AI coding agents keep stopping to ask questions. How do you babysit yours?
I've noticed my workflow has completely inverted over the past year. I used to sit at my Mac typing code; now Claude Code or Cursor does the long stretches, and my job is the interruptions: it stops, asks "should I refactor this or keep the interface stable?", and waits until I answer.
Which means I'm chained to my desk not by the work, but by the questions. Walking back from the kitchen to type "yes, option 2" feels absurd.
Curious how everyone else handles this:
Do you just stay at the desk while agents run?
Push notifications to your phone and sprint back?
SSH from a phone terminal app?
Multiple agents in parallel so there's always something to respond to?
I got frustrated enough that I built a phone app to remote into my Mac for exactly this, but I'm genuinely curious whether this bugs anyone else or whether my agents are just needy. What's your setup?
Replies