Where do AI coding assistants usually break down in your workflow?

AI tools can handle basic CRUD apps UI layouts and API integrations surprisingly well these days.

The problems usually start when things get more complicated optimistic UI updates WebSocket disconnects heavy database queries or edge cases that aren't obvious at first.

I was working on a real time collaborative feature recently and the LLM generated the UI components pretty quickly. But when it came to keeping the state in sync reliably, I still had to work through a lot of the logic myself to avoid subtle bugs.

For those using AI coding agents in production, how do you handle this?

Do you usually write the core architectural logic yourself or have you found a good way to guide the LLM through these kinds of edge cases?