Functional Flexibility in Generative AI Interfaces: Text Editing with LLMs through Conversations, Toolbars, and Prompts

TL;DR

This paper investigates how different user interfaces influence the way users access and utilize the flexible functions of large language models, combining surveys, user studies, and UI design insights.

Contribution

It introduces the concept of functional flexibility as a theoretical framework and compares conversational, toolbar, and prompt-based UIs for interacting with LLMs.

Findings

Users prefer short command prompts for AI interaction.

Toolbar shortcuts enable dynamic switching between AI functions.

Different UIs shape user access to AI capabilities.

Abstract

Prompting-based user interfaces (UIs) shift the task of defining and accessing relevant functions from developers to users. However, how UIs shape this flexibility has not yet been investigated explicitly. We explored interaction with Large Language Models (LLMs) over four years, before and after the rise of general-purpose LLMs: (1) Our survey (N=121) elicited how users envision to delegate writing tasks to AI. This informed a conversational UI design. (2) A user study (N=10) revealed that people regressed to using short command-like prompts. (3) When providing these directly as shortcuts in a toolbar UI, in addition to prompting, users in our second study (N=12) dynamically switched between specified and flexible AI functions. We discuss functional flexibility as a new theoretical construct and thinking tool. Our work highlights the value of moving beyond conversational UIs, by considering how different UIs shape users' access to the functional space of generative AI models.