A futuristic software development model is being tested where humans only provide high-level direction. AI agents write, test, and deploy code without human review, similar to an automated factory that can run with the lights off. This relies heavily on sophisticated, AI-driven QA processes.

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.

As AI generates more code than humans can review, the validation bottleneck emerges. The solution is providing agents with dedicated, sandboxed environments to run tests and verify functionality before a human sees the code, shifting review from process to outcome.

The endgame for software development isn't just code completion, but an "AI factory." A chain of specialized agents will handle design, coding, review, and security. This requires an interoperable platform where different models can check each other's work, with humans as "agent managers."

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.

Simply deploying AI to write code faster doesn't increase end-to-end velocity. It creates a new bottleneck where human engineers are overwhelmed with reviewing a flood of AI-generated code. To truly benefit, companies must also automate verification and validation processes.

To maintain high velocity with AI coding assistants, Chris Fregly has stopped line-by-line code reviews and traditional unit testing. He now focuses on high-level evaluations and 'correctness harnesses' that continuously run in the background, shifting quality control from process (review) to outcome (performance).

AI agents can generate and merge code at a rate that far outstrips human review. While this offers unprecedented velocity, it creates a critical challenge: ensuring quality, security, and correctness. Developing trust and automated validation for this new paradigm is the industry's next major hurdle.

Chris Fregley argues that manually reviewing AI-generated code is slow and ineffective. He has replaced traditional code reviews and unit tests with a focus on robust, continuous evaluation frameworks ("evals") and correctness checks that run in the background, allowing for faster and safer code deployment.