I realized as I was doing this also, I think I sort of mentioned with a sketch, I really often was taking the output of a language model prompt and doing something in Python. Another one of the patterns was increase the temperature, ask it to write the sequel, you get like 10 different sequel answers in parallel. And just chaining that stuff, it's like very Pythonic functions,. Like you can really just imagine, oh, I just need to write a for loop, IJust need to run this function, take the output, V didn't do another function, very procedural. But when you, uh, all the abstractions in the open app open AI API, the things