Some people run multiple coding agents at once


Some people run multiple coding agents at once.

But I'm skeptical - is it worth it?

When coding with AI assistance, human inspection and approval is the new bottleneck.

So running multiple agents at once just leads to a bigger inspection queue, right?
The wonderful book "The Phoenix Project" drives this point home.

Optimizing for anything that isn't the bottleneck is a waste of time because it just creates a bigger queue - It doesn't actually lead to things getting done faster.
Of course, this assumes you're inspecting manually.

And you almost certainly should be.

AI code review tools are great and useful, but I wouldn't blindly trust them. Human reviews remain critical for now.

View original on X