Wow, really negative comments here! I'm not a cursor user, and I can't say I love the look of this UI, but my team and I are very heavy users of https://www.conductor.build . Managing many agents, each in their own sandbox, felt like indisputably the future after using conductor for a day. We were a cursor company before conductor, but we cancelled all our seats around the time Opus 4.6 dropped because conductor was vastly more productive. So IMO, Cursor is definitely moving in the right direction w/ this -- the days of the IDE are numbered & they're correctly designing for the future.

For me, there's no way to get into a flow state if I'm thinking about terminal windows and Claude Code. Even before conductor dropped on our team, I'd been building CLIs to spin up agent sandboxes on work trees -- but that still required a lot of terminal window management.

My work now is usually: - 1 hard task (hard to think about more than 1 of these at once) -- localized to a sandbox, but with multiple agents in different convo threads - N simpler tasks (usually 4-8). These are usually one-shottable. They're a pleasure to come up with & ship.

I'm thinking about and managing the hard task. When it's cooking for more than 10 seconds, I'm switching to an ez task and pushing them along.

Just like OG coding -- hard to be in a flow state every day. But when it works, you can get an unbelievable amount of work done.

I'll be walking around now, and I'll add voice notes of little tasks or cleanups I want to throw an agent at when I get home. Good products are made of 1000s of small, good decisions -- and now those are free to implement, the slowest part is writing them down as tickets.