Pod Insights Y Combinator Podcast The End of the Designer–Engineer Divide About this episode Head of Design Ryo Lu helped transform Cursor from a feature-layer on top of VS Code into one of the world's leading AI code editors. He joins YC's Aaron Epstein on Design Review to talk about the path that brought him to Cursor, how rapid prototyping reshaped the core product and how he's breaking down the barriers that once separated designers and coders.
Transcript 0:00 Speaker 00 My personal KPI at Cursor this year is to turn all the designers into coders. The roles will start blurring, the designers will start coding, the engineers will start designing, and then our shared language is code. You start not by getting everything perfect, you actually start by building. If you get something bad or ugly, it's actually your job to make it pretty, the way you want it, and that's the part that the AIs can't really do right now. As we break the boundaries between these tools, as everyone can start talking with the code, magical things can happen.
0:40 Speaker 01 Today, I am excited to welcome Rio Liu. He's the head of design at Cursor, the leading AI coding tool used by more than a million people worldwide. Before that, he was a founding designer at Notion and a product designer at Stripe and Asana. Today, we'll talk about his background and design process, and then we'll hear his thoughts on the future of design in a world of AI. Rio, welcome to Design Review.
1:03 Speaker 00 Thank you.
1:04 Speaker 01 Maybe to start off, why don't you tell us a little bit about your background and how you got into design in the first place?
1:09 Speaker 00 I was just making websites since I was 11. I just kept making bigger websites. The first one was for this anime that I really liked. I just made it for myself. And then I started making like community websites, like low forms. And then I made one when I was 17 for like Apple fanboys in China. That got kind of popular, and I just kept doing it. When I started, I did not know like what's the difference between like design or engineering or product. It was just the whole thing. Then I became more like a professional designer.
1:50 Speaker 00 I made a couple startups myself, and then I got an offer from Asana. So I came, and then I became a designer.
1:59 Speaker 01 Were you technical all those years, like when you first started to design?
2:04 Speaker 00 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 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. Like, I did not know the concept, the words. I just, I want to do this. I'll just figure out how to do it. Use whatever tool that's there. And then you learn by doing that.
2:40 Speaker 01 Yeah.
2:40 Speaker 00 But now it's like with the agent, with Cursor, you make this process so quick. Like, instead of, you felt, ah, like coding is a little scary. It wasn't like, you know, it's not something that we as designers is supposed to do. Or like, you just feel like, in order for me to start something new, or like a prototype, I need to learn all of these like, low-level concepts, there are kind of dependencies. It's kind of scary.
3:07 Speaker 01 And that'll take forever, right?
3:09 Speaker 00 It will take like,
3:09 Speaker 01 That's the fear.
3:10 Speaker 00 It will take like months. Almost like you need to like, really focus on this and then, go to a book camp and whatever. Versus now, you just ask the agent. And then, if you don't know, like exactly what you're doing, agent's able to like fill you with the gaps. It can do research for you. It can search the web on, ah, what is the best way to do X, Y, Z? And it will help you do that. And then you learn. And you learn by doing. And you get the result really quickly. And you can iterate really quickly.
3:42 Speaker 01 Yeah.
3:43 Speaker 00 So that's the difference.
3:44 Speaker 01 It sounds like you went through this journey of being frustrated that you were kind of put in the design box of like, this is the little piece that you should focus on. And now you have all these tools and you're able to actually build the thing that you have vision, that you've designed. You can make it come to life and be real. And I know you kind of have a personal mission this year. Tell us more about that.
4:04 Speaker 00 Yeah, so, 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? 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. But you know, like as designers, as people who worked on software so long, we all have intuition of how things should work. Like, we all know these things, like,
4:45 Speaker 00 I don't know, say like version control for Git, files and folders, all these things. We know them, we just maybe don't know exactly like what is the right way to do it at this time, or all the little details. But now it's like,
5:00 Speaker 00 you don't have to think about it anymore.
5:01 Speaker 01 So for anybody watching, maybe they're a designer, they feel stuck in that box, they haven't been able to build the thing.
5:07 Speaker 00 Yeah.
5:08 Speaker 01 Break out. What's like the first step? Like, what are the things that they should do?
