AI Writes the Code, but Humans Can't Review It All. Now What?

Very true Sylvain. The evolution of the code review agents is on have configurable autonomy, work on the human learning side, prevent issues both on pull requests or trunk based development depending your style. Working on it https://dromeas.ai/code-review

But it does not stop there, coding agents need the right context to limit iterations and testing cycles. Indeed the CI/CD automation is paramount.