I recently cancelled my cursor subscription (and chatgpt), and went all in on pi.dev.

The thing I've noticed is cursor was better at producing better results with a really shitty prompt.

That said, well written prompts on pi.dev seem to be out performing anything I ever tried on Cursor. That may just be me, but it's what I've noticed in my work.

This week I had 4 different agents, each with sub agents, all working on different tasks. Mostly greenfield work. My feedback was mostly nitpicky. I was pretty damn impressed