5:12 Speaker 00 Yeah.
5:12 Speaker 01 To put them on that path to your KPIs.
5:14 Speaker 00 Yeah.
5:15 Speaker 01 Of turning them into developers too.
5:17 Speaker 00 I think it's actually fine, or it's good to play with the more like vibe coding tools.
5:23 Speaker 01 Mm-hmm.
5:23 Speaker 00 So like Figma Make or V0. Like, those can help you get started in a more constrained fashion.
5:32 Speaker 01 Mm-hmm.
5:32 Speaker 00 And they kind of work with your existing workflows better. But you will run into a point where like, those more constrained version of coding doesn't let you do everything. And then that's when you go to Cursor.
5:47 Speaker 01 Mm-hmm.
5:47 Speaker 00 And then you realize that, oh, the stuff I do in Cursor and the stuff I do in Figma Make or V0 are actually the same, or like they feel very similar, it's very simple. But then, in Cursor, you can actually do everything, like, everything. Anything, because it's just, like, we're kind of unopinionated. It is just like a suite of tools and agents with an editor that can write any code, anything. iOS, web, you can even write a novel, like a book with it.
6:19 Speaker 01 Mm-hmm. How long have you been at Cursor? And tell us more about your role and what you do in the day-to-day there.
6:24 Speaker 00 I've been at Cursor for almost 10 months.
6:28 Speaker 00 But it feels like five years, like in AI time. So I'm the head of design. I was like the first product slash design person at Cursor. When I joined, we had like twenty people. Now we have two hundred fifty people. Our team is still really small. We have like four people, including myself. Three of us work primarily on the product. And then we have Justin, who works on the brand. We're trying to expand the team a little bit. Everyone on the team codes. And I think how design works at Cursor, the difference is that one, a lot of our engineers, they also kind of design Cursor. Because Cursor primarily, like at its core,
7:10 Speaker 00 it is still like a tool designed for professional developers to do stuff with AI and kind of augment themselves.
7:17 Speaker 01 You have a lot of your own users at the company.
7:19 Speaker 00 Yeah, like every single person at the company is a user. And then every single person has cool ideas. And as you know, like engineers, they also are very different. Each of them, some of them prefer like doing everything in the keyboard. Some of them are also like, you know, button clickers. People have different preferences of the suite of tools they need. They might want different buttons to appear. The core of the system needs to be really simple, but it kind of adapts to different needs and different people's like preferences. Figure out like, say, I wake up today and then boom, there's like three new buttons. Why do we need them to be there? What are the things that we can unify and clean up? So that, you know, things feel simple, but then you can still do all these things.
8:04 Speaker 00 How do different projects and ideas fit together? How do we decompose them and then merge them back? How do we keep the thing simple? But still, like you start simple, but you can gradually get to a pretty sophisticated place. You don't lose functionality, but things get more organized.
8:23 Speaker 01 Yeah, it's like layers of an onion. You want it to seem simple at first glance, but if you want power tools, you're able to uncover those.
8:29 Speaker 00 Exactly.
8:30 Speaker 01 Talk about, you've been there ten months now. You've shipped a lot of really major things and worked on and designed a lot of really important changes. Can you talk about some of those?
8:38 Speaker 00 Yeah, two biggest thing that I've done. One is the first day I joined. The problem was Cursor, maybe earlier this year.
8:49 Speaker 00 It was more like a couple of features slapped on top of VS Code. There is the tab, which is the inline completion thing. Still like the world's best, the most magical tab experience. We had the chat, which was you're just talking to the model with maybe some code-based information, maybe not. And then it's just give you like a textual output. It doesn't do anything. That was like the primary interface of Cursor. And it's, it was like a little sidebar on the side that you have to toggle it open yourself. And then there's the Composer, which is like the chat, but it can offer to edit some files. And that's the only thing it did.
9:33 Speaker 00 It's like if the chat outputs some code, you can apply the code changes. To me, that and the chat is basically the same thing. And then like November last year, Cursor added the agent. That was actually what hooked me to Cursor. Like I tried Cursor three times before. I churned every time. I had to search on the web how to turn on the agent. I couldn't find it myself. It was like a little checkbox in the Composer tab that says "normal". It's like normal versus agent. Nobody knows what normal means. Right. And there was like other things. So like there was a bug finder, there was some random crap around.
