--- title: Stop Catching the Same AI Mistakes in Code Reviews description: Recurring code review comments on AI-written code are a sign the team needs a checkable rule, not another manual catch. The fix: mine the last quarter of PRs... canonical: https://daily.dev/posts/stop-catching-the-same-ai-mistakes-in-code-reviews-c87kjwqch twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Stop Catching the Same AI Mistakes in Code Reviews | daily.dev og:description: Recurring code review comments on AI-written code are a sign the team needs a checkable rule, not another manual catch. The fix: mine the last quarter of PRs... og:url: https://daily.dev/posts/stop-catching-the-same-ai-mistakes-in-code-reviews-c87kjwqch og:image: https://api.daily.dev/og/posts/C87KJwQCH.png og:image:alt: Stop Catching the Same AI Mistakes in Code Reviews og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Stop Catching the Same AI Mistakes in Code Reviews **[Aviator Blog](https://daily.dev/sources/aviator-blog)** · 7 min read · 0 upvotes · 0 comments ## Summary Recurring code review comments on AI-written code are a sign the team needs a checkable rule, not another manual catch. The fix: mine the last quarter of PRs for comments repeated more than twice, then route each one to the cheapest enforcement layer. Formatting and naming go to linters, semantic rules like 'handlers must authenticate first' go to Aviator Verify invariants, and judgment calls stay with humans. Aviator's 'AI from PR comments' source analyzes PR history and drafts invariants from recurring feedback, and the setup docs can get you to a first invariant in about ten minutes. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is AI slop in code review? AI slop is AI-generated code that technically works but ignores a team's established conventions, such as skipping a data-access layer or an authentication step. It usually passes tests and looks fine in a diff, which is why only experienced reviewers tend to catch it, and why it keeps recurring across pull requests. _Teams fighting repeated AI code review feedback can track automation approaches like this on daily.dev._ ### Should I enforce a code review rule with a linter or a semantic check? Use a linter for rules about syntax or simple patterns, like formatting, naming conventions, or banned function calls, since these are deterministic and fast. Use a semantic invariant check when the rule requires understanding what a change actually does, such as enforcing that writes go through a repository layer or that handlers authenticate before running business logic. _Developers deciding how to structure review automation can follow this kind of tooling guidance on daily.dev._ ### How do I turn a recurring code review comment into an automated rule? Mine the last quarter of pull request history for comments repeated more than twice, keep only the ones that would apply across different authors (not personal style preferences), then write each as a single checkable sentence that's specific about the assertion but vague about implementation details like file paths. Test it in draft mode before promoting it to block merges. _Teams building review automation workflows can keep up with approaches like this on daily.dev._ ## Similar posts on daily.dev - [AI Code Review Best Practices](https://daily.dev/posts/ai-code-review-best-practices-ii7hbaa3j) · Aviator Blog · 15 upvotes · 1 comments - [How long before we stop reading the code?](https://daily.dev/posts/how-long-before-we-stop-reading-the-code--omchyubsd) · The New Stack · 1 upvotes · 0 comments - [6 Best Practices for Human Reviewers: How to Review AI-Generated Code](https://daily.dev/posts/6-best-practices-for-human-reviewers-how-to-review-ai-generated-code-xuylblot0) · Aviator Blog · 0 upvotes · 0 comments - [Stop Sending IDE-Catchable AI Code Errors to Review](https://daily.dev/posts/stop-sending-ide-catchable-ai-code-errors-to-review-lepmps4fa) · JetBrains · 0 upvotes · 0 comments - [Code Reviews in the Age of AI](https://daily.dev/posts/code-reviews-in-the-age-of-ai-acvy63drb) · Earthly · 1 upvotes · 0 comments --- Tags: [#cicd](https://daily.dev/tags/cicd), [#ai-coding](https://daily.dev/tags/ai-coding), [#code-review](https://daily.dev/tags/code-review) [View this post on daily.dev](https://daily.dev/posts/stop-catching-the-same-ai-mistakes-in-code-reviews-c87kjwqch) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Stop Catching the Same AI Mistakes in Code Reviews","url":"https://daily.dev/posts/stop-catching-the-same-ai-mistakes-in-code-reviews-c87kjwqch","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/stop-catching-the-same-ai-mistakes-in-code-reviews-c87kjwqch"},"datePublished":"2026-10-26T08:59:05.609Z","dateModified":"2026-10-26T08:59:39.245Z","description":"Recurring code review comments on AI-written code are a sign the team needs a checkable rule, not another manual catch. The fix: mine the last quarter of PRs...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0a74d1203ea840aa53f7455addfea03a?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0a74d1203ea840aa53f7455addfea03a?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Aviator Blog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Aviator Blog","logo":"https://media.daily.dev/image/upload/s--PW_g-vhQ--/f_auto,q_auto/v1774960853/logos/aviator-blog?_a=BAMAMiWQ0","url":"https://daily.dev/sources/aviator-blog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/stop-catching-the-same-ai-mistakes-in-code-reviews-c87kjwqch","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"cicd,ai-coding,code-review","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Aviator Blog","item":"https://daily.dev/sources/aviator-blog"},{"@type":"ListItem","position":3,"name":"Stop Catching the Same AI Mistakes in Code Reviews"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/stop-catching-the-same-ai-mistakes-in-code-reviews-c87kjwqch#faq","mainEntity":[{"@type":"Question","name":"What is AI slop in code review?","acceptedAnswer":{"@type":"Answer","text":"AI slop is AI-generated code that technically works but ignores a team's established conventions, such as skipping a data-access layer or an authentication step. It usually passes tests and looks fine in a diff, which is why only experienced reviewers tend to catch it, and why it keeps recurring across pull requests. Teams fighting repeated AI code review feedback can track automation approaches like this on daily.dev."}},{"@type":"Question","name":"Should I enforce a code review rule with a linter or a semantic check?","acceptedAnswer":{"@type":"Answer","text":"Use a linter for rules about syntax or simple patterns, like formatting, naming conventions, or banned function calls, since these are deterministic and fast. Use a semantic invariant check when the rule requires understanding what a change actually does, such as enforcing that writes go through a repository layer or that handlers authenticate before running business logic. Developers deciding how to structure review automation can follow this kind of tooling guidance on daily.dev."}},{"@type":"Question","name":"How do I turn a recurring code review comment into an automated rule?","acceptedAnswer":{"@type":"Answer","text":"Mine the last quarter of pull request history for comments repeated more than twice, keep only the ones that would apply across different authors (not personal style preferences), then write each as a single checkable sentence that's specific about the assertion but vague about implementation details like file paths. Test it in draft mode before promoting it to block merges. Teams building review automation workflows can keep up with approaches like this on daily.dev."}}]} ```