Lenny Rachitsky outlines two design patterns for conversational agents: clarifying follow-up questions that reduce typing, and "writing blocks" that embed generated content as editable components in the chat. Both rethink how interfaces adapt to what users actually need.
Chapters
What's been really fun design space for us is there's 2 things we think about. One is like, how can we help you express your intent better? We recently shipped some features where if you ask sort of an open-ended question, it can follow up with some follow-up questions versus having to type everything out. Then once you actually ask it to do something, there's— the chat transcript doesn't need to be purely text, right? So a good example is what we call writing blocks. You ask it to write you a letter or an email. And it now contains that, um, that email in sort of a block that you can directly manipulate. And I think that's where the UIs really continue to evolve is if you come at this and you're a designer, maybe ChatGPT should actually really look differently or have different affordances. So like understanding the context and giving you different affordances based on that is something that, you know, we're thinking a lot about.