10:15 Speaker 00 And then the first thing I did was let's just unify everything. The things that should be similar or 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 agent. And then agents can have different modes or like how I think about it is they're all agents, same agent, but with different settings applied to them. So like Ask mode is just the agent without editing capabilities. Or maybe like, you know, we're adding a thing called Plan mode. That is just the agent before it wants to, you know, run the plan, build the stuff, you have to hit a button. We just block you from doing that.
11:00 Speaker 00 But they're all talking to the same thing. And to the user, we just flip the default. So you always get the agent when you open up Cursor. That's the only thing I did. And then the agent took off like that. Like we kind of see the data from like primarily tab users, primarily agent users.
11:22 Speaker 00 And then the second thing I did, which is pretty recent, is like after we flipped the default to agents, we just noticed like the world kind of changed. And also like there were, you know, newer agent tools that are almost pure agents. And everyone kind of moved from even earlier this year, primarily still writing code, but then it's kind of assisting you to now the agent writes most code. And then you're mostly interacting with the agent. So with Cursor 2.0, all I did was Cursor used to say show the default UI hierarchy from like a file-centric view.
12:05 Speaker 00 So you have a list of files, you have the editors that show the file themselves, and then the agent is kind of like on the side. All I did was I flipped the order. And then in this new agent layout, when you start, it's just one agent. When it's empty, it's just a prompt box, you can do whatever. As you do more, maybe you run multiple agents. You can see like multiple agents, their states, you can swap between them. You can see, ah, this one needs my review, this one's blocked, this one's still ongoing. Maybe you can run for a long time. And then as you're doing that, you actually don't have to look at the code if you don't want to. But if you do, you hit this review button and then we list out like every single change,
12:49 Speaker 00 you can just scroll through and then review really easily. Versus say before, everything's like in this really file-centric view. When you open up Cursor, when you have nothing, you still have like a blank editor, a blank file tree. It's really hard for like a person who wasn't used to coding to do anything in that state. Versus now, we flipped it. When you start on Cursor in this new world, you can just type in your prompt, boom, see what happens.
13:21 Speaker 01 You've talked a lot about, you know, simplifying UIs, simplifying interactions. Is there a lesson in there for design founders as they're building their projects?
13:28 Speaker 00 Yeah, I think of like design, you can do it in two ways. One way is more like Like I'll call it the traditional human-centered design way. Meaning like you start from a set of users, their problems. You come up with like really specific solutions for their problems. And then you can design like a low world for them that way. The problem with that is like as you start working on more problems. And then as 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, button, concept, concept, concept. More levels of NAV and hierarchy.
14:10 Speaker 00 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. That doesn't really work, that doesn't conceptualize as well. Versus you design in a more like systems first way. Meaning you kind of decompose the problems into what are the parts, the primitives, the low-level concepts. When they work together, they solve their problems. And you try to keep that core concepts, the core set of concepts and primitives as simple as possible. But they all are somewhat flexible.
14:52 Speaker 00 Say for, for example, when we were working on Notion. Like the core concepts are just blocks, pages, databases, and the people, the teams. And then Notion is just like different configurations of these things. And then when they get put together, they do amazing things. They kind of emerge complexity. So it's all about figuring out for the world you're building. What are the core elements that actually like they will always stay, they won't really change. But they will evolve, they will, you know, make new connections. Each of them will get better. And then how do you map your user problems,
15:35 Speaker 00 the things you want to do, your roadmap, your ideas to this thing under? And then ideally, you don't add things all the time. You're actually like decomposing things, merging them back, figuring out what is the better configuration of the stuff that you have now. If you tweak that a little bit, boom, you solve the problem.
15:53 Speaker 01 Yeah, I think one of my takeaways is as product scale, and certainly you're probably Cursor is one of the fastest growing products ever in history.
16:02 Speaker 00 Yeah.
16:02 Speaker 01 The tendency is to keep adding more features. And the product expands in complexity as the user base scales and all the use cases expand. And if you're not intentional about going back through and rethinking things and pairing it back down to the simpler state, it's very easy for these products to get out of control. And then it becomes something that is for nobody.
