[cautiouscat]

I’ve also been finding that “Spin a cadre of agents to design/implement a feature from a concise spec” is really difficult. It’s been faster (for me) to do what you said and do a hybrid.

I’ve been trying out this cadre of agents idea with PR stacking and while I think it’s going to end up working fine, it took so much massaging to get it to where I needed it to be. Whereas with the hybrid approach, the problem space is a lot narrower and easier for me to define and the LLM to implement.