Hamel Husain explains why AI can fix code but can't judge what makes a product feel right. AI doesn't understand user expectations or what your team actually wants. Human judgment is essential to catch when something seems off and to know what you're missing.
I think AI is really good at fixing bugs, deterministic errors in your product, like the code's not working or it's doing the wrong thing or it's failing a test. But AI cannot read your mind. It doesn't know what you feel like good is. So if a customer is interacting with your product and the product is not doing the right thing, it may look like it's helpful on the surface to an AI. But if you put your product hat on, you're like, you know what, we could have done better here. We should be able to help the customer in a better way or help the user in a better way than this. Or, you know what, 'What? This interaction doesn't make any sense. We don't have the best tools here. We need to fix the tools we have. We need to fix our retrieval because we're not really bringing in the right sources here.' And so the AI doesn't know what it doesn't know. It doesn't have the ability to read your mind and sort of elicit what good looks like.