16:24 Speaker 00 Yes.
16:25 Speaker 01 Because it doesn't have an opinion.
16:26 Speaker 00 Yes.
16:26 Speaker 01 And it's impossible to work with these primitives like you described. And it sounds like that is an exercise that you are regularly going through.
16:33 Speaker 00 Oh, yeah. Maybe like on paper or like to the users, like the concepts don't really change. But underneath, it's like getting rebuilt every couple of months. And then things that were maybe like disjointed, they get unified as we go. It's like a healthy tension. It's like people want to add things, people want to experiment. You let them do, you let them be, they build some stuff. Maybe they actually just slap a button here. But then, like as designers, we can help people rethink how to fit things better. Like what are the common parts that are shared? That can, you know, if you fix this common part, it not only makes this feature better, but makes everything better.
17:17 Speaker 01 Awesome. I would love for you to walk us through your design process at Cursor and how you've built some of these things. So one thing I would love to see here is if you can time travel us back to Cursor, maybe before you joined or around the time that you joined, talk about your feedback, looking at the site, especially now. And then pull up the most recent one and talk about some of the changes along the way.
17:39 Speaker 00 Let's go. So I just pulled up Cursor when it started in 2023. Wow. What is this? What does it do?
17:49 Speaker 01 It's very dark also.
17:51 Speaker 00 Yeah, very dark, very like, not sure what these gradients are.
17:55 Speaker 01 Yeah.
17:56 Speaker 00 Not sure what this is either.
17:58 Speaker 01 Mm-hmm.
17:59 Speaker 00 It's like...
18:00 Speaker 01 Yeah, I see some blurry code.
18:01 Speaker 00 Very, very not sure.
18:02 Speaker 01 A text box.
18:03 Speaker 00 Looks like the fonts are not loaded, but it might be something not that great. Chat with your project, ask about codebase.
18:12 Speaker 01 Alright, now we're getting into a little bit more specific.
18:14 Speaker 00 This thing is kinda crazy.
18:15 Speaker 01 The line follows you.
18:16 Speaker 00 Yeah, yeah, yeah. So extra. Like, what are you trying to do? Like, you want people to focus on this line?
18:23 Speaker 01 Right.
18:24 Speaker 00 Like, what the hell?
18:24 Speaker 01 Yeah, it's distracting, huh?
18:26 Speaker 00 Yeah.
18:27 Speaker 01 Or it makes you think you're living in the future right now. It's like Tron or something.
18:31 Speaker 00 But if you look at all these UI, like, I just don't know what I'm looking.
18:34 Speaker 01 Yeah, that's always the problem with showing specific screenshots, especially of code, is it's impossible for somebody to get the context of it.
18:41 Speaker 00 And a lot of the code examples and stuff is like so foreign. Like, as a reader, say like, maybe I'm doing like a B2B SaaS app, or I'm doing healthcare. And then I see some random agent interface service code. Like, I just don't, it doesn't talk to me.
18:55 Speaker 01 Right. It's not your code, right?
18:59 Speaker 00 Sure, sure, sure.
19:00 Speaker 01 Alright, we got a bunch of social proof here.
19:01 Speaker 00 Okay. Back in the days, Cursor, what is really good at is the tab, but there's no tab.
19:06 Speaker 01 Yeah.
19:07 Speaker 00 What the hell?
19:08 Speaker 01 Yeah. What's the biggest thing, like, you're going to make a change on this? What's like the number one thing that you wanna change and get right on the next version?
19:16 Speaker 00 Kill all the gradients.
19:17 Speaker 01 Why?
19:18 Speaker 00 It's just very distracting. You're like trying to create a scene, a world, for people to come in. And then when they come in, you're really like disoriented. Like, you don't know what, what is this, where?
19:32 Speaker 01 Yep. That second section is the thing that I would most change.
19:36 Speaker 00 This one?
19:37 Speaker 01 Yeah.
19:37 Speaker 00 Yeah. It doesn't show you anything.
19:39 Speaker 01 Yeah, I can't figure out what it's trying to convince me of, and it's prime real estate.
