a. not everyone is using a monorepo :)
b. It's I think the difference between 2 SME vs a Fullstack engineer.
personally - and maybe I'm biased, I prefer the expert approach.
personally - and maybe I'm biased, I prefer the expert approach.
The multi-agent approach lets you scope each agent to what it knows best. Backend agent stays in /api, knows the DB schema cold. Frontend agent lives in /web, knows the component library.
When they need to coordinate, they message each other with just the relevant context - not the entire codebase.
It's also useful for parallel work. Both agents can be coding simultaneously instead of one waiting for the other.