Summary
Designing user interfaces (UIs) by hand is complex and requires many HCI (human-computer interaction) rules. This paper describes how large language models can create UIs from simple user descriptions, making the process faster and more flexible. Instead of just generating interfaces, the authors suggest turning the conversation between user and AI into a shared workspace called a Space to Think, where design rules are encoded as machine-readable skills that guide the interface creation. This approach lets the HCI community update and control these rules directly, so the resulting interfaces are better in accessibility, learnability, and consistency. The paper proposes a future where UI design knowledge is executable by machines, not just checked at the end.
What this means in practice
- •For ui designers: Use a shared AI-assisted workspace that applies formal HCI rules during interface creation to improve design quality and accessibility on the fly.
- •For software engineers: Incorporate machine-readable HCI skills as modular, editable code components to automate UI generation aligned with best design practices.
A position paper. It proposes an approach and reports no results.
Abstract
Human-computer interaction (HCI) is in the middle of a transition: large language models can now generate functional user interfaces (UIs) on demand from natural-language task descriptions. A user explains what they are trying to accomplish, and the system materializes a working interface to support it. This capability already exists in systems such as Claude and ChatGPT and continues to grow in fidelity as the underlying models improve. The next step along this trajectory is to move from interfaces that are merely generated to interfaces that are generated well. We propose a framework in which the dialogue between user and artificial intelligence (AI) becomes a Space to Think: a shared, structured cognitive workspace in which task decomposition produces an on-demand user interface as an extension of the user's thinking rather than as a separate artifact. Within this paradigm, classical HCI design knowledge (Nielsen's heuristics, Norman's affordance prescriptions, Web Content Accessibility Guidelines (WCAG) success criteria, cognitive-load constraints, and mixed-initiative principles) is encoded as skills: machine-readable skill.md files that the generating agent loads at runtime as software engineering tools. Skills turn HCI design knowledge into declarative, inspectable, version-controlled, and editable artifacts owned by the HCI community itself so that accessibility, learnability, and consistency become properties of a generative process rather than properties of a finished product. We outline a research agenda depicting a future where the HCI field transitions from today's design and knowledge heuristic checklist towards a future where the craft becomes machine-readable, executable, and open.