For decades software products created structure and flow through interfaces to direct users within a pre-determined paths. The job of the interface was to give people orientation in terms of where they are and what they can do at the point.

Criteria for a “good” interface was whether the user’s expectations before clicking a button were met after they actually clicked it. It was hard because people’s behaviour is often unpredictable, there can be a huge difference in mental models, pre-existing knowledge and comprehension between people looking at the same interface. As creators we had no control on that side of interaction, so we tried to craft the interface to be as robust as we could to enable as many people as possible to achieve their goal.

But with LLMs that equation have changed.

Now we have non-deterministic (and sometimes surprising) behaviour on the side of the system as well.

From design point of view it poses a challenge - what exactly are we designing? How “open” should a product be to accommodate variety of users and use cases, yet how “closed” should it be to still be focused on reaching user’s goal.

When ChatGPT ends every response with a question, this “open” approach leads to a conversation that may not have an end, which is an unlikely goal. On the opposite end of the scale, a very “closed” approach might be just pulling in a structured response from an LLM (classification task for example).

The real power might be in finding a balance – provide enough structure but allow variation and interaction within it.