Back/Design/Cursor
IntermediateDesignCursor

How to Iteratively Refine an AI-Generated UI Using Design Principles in Cursor

Transform an ugly, AI-generated UI into a polished, professional design by providing specific feedback to Cursor. This workflow teaches you how to guide the AI using negative feedback, aesthetic direction, real-world examples, and established design theory.

From How I AI

How I AI: A Designer's Guide to Cursor with Elizabeth Lin – From Y2K Aesthetics to Interactive Pianos

with Claire Vo

How to Iteratively Refine an AI-Generated UI Using Design Principles in Cursor

Tools Used

Cursor

AI-first code editor

Step-by-Step Guide

1

Provide Clear, Specific Feedback and References

Start the refinement process by giving the AI multi-faceted feedback. Tell it what to remove (negative feedback), give it an aesthetic direction, and provide positive examples of well-designed products in the same category.

Prompt:
let's work on the finance dashboard... remove all the drop shadows. And then I'm gonna say, make the components look more modern. And then I'm also gonna ask it to... make it look like Robinhood Cash app or Stripe, et cetera.
2

Iterate with Established Design Principles

Leverage the LLM's vast training data by referencing established design theory or well-known experts. This is a smart shortcut to guide the AI toward more sophisticated and legible design choices without spelling out every detail.

Prompt:
I kind of want it to simplify the colors a little bit on the page... and then I also want it to maybe be inspired by Edward Tuft's principles
3

Use a Psychological Hack for Layout

To fix layout and spacing issues, use a prompt that appeals to a known standard of quality. Referencing a company with a strong design philosophy, like Apple, taps into the AI's knowledge of grid systems and clean organization.

Prompt:
can you improve the layout to make it look like something a top designer Apple would approve

Become a 10x PM.
For just $5 / month.

We've made ChatPRD affordable so everyone from engineers to founders to Chief Product Officers can benefit from an AI PM.