AI Code Review

In February 2025, Andrej Karpathy posted a tweet that most engineers scrolled past: “There’s a new kind of coding I call ‘vibe coding’, where you fully give in to the vibes, embrace exponentials, and forget that the code even exists… I just see stuff, say stuff, run stuff, and copy-paste stuff.” Most senior engineers read it and moved on. “A prototyping trick. Nothing serious.” They were wrong. Fifteen months later, 63% of users of AI coding tools are non-technical. CEOs are building internal systems with Claude prompts. PMs are replacing Excel with automated dashboards. BAs are creating workflow automation without touching a codebase. And critically — they are shipping those things to production. ...

Series Orientation: This article is Part 3 of the AI Code Review & Vibe Coding series, examining the unique failure modes of AI-generated code. For the broader business context, see the Series Executive Summary. When engineers first review AI-generated code, they often encounter a counterintuitive phenomenon: the code looks right. It passes compilation. The tests are green. The function signatures are clean. The variable names are descriptive. And somewhere inside, there is a logic error that will silently corrupt your data, or a missing authorization check that will expose every user record to the first person who thinks to try a simple query manipulation. ...

Answer-first: “Vibe coding”—relying on AI to write code without understanding it—creates complex, hard-to-maintain codebases that fail in production. Resolving this requires automated AI code reviews in the CI/CD pipeline to enforce design conventions and detect security vulnerabilities. What You’ll Learn That AI Won’t Tell You Setting up automated AI reviewer tools in GitHub Actions. How to enforce design guidelines and coding standards in LLM-assisted pipelines. In February 2025, Andrej Karpathy, former Tesla AI Lead and OpenAI co-founder, tweeted a phrase that would define a new paradigm in software development: ...