sincere question: why would you not be able to code review it in the same way you would for humans?
Agents could generate more PRs in a weekend than my team could code review in a month.
Initially we can absolutely just review them like any other PR, but at some point code review will be the bottleneck.
Surely humans are the ones initiating the agent though, no? Just do that at a measured pace. And set up comprehensive prompts/mechanisms to make sure the agent satisfies your criteria for tests, style, etc - there's a lot of prompts and tools around the Cline/Roo community for doing stuff like that.