So how far should you let go? No one can answer that for you, but there is a scale to argue over.
Levels of autonomy
Also called Autonomy slider, The five levels
A scale for how much of the work an agent does before a person looks at it. At one end you approve every line. At the other you write a spec and judge only the result.
Each step up removes a check you were doing, and it is only safe if something else now does that check. People talk about the levels as if higher were better. The honest question is what replaced you at each one.
Say it to your agent
“In this repo you write and I review every diff, except docs/, which you can merge once CI is green. Put that in AGENTS.md. Then tell me which checks would have to exist before I could stop reading src/payments/.”