How to use Cursor for interactive prototypes, sound design, and data visualization

Episode Overview

• Designer Elizabeth Lin demonstrates her unconventional use of Cursor, an AI-powered code editor, as a creative partner for design exploration and rapid prototyping.
• The episode explores the concept of "teaching an LLM good taste" by feeding it unexpected sources of inspiration, like K-pop videos, alongside established design references to generate unique aesthetics.
• Elizabeth showcases a workflow of building complex, interactive prototypes—such as a functional digital piano—using simple, conversational text prompts.
• Key strategies discussed include automating tedious setup with custom "Cursor Rules" and using an iterative prompting style to refine designs conversationally.

Key Concepts

• AI as a Creative Partner: Using AI not just for execution but as a collaborator to brainstorm, explore diverse visual styles, and discover new design directions.
• Teaching AI "Taste": A method of guiding the AI to produce higher-quality, more unique aesthetics by providing it with a mix of unconventional inspiration (e.g., K-pop music videos) and specific, well-designed references (e.g., Stripe, Robinhood, Edward Tufte).
• AI-Powered Rapid Prototyping: Leveraging AI to dramatically accelerate the creation of high-fidelity, interactive prototypes with complex features like sound and data visualization, moving quickly from static mockups to functional applications.
• Workflow Automation: Streamlining the creative process by creating custom "Cursor Rules" that automate repetitive setup tasks, such as creating file and directory structures for new projects.
• Iterative and Conversational Prompting: A design refinement technique that involves using short, targeted prompts to make small changes one at a time, treating the interaction with the AI like a back-and-forth conversation.

Quotes

• At 0:05 - "How do you teach an LLM to have good taste?" - Host Claire Vo asks the central question that frames Elizabeth's approach to using AI for design.
• At 0:17 - "I would try to send like really random things like the K-pop music video or like different pieces of art that it might not normally be inspired by and kind of see what it takes from it." - Elizabeth explains her method for expanding the AI's creative palette beyond its standard training data.
• At 15:17 - "I know a lot of people have really, really long rules, but mine is basically like, if I ask you to create a new prototype, copy this folder and then add it to my homepage." - She highlights the power of creating simple, custom rules to automate repetitive and tedious coding tasks.
• At 16:43 - "I actually think it's important to kind of have a baseline understanding of what's going on... but I don't try to understand all the little details because I personally like this part better." - Elizabeth shares her philosophy on balancing the use of AI as a tool with the need for foundational engineering knowledge.
• At 23:03 - "I personally like to use really short prompts. I know there's like a whole movement out there for people who really like giving using long prompts, but I feel like I kind of like it to be a little bit more conversational." - She explains her preference for an iterative, conversational prompting style over creating long, complex initial prompts.

Takeaways

• Treat AI as a creative partner for rapid visual exploration by generating numerous distinct styles from a single starting point.
• Guide the AI's aesthetic by providing a mix of unconventional inspiration and established design references to push beyond generic outputs.
• Refine designs iteratively with short, conversational prompts, as AI often responds better to single, focused changes than to long lists of instructions.
• Automate tedious setup tasks using custom rules or scripts to spend less time on manual configuration and more time on creative work.