation-report"&gt;CodeRabbit&lt;/a&gt;, a code-review vendor whose analysis covered 470 open source pull requests. Teams solved the bottleneck in writing code and built a new one in reviewing it.&lt;/p&gt;
&lt;p&gt;68% of engineers surveyed say AI has already changed how they run code review, and &lt;a href="https://leaddev.com/ai/as-ai-helps-us-write-more-code-whos-catching-the-bugs"&gt;86% of those use AI to pre-screen&lt;/a&gt; before a human ever opens the diff, per LeadDev&amp;rsquo;s 2026 survey. The same survey found review&amp;rsquo;s own response to all that upstream speed is mixed, not uniformly faster: 29% say reviews now take longer, 24% report time savings, and the largest share, 47%, see no change at all. LeadDev&amp;rsquo;s own conclusion matches what I&amp;rsquo;ve been watching: &amp;ldquo;Manual code review is now the bottleneck.&amp;rdquo;&lt;/p&gt;</description></item></channel></rss>