i mainly wanted a single central place for giving my intent no matter what it is. this is the central ux principle I used while building NIMBUS. and also why it isnt a chrome extension or an afterthought addition to current browser forks. wanted to see what agent native ui for a browser would look like. i dont think many agent browsers are doing this right now.

i just did alpha launch, so its too early to say, how users are using it. but it is in a state where i myself can actively dog food it.

i also dont consider this browser automation at all, its just the way browsers should be. giving the user the freedom to think about the task at hand and not worry about tab switching, different implementations of different websites. and at the same time give enough visibility into what the agent is doing.