AI Empowers Designers as Coders, Redefining Product Development

Key Quotes

"I was just like making websites since I was 11. I just kept making bigger websites. The first one was um for this anime that I really liked. I just made it for myself and then I started making like community websites like little forums and then I made one when I was 17 for like apple fanboys in China that got like kind of popular and I just kept doing it."

Ryo Lu explains his early, self-driven engagement with web development, highlighting a consistent pattern of building and expanding projects from a young age. This demonstrates a foundational approach to learning and creation through direct action rather than formal instruction.

"I would say I kind of self taught most of my software design building parts so I studied CS and bio in college but most of the CS courses were like so ancient they did tell me like more systematically how to program but they weren't that helpful like how I learned is really by just making stuff building things without knowing what the fuck I'm doing."

Lu describes his learning process as primarily experiential, emphasizing that practical application and building were more effective for him than traditional academic computer science courses. This illustrates a preference for learning by doing, even when lacking a complete understanding of underlying concepts.

"My personal KPI at Cursor this year is to turn all the designers into coders and then I don't want them to be say we're forcing you to start learning how to code or like how does the code editor work or how does Git work all these little details but rather now it's time to just start building like you actually don't have to care about all the details anymore just let the agents fill the gap for you but now you can actually start coding without knowing how to code."

Lu states his ambitious goal for the year: empowering designers to code by leveraging AI agents to abstract away complex technical details. This highlights a vision where AI tools democratize coding, allowing individuals to focus on building and creating rather than mastering intricate low-level concepts.

"The problem with that is like as you start working on more problems and then you ask you make more of these specific features it's really hard to kind of put them back together and then what you ended up usually is more buttons button button button button concept concept concept more levels of nav and hierarchy then a thing that you were designing for this small group of people that solved their problem becomes something really massive that's hard to understand and that doesn't really work versus you design in the more like systems first way."

Lu contrasts two design approaches: a traditional, user-problem-focused method that can lead to feature bloat, and a "systems first" approach. He advocates for decomposing problems into core primitives and keeping those simple, allowing complexity to emerge from their configuration.

"The first thing I did was let's just unify everything the things that should be similar were like gobbled together actually you know one thing so we merged the chat the composer the agent into one thing and then it's just agents and then agents can have different modes or like how how I think about it is they're all agents same agent but with different settings applied to them."

Lu details a significant product change at Cursor where he unified disparate AI interaction features (chat, composer, agent) into a single, cohesive "agent" experience. This demonstrates a focus on simplifying user interfaces by consolidating related functionalities under a consistent paradigm.

"The new way is you just ask the agent and you get this lump of thing it might not be great it might not be perfect but it is the thing and you sculpt it you mold it you use just say ah this part I want to make it like that instead I want to kill this part I want these things to be merged together and as you kind of do do more revs the thing gets closer to what you wanted and it is the whole thing it is the full thing it is not an artifact it is not like pixels stuck in a canvas."

Lu likens the new AI-assisted development process to sculpting, where users start with an imperfect but functional output from an agent and then iteratively refine it. This metaphor emphasizes a shift from detailed, pixel-level design to a more fluid, iterative shaping of a complete product.