"Test harness is everything, if you don't have a way of validating the work, the loop will go stray"

This is the most important piece to using AI coding agents. They are truly magical machines that can make easy work of a large number of development, general purpose computing, and data collection tasks, but without deterministic and executable checks and tests, you can't guarantee anything from one iteration of the loop to the next.

Agents run tools in a loop.

The ability to test their work reliably is a tool, if you don't give them that, it's kinda silly to expect any kind of quality output.