Prompt Design
HCI Today summarized the key points
- •This article argues that prompting should be viewed not as engineering, but as ‘prompt design (prompt design).’
- •The author describes prompting as clear communication with humans who have time constraints, explaining that it is adjusted to match dynamic inputs—much like web design.
- •The author also emphasizes that you should verify the actual prompt and its rendering results, as if you were looking at a real screen, and that componentization and declarative authoring are beneficial for maintainability.
- •From this perspective, the author introduces Priompt, a JSX-based prompt design tool, and explains how it makes iterative work easier through real-data previews and quick edits.
- •However, the author warns that as models and APIs evolve quickly, the importance of fine-grained control and long context windows may decrease—meaning the value of prompt design itself could change as well.
This summary was generated by an AI editor based on HCI expert perspectives.
Why Read This from an HCI Perspective
This article reframes prompting not as simple sentence writing, but as a design practice for handling input variables. For HCI/UX practitioners and researchers, it helps them view LLM interactions as a problem similar to screen design, and encourages thinking about how established interface principles—such as readability, composability, and responsiveness—can be translated to AI interfaces. In particular, the perspective that treats prompts as a ‘renderable artifact’ is especially useful in practice.
CIT's Commentary
From a CIT perspective, the core contribution of this article is that it shifts prompting from language use to interface design. The analogy to web design may feel somewhat exaggerated, but the suggestion to actually render and review ‘invisible internal instructions’ is highly important in HCI. Concepts such as JSX-based compositional authoring, real-data previews, and partial re-rendering turn prompts from something shaped by an individual developer’s intuition into a repeatable design workflow. However, because model performance and API constraints change rapidly, an additional framework is needed to distinguish design principles from runtime constraints.
Questions to Consider While Reading
- Q.If we treat prompts as ‘renderable interfaces’ like web pages, what interaction-quality aspects should HCI evaluation metrics include beyond accuracy?
- Q.How much does JSX-based prompt design actually help with collaboration and maintenance, and can we conduct empirical studies comparing it with existing string-template approaches?
- Q.In an environment where models and APIs change quickly, what stable design principles does ‘prompt design’ have, and when should abstraction move into a framework or compiler layer?
This commentary was generated by an AI editor based on HCI expert perspectives.
Please refer to the original for accurate details.
Subscribe to Newsletter
Get the weekly HCI highlights delivered to your inbox every Friday.