Transcription
Should you actually bother using a prompt framework when using AI? So right now, there are a bunch of videos going around saying that you don't need to learn prompt engineering. You don't need a prompt framework. Instead, all you need to do at the end of any prompt is say, "Ask clarifying questions," and then ChatGPT or Claude or whatever you're using is going to ask you questions and help you refine and get to your answer.
To be fair, I also shot a video just like this months ago. But does that mean you shouldn't be learning any prompt frameworks? Well, no. It depends on what you're using AI for.
If you're using it in an ad hoc, casual way and you just need to get your result and get out, then absolutely add "Ask clarifying questions" or anything like that in order to get a better output.
However, if you are building a prompt that's going to be reused again and again, we don't want to add something like "Ask clarifying questions" at the end. This is going to be the case if you are building an application or a custom GPT or a prompt library that your colleague is going to share. In these cases, we want a nice, clean, single prompt that's going to do the work we ask it to. We don't actually want it to ask clarifying questions; we just want it to get it done.
So, the answer is: it depends. If you just want to get an answer and it's a one-off thing, absolutely add "Ask clarifying questions." If, however, it's a prompt that's going to be reused again and again for making blog articles or social media posts, then no, you shouldn't add this because it's going to get in the way of the workflow.
So, nobody's right or wrong here. It's just different use cases. It depends on how you're using the AI.