I treat AI as my digital partner in pair programming. I've learned how to give it specific and well-defined tasks to do, and it gets it done. The narrower the scope and more specific the task then the more successful you'll have.
there’s a sweet spot in there, it’s not “as narrow as possible” - the most productive thing is to assign the largest possible tasks that are just short of the limit where the agents become stupid. this is hard to hit, and a moving target!
