<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Code Review on piotrooo's codes</title><link>https://piotrooo.codes/tags/code-review/</link><description>Recent content in Code Review on piotrooo's codes</description><generator>Hugo</generator><language>en-us</language><copyright>© Piotr Olaszewski</copyright><lastBuildDate>Thu, 03 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://piotrooo.codes/tags/code-review/index.xml" rel="self" type="application/rss+xml"/><item><title>Reviewing AI-Generated Code with herdr-reviewr</title><link>https://piotrooo.codes/reviewing-ai-generated-code-with-herdr-reviewr/</link><pubDate>Thu, 03 Sep 2026 00:00:00 +0000</pubDate><guid>https://piotrooo.codes/reviewing-ai-generated-code-with-herdr-reviewr/</guid><description>AI coding agents have changed the speed of implementation. A task that once required an hour of typing can now produce a working patch in a few minutes. That is useful, but it does not remove the need to understand the code.
In fact, it creates a new bottleneck.
The agent finishes its work, and now I need to inspect every changed file, understand the decisions it made, find the details that require another pass, and explain my feedback with enough context for the agent to act on it.</description></item></channel></rss>