19:42 Speaker 00 Zero information about what the Cursor can do.
19:45 Speaker 01 Yeah.
19:46 Speaker 00 At the chat tab, the composer. When you toggle these things on, it actually defaults you to the chat tab. You have to click composer. You have to find this normal slash agent toggle.
19:58 Speaker 01 Right.
19:58 Speaker 00 You hit on agent, then you can do something.
20:01 Speaker 01 Right.
20:01 Speaker 00 Versus... This.
20:04 Speaker 01 Right.
20:04 Speaker 00 You can just do something.
20:06 Speaker 01 Yep. And it defaults to the agent. You don't have to go through and click all the things.
20:09 Speaker 00 Yeah, yeah, yeah.
20:10 Speaker 01 Yep.
20:11 Speaker 00 That's it.
20:11 Speaker 01 Okay, let's take a look at the latest version.
20:14 Speaker 00 Yes, we kind of clean up all the, it's like the foundation of the brand. Like fine tuned every single detail from the logo, the typeface. We have like a custom typeface called Kirtha Gothic.
20:29 Speaker 01 I noticed it's not dark mode also.
20:31 Speaker 00 Aha, but it's like, the idea is it should follow your, your system.
20:36 Speaker 01 Ah, okay.
20:37 Speaker 00 So that's the default.
20:39 Speaker 01 Yeah.
20:39 Speaker 00 But if you're dark, it's still dark.
20:41 Speaker 01 Yeah.
20:42 Speaker 00 But I don't want to kind of, you know, give people brightness in the day if they want.
20:47 Speaker 01 Right, right.
20:48 Speaker 00 Yeah, make Cursor feel a little less alienating. One of the ideas of like say behind these, what we call like wallpapers, is that they're, they're now like just great art created by humans. Um, like a lot of these pictures.
21:04 Speaker 01 The human connection, right?
21:05 Speaker 00 Yeah, like they're not AI generated. They're actually like from past artworks in the eighties, like in the eighteen hundreds and stuff. One thing that's cool with like our new site is that like all of these are interactive.
21:19 Speaker 01 Oh, that's cool.
21:20 Speaker 00 They are real.
21:21 Speaker 01 I thought it was a screenshot.
21:21 Speaker 00 They're actually real code. I made a lot of these. It's like you can actually.
21:26 Speaker 01 So you can just try it out live.
21:27 Speaker 00 Yeah, yeah, yeah. And then like a lot of these things actually work. So you can swap between different examples. So maybe like this is more for like ML training.
21:36 Speaker 01 Yeah.
21:36 Speaker 00 This sounds like you're, you're learning how Cursor works.
21:39 Speaker 01 Yeah.
21:39 Speaker 00 There's like a rule that's being edited.
21:41 Speaker 01 Yeah.
21:41 Speaker 00 We show like a bunch of different like industries.
21:45 Speaker 01 That's so important because you want to get people to the aha moment of using the product. And the best way to do that is not download it and install it and then set it up.
21:54 Speaker 00 Yeah.
21:54 Speaker 01 Figure out what project you're going to work on. It's just like, here it is, right here in the browser. You can start using it immediately.
22:00 Speaker 00 Yeah, and then you can actually type in it and then boom, you can download.
22:04 Speaker 01 Yeah.
22:04 Speaker 00 Each of the pages are also really simple. It's just like boom, boom, boom. And then you can dive into them if you want.
22:11 Speaker 01 Yeah, and it seems like you have one key point for each one that you're trying to make.
22:15 Speaker 00 Yes.
22:15 Speaker 01 Something that you are showing with a screenshot visually to illustrate as well.
22:18 Speaker 00 Yes, it's like kind of calling back to like the, the core concepts that I just talked about. It's like. The slides should also just show those.
22:28 Speaker 01 Yeah.
22:28 Speaker 00 Yeah.
22:29 Speaker 01 Yeah, so go back to the homepage for a second.
22:30 Speaker 00 Yes.
22:31 Speaker 01 Let's look at all of those.
22:32 Speaker 00 Mm hmm.
22:33 Speaker 01 And I'm curious which you picked and why.
22:35 Speaker 00 Yeah.
22:35 Speaker 01 Okay.
