Maybe not when answers will be almost instant, but the biggest gap to me now is latency, not capability. Having to wait for 5 minutes and more for an answer, I can switch to another project / feature / etc. and run work streams in parallel.

Same. I haven't been able to see how people let agent loops run without significant steering and produce good quality software. VS Code with one or two integrated terminals running is fine for me. Or a couple of VS Code instances if I'm working one a couple of projects concurrently. The advantage of VS Code is the code / diff visibility if you like to be hands on.

I often have many active. Bug investigations, writing code, reviewing, checking logs after deploys and so on.

I found that a good tool helps a lot once I switched to Github Copilot app. It solved the friction and mental tax for me. I easily manage 4 sessions in parallel on same or different projects while 2 was max in the past. The bottleneck now is only in review and decision making.

If you have more than one issue to work on, then you can open an agent for each one and go though them round-robin.

Maybe very early on a greenfield project you only have one known issue (the next feature you're building), but other than that seems like short-changing yourself.

Nope, they need to signal, that they know what they are doing and chic, and very trendy. And agent cnt must be > 12, open windows cnt > 6 otherwise feels himself as a peasant.

yeah I also don't really see a use case for me, like do ppl really run that many agents in parallel that they cannot comfortably multiplex them using just a terminal emulator

I usually have 5-8 at a time