I personally explicitly avoid parallel agents, since it creates too much cognitive debt, and sometimes an agent may need steering towards an architectally sane solution mid-work.
Agreed. With simple stuff it works. But then again with simple stuff it’s pretty fast to do it sequentially.
With complex stuff I often have open the “thinking” output so I can stop/interrupt with guidance. Without that it’s often garbage output that I then have to work to fix, which is difficult to do while you’re also doing the same with a parallel process.
Totally agree, the more parallel agents you spawn the more the probability of you vibe coding rather than guide coding. There comes a point when my mind says just commit and move on, which I fight to not do it.
My approach these days is to do one change at a time, until I can fully merge it with confidence.