22:35 Speaker 00 Agents.
22:36 Speaker 01 Yep.
22:37 Speaker 00 The tab.
22:38 Speaker 01 Yep. Tab autocomplete.
22:40 Speaker 00 And this is like the ecosystem slash the cursor is everywhere.
22:44 Speaker 01 Right, it's connected with all the other tools that you use.
22:46 Speaker 00 Yep. Some testimonials.
22:49 Speaker 01 Mm hmm.
22:50 Speaker 00 These are more like ways for you to kind of go into different spots. There's one for enterprise, one for learning models.
22:58 Speaker 01 Mm hmm. I would love for you to walk us through your design process.
23:01 Speaker 00 Yes.
23:01 Speaker 01 At Cursor and how you've built some of these things.
23:03 Speaker 00 Uh huh. I'll first show you like something I do for work and then I'll show you something for fun. The first thing I showed is Baby Cursor.
23:13 Speaker 01 Mm hmm.
23:13 Speaker 00 And the idea is a lot of times for designers, when we explore ideas, we actually don't really care about like the technical implementation details of how things work. So if you want to do your prototype in a, in a production level code base that's really massive and complex, it actually takes more time. Then say, you just built a little environment for you to play with your ideas. You can kind of reconstruct parts of the UI and the interactions. It doesn't have to have all the details, but once you put them together, you can actually feel like, like you can feel it almost like, like alive.
23:52 Speaker 01 So Baby Cursor is like a scaled down, simplified version of Cursor.
23:57 Speaker 00 Yes.
23:57 Speaker 01 That is like it in many ways and it becomes your own personal playground for you to just add new features and explore different ways of doing things to try to get it right before you eventually wrap it back in.
24:09 Speaker 00 Yeah.
24:09 Speaker 01 Into a grown up Cursor.
24:11 Speaker 00 Yep, so I built this in, I think in afternoon, maybe like a couple hours. It has all the hotkeys, the primary like interactions that we have here. Um, there is actually like a integration with like AI models. So I can ask like, what is this? And then you can see the live output. A lot of the stuff here, like they feel like the real cursor, but it has like say little details that I want that is not even in the product. Like I want to make the keyboard navigation really well. Like you can actually select all the parts of the chat. There is like a little preview here where you can see live output of the code. We added the internal browser, so maybe that's like how this thing ended up.
24:56 Speaker 01 And that started in Baby Cursor?
24:58 Speaker 00 And one example that's kind of cool is I was trying to like explore some ideas of how we can run multiple agents at the same time. So I made this, like you can say translate to Korean and translate to Japanese. And then when you hit this, it will run the agent at the same time.
25:20 Speaker 01 Cool.
25:22 Speaker 00 You can see both live outputs, you can kind of pick and compare different changes. And like this kind of stuff for you to make Infigma is gonna be like insane.
25:34 Speaker 01 Yeah.
25:35 Speaker 00 Because a lot of the outputs are like from the AI. There's a lot of live states and you know, different things show up and not very hard.
25:44 Speaker 01 The problem is you would spend forever designing this as a mock-up with fake data.
25:48 Speaker 00 Exactly.
25:49 Speaker 01 And you'd have no way to like actually test what it feels like to use it. And then you'd have to wait forever for an engineer to free up.
25:56 Speaker 00 Exactly.
25:56 Speaker 01 And be able to prototype it for you so you could compare different ideas.
26:00 Speaker 00 Yeah.
26:00 Speaker 01 And you can just do that instantly.
26:02 Speaker 00 Exactly. Like it's so easy.
26:04 Speaker 01 Yeah.
26:05 Speaker 00 This is kind of like how Cursor used to look like, like pre one, pre 2.0. You know, we talked about like there's the files, there's some editors, there's the chat. That's kind of like on the side. And then let me show you like Cursor 2.0. So we kind of flipped the order of things, like you kind of focus on the agent, what they did. You can make a new one really easily. And we have like this internal browser where you can see the code output. You can keep like Cursor really clean, like if I'm just like doing stuff, say in my little prototype, um, real as.
