The creative process with AI involves exploring many options, most of which are imperfect. This makes the collaboration a version control problem. Users need tools to easily branch, suggest, review, and merge ideas, much like developers use Git, to manage the AI's prolific but often flawed output.

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.

Most developers admit to giving pull requests only a cursory glance rather than pulling down the code, testing it, and reviewing every line. AI agents are perfectly suited for this meticulous, time-consuming task, promising a new level of rigor in the code review process.

When an AI model generates code, the focus of a pull request review changes. It's no longer just about whether the code works. The engineer must now explain and defend the architectural choices the model made, demonstrating they understand the implications and haven't just accepted a default, suboptimal solution.

Despite being the top community feature request for years, implementing a 'stacked diffs' workflow has been repeatedly shelved at GitHub. Previous efforts were deemed 'too risky' and 'too big of a change' for the platform. This illustrates how even highly desired features can be blocked by the inertia and complexity of a large, established system.

Go beyond static AI code analysis. After an AI like Codex automatically flags a high-confidence issue in a GitHub pull request, developers can reply directly in a comment, "Hey, Codex, can you fix it?" The agent will then attempt to fix the issue it found.

A surprising side effect of using AI at OpenAI is improved code review quality. Engineers now use AI to write pull request summaries, which are consistently more thorough and better at explaining the 'what' and 'why' of a change. This improved context helps human reviewers get up to speed faster.

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.

Instead of top-down directives, reviewing numerous diffs provides a natural context to debate practices and influence engineers. Good feedback spreads virally as those engineers apply the learnings in their own work and reviews, creating a scalable way to elevate code quality.