Im doing this, against my will i preffered an anchored approach but well the thing is i work for a rich guy, like most of us, i dont care the thing has 'money worth' i only care the rich guy gives me a fraction of the money we produce.

But still, if the thing is really bad it just makes my work harder so im trying to keep it stable, i am still reading the core of the system as much as i can, the agentic pipeline in this case. I have different reviewers working, custom company model, claude, codex they run in different stages of the projects like for SOLID, for linting, thats what we build the review agents for. I check the architecture and design documents throughly before starting, then the AI creates documents that the AI will consume and i check the details didnt changed, the same if you need example proof of concepts, like some inherited approach from the anchored spec driven times. At this point reading every line is not possible, not even worth it to discuss it at company level its not happening, so these kind of things are your safety net now so if anyone has other strats please do share them i think we all need them.