26:45 Speaker 00 I just do this. It almost feels like a lovable. But the difference is, you get the whole thing. Like, you still get like all the files, the get tools, the search. You get the full like command palette. You get everything. But you can always like, you know, start with a simpler state. Focus on, you know, ideating or planning or making stuff.
27:11 Speaker 01 I love this. This is reOS. This is your own personal playground, right?
27:15 Speaker 00 Yes, yes, yes.
27:16 Speaker 01 Uh, yeah, just show us high level. Like, what have you built here?
27:19 Speaker 00 It's kind of meta. I don't know what I'm doing, but the idea is. I started this thing from just making one app in this, in this OS. Started from this soundboard app that makes sounds. And I just asked the agent, hmm, put it in a window. And then they made this like dragable window thing and then added the menu bar. And then I was like, hmm, why not just add more apps? And I kept at, kept at making new things. I made an iPod that actually works. Uh, I made a time traveling browser.
27:55 Speaker 00 Goes back in time, but also you can jump to the future. Go back into like ancient times. These are like generated by AI.
28:03 Speaker 01 If you go to 1000 B C.
28:04 Speaker 00 Let's go.
28:04 Speaker 01 What did the internet look like back then?
28:06 Speaker 00 Oh, wow. It's in Korean too. But you can actually change, you know, the generation. You can also set like a scene. I don't know. Maybe you're in the UK. And then let's try refresh.
28:19 Speaker 00 It's gonna fetch the latest apple.com contents. Pass it to, to like a L M and then it's gonna generate the page for. And as it does it, it makes like a elevator music. So how I would, um, start a new thing? So in 2.0, we have a new mode called plan mode. And then the idea is maybe you don't really know all the details of what you're doing. You kind of want to ideate with the agent. Come up with better details, then the agent can build the stuff exactly how you wanted it. So maybe we can ask the agent like. I want to make sharing new applets easier and more discoverable.
29:04 Speaker 00 Then we can try like, see what the agent comes up with.
29:09 Speaker 00 What it's gonna do is, it's gonna search through the whole codebase, figure out what's there, come up with a plan. It might also like, ask a few questions back, so that if there's something like ambiguous, oh, here it is, you can just like, talk to it. And then, at the end, it will come up with a plan. So, directions to share, let's see.
29:35 Speaker 00 Not obvious, you can share an app that's saved.
29:42 Speaker 00 Two, what would help better? Maybe, let's see.
29:47 Speaker 00 Make it auto open. And then, three, I don't know, let's just let it be. So, once you answer the questions, it's gonna make a plan for you. And the plan looks almost like a PRD that your PM writes. You can actually like, edit the thing if you want. Let's see what it wants to do. Add a share button to the viewer.
30:16 Speaker 00 Add a button for the fee cards.
30:23 Speaker 00 Okay. So if you're okay with the plan, all you need to do is to hit build. And then it's just gonna do it for you.
30:33 Speaker 00 And with our new composer model, like it's four times faster than Sonnet's. And it's like, twice as cheap. So, things will happen like, almost like, pretty quick before your eyes.
30:51 Speaker 00 Ah, cool.
30:54 Speaker 00 Let's see what's gonna happen.
30:58 Speaker 00 Adding more buns.
31:02 Speaker 00 Cards, let's see. So like a share button? Oh, fixing some bugs. Oh, okay, let's see what happened. Share button in the toolbar.
31:17 Speaker 00 Upload it, let's see if I get this. Ah, little share button.
31:22 Speaker 01 There we go.
31:23 Speaker 00 Let's see what happens when you click on it. Eh, it didn't work. Maybe like, let's ask it to hook up the share button with the share model.
31:39 Speaker 00 Then it's gonna fix it. Let's see if it worked. Oh, oh, oh, oh, oh. Nice, there you go. Beautiful.
31:50 Speaker 00 Cool.
31:50 Speaker 01 That's great, and the cool thing is you didn't even have to touch any code, right? You basically just spoke in English, you got a PRD, which designers are used to today.
31:58 Speaker 00 Yep.
31:59 Speaker 01 And you just kept telling it what to do to fix things.
32:03 Speaker 00 And if you want to look at code, it's here.
32:05 Speaker 01 It's there if you want it. That feels approachable for any designer to do, right? And start building something themselves.
32:12 Speