The focus of "code review" is shifting from line-by-line checks to validating an AI's initial architectural plan. After plan approval, AI agents like OpenAI's Codex can effectively review their own generated code, a capability they have been explicitly trained for, making human code review obsolete.

The ease of creating PRs with AI agents shifts the developer bottleneck from code generation to code validation. The new challenge is not writing the code, but gaining the confidence to merge it, elevating the importance of review, testing, and CI/CD pipelines.

An internal OpenAI team maintains a codebase written entirely by AI. By removing the "escape hatch" of manual coding, they are forced to solve fundamental problems in providing better context and documentation to the AI, thus uncovering best practices for agent interaction.

Inspired by fully automated manufacturing, this approach mandates that no human ever writes or reviews code. AI agents handle the entire development lifecycle from spec to deployment, driven by the declining cost of tokens and increasingly capable models.

Contrary to the belief that AI introduces risk, Intercom's AI code review agent led to a lower revert rate for AI-approved code. This demonstrates that AI can enhance safety and quality, not just speed, by systematically enforcing standards on every pull request.

To maximize an AI agent's effectiveness, establish foundational software engineering practices like typed languages, linters, and tests. These tools provide the necessary context and feedback loops for the AI to identify, understand, and correct its own mistakes, making it more resilient.

With AI agents autonomously generating pull requests, the primary constraint in software development is no longer writing code but the human capacity to review it. Companies like Block are seeing PRs per engineer increase massively, creating a new challenge for engineering managers to solve.

A new paradigm for AI-driven development is emerging where developers shift from meticulously reviewing every line of generated code to trusting robust systems they've built. By focusing on automated testing and review loops, they manage outcomes rather than micromanaging implementation.

The debate isn't between manual coding and blindly trusting AI ("vibe coding"). A new discipline, "agentic engineering," is emerging. This involves creating new best practices, security controls, and governance for using AI agents to build software. This structured approach will replace the current era of unchecked individual developer experimentation.