When agents can generate forty-five pull requests in a single day, the bottleneck is no longer writing code. It is reviewing it.
Teams running background agents against their ticket queues are discovering the output is generally good — not perfect, but good enough to merit review. The problem is volume. When an agent can produce a working PR in six minutes, you quickly end up with more reviewable code than your team can process. The PRs are not hallucinated garbage. They are reasonable code that might have made a different architectural choice than you would have. Every one of them needs eyes.
The most forward-thinking teams are building AI-assisted code review on top of AI-assisted code generation. The agent writes the PR. A second agent helps the reviewer understand what changed and why. The human still owns the merge, but the job shifts from reading every line to validating intent.
I've made the broader case elsewhere that event-driven agents are the underappreciated capability of this wave — and review is one of the highest-leverage events to wire. A new PR is an event. An agent should already be summarizing the diff, flagging risk, and surfacing the architectural decision before the human opens the tab.
Organizations that treat AI adoption as a code generation problem will plateau at the review bottleneck. The ones that build review infrastructure alongside generation infrastructure will compound. Pick your wall now.
Sources
Related Essays
The Algorithm Should Be Inspectable
Trust is the bottleneck for agent adoption, not capability. Hide the logic in a prompt and people stop using it. Make it inspectable code and they iterate with you.
Event-Driven Agents Change What Is Possible
A new tag, a new ticket, a new error. The most underappreciated capability in this wave is not generation. It is agents that fire because something happened.
Taste Does Not Scale With Token Throughput
Code production is no longer the constraint. Deploy pipelines, feature flags, and code review are. The new bottleneck is taste, and taste does not scale.
Key takeaways
- Generation throughput moves the bottleneck to review. Forty-five PRs a day is not a generation problem.
- The PRs are not hallucinated garbage. They are reasonable code that picked a different architecture than you would have. Each one needs eyes.
- Teams that build AI-assisted review on top of AI-assisted generation compound. Teams that only invest in generation plateau.
FAQ
Why does code review become the bottleneck?
Because an agent can produce a working PR in six minutes. At that rate you accumulate reviewable code faster than humans can process. The output is good enough to merit review, which is exactly why review cannot keep up.
How do teams unblock the review wall?
They build AI-assisted review on top of AI-assisted generation. The first agent writes the PR. A second agent helps the reviewer understand what changed and why. The human still owns the merge.