Comment by RyanOD

That's one way. The approach I take is more of a "Hey, AI, here is what I'm trying to accomplish and here is the approach I plan to take. What do you think of this approach? Does it support my broader goals? Etc."

But, much of what I spend my time on are already solved problems (building retro video game clones) so AI has a LOT of high-quality content to draw upon. I'm not trying to create new, original products.