# Why Coding Agents Still Need Human Code Reviews

DevFeed: [Why Coding Agents Still Need Human Code Reviews](<https://devfeed.tech/articles/the-broken-windows-theory-of-coding-agents-32329.md>)

Original publisher: [Read original article](<https://newsletter.manager.dev/newsletter/the-broken-windows-theory-of-coding-agents>)

Author: Anton Zaides

Published: 2026-09-15T06:01:00Z

Content type: opinion

Language: en

Sources: [Manager.dev](<https://devfeed.tech/sources/manager-dev.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>)

Tags: [claude](<https://devfeed.tech/tags/claude.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [code-reviews](<https://devfeed.tech/tags/code-reviews.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

## AI overview

The article argues that coding-agent workflows still require human code reviews. It describes how making reviews optional caused them to drop sharply, allowing passable implementations to become templates that spread bugs, performance problems, race conditions, and confusion among agents.

## Source excerpt

When my most experienced engineer got tired of our shitty code