[danenania]

I'm building a terminal-based tool that is somewhat similar to Devin[1]. Part of the premise of my tool is that "AI software engineer" is the wrong target for current model capabilities.

That's L5, and it may well be the future, but as it stands today, I believe L3-L4 is a more productive target for a coding agent. Before building full autonomy, we first need the infrastructure to precisely guide the models and iterate efficiently on our interactions with them.

Once that foundation is in place, it will then be possible build more and more robust layers of autonomy on top. But crucially, the developer will always be able to a drop a few layers down and take over the controls.

1 - https://github.com/plandex-ai/plandex