Prompt design

Summary

The post argues that “prompt design” better describes prompt construction than “prompt engineering,” comparing it with web design. It frames prompts as clear communication with dynamic inputs that must adapt to changing content and context-window limits, then identifies shared practices such as inspecting rendered output, using composable declarative components, and pursuing precise formatting. For LLM agents, the analogy extends to interactive websites whose prompts re-render after function calls, although text-only output and caching constraints differ. This perspective motivates Priompt, a React-like, JSX-based library used internally at Cursor, with a preview site that renders prompts using real request data and serialized props; the author considers JSX more ergonomic than string templates while noting that model capabilities and platform abstractions may weaken the analogy over time.

Takeaways

1. 1

   Prompt design shares web design practices including inspecting rendered output, composing reusable components, favoring declarative structure, and adapting content to dynamic constraints.

2. 2

   For LLM agents, prompts can be treated like interactive websites: function calls act like button clicks, and the prompt re-renders in response.

3. 3

   Priompt uses JSX instead of string templates and provides a real-data preview workflow; the author says this makes prompt iteration easier, while acknowledging that model and API changes may limit the analogy.