Apple researchers have conducted a study to explore what everyday users truly expect from AI agents and how they prefer to interact with them. Titled “Mapping the Design Space of User Experience for Computer Use Agents,” the paper — authored by a team of four Apple researchers — notes that while the industry has poured significant resources into building and assessing AI agents, key elements of the user experience remain under-explored: specifically, users’ preferred ways of interacting with these agents and the ideal design of their interfaces.
To explore that, they divided the study into two phases: first, they identified the main UX patterns and design considerations that AI labs have been building into existing AI agents. Then, they tested and refined those ideas through hands-on user studies with an interesting method called Wizard of Oz.
By observing how those design patterns hold up in real-world user interactions, they were able to identify which current AI agent designs align with user expectations, and which fall short…
Once all was said and done, the researchers found that users want visibility into what AI agents are doing, but not to micromanage every step, otherwise they could just perform the tasks themselves.
They also concluded that users want different agent behaviors depending on whether they’re exploring options, or executing a familiar task. Likewise, user expectations change based on whether they’re familiar with the interface. The more unfamiliar they were, the more they wanted transparency, intermediate steps, explanations, and confirmation pauses (even in low-risk scenarios).
They also found that people want more control when actions carry real consequences (such as making purchases, changing account or payment details, or contacting other people on their behalf), and also found that trust breaks down quickly when agents make silent assumptions or errors.
MacDailyNews Note: Read more in Apple’s “Mapping the Design Space of User Experience for Computer Use Agents” <a href=”https://machinelearning.apple.com/research/mapping>here.
Please help support MacDailyNews — and enjoy subscriber-only articles, comments, chat, and more — by subscribing to our Substack: macdailynews.substack.com. Thank you!
Support MacDailyNews at no extra cost to you by using this link to shop at Amazon.
