You can get more confidence by asking the LLM about when the architecture would be appropriate than by trying to intuit it yourself. The LLM is trained on so many more architectures and stories of how they panned out than you are.
The skill is really in manually testing before handoff.
I still get occasional hallucinations, wrong answers, and entirely unnecessary change proposals from LLMs. An LLM being confident in its own work does not make me confident in it.
You get that from humans too.
No shit, that's why we review code...
You're not making a point
And LLMs are already better code reviewers than humans are; take a look at the bugs found in the Linux kernel.