ChatGPT works best when apps are built around four specific modes: exploring, creating, deciding, and executing. A well-designed app knows which mode you're in and shapes itself to support it. The framework is meant to evolve as people use it.
I've been trying to create a taxonomy that we can and we will update, but what I've seen so far is that there are different modes of work and the ChatGPT app, if it's well constructed, it will be very opinionated about what mode of work the user is in at the moment. So the main ones that we are seeing today are the user is exploring, the user is creating, the user is deciding or the user is executing. But just so we're clear, these are the modes of work ChatGPT apps are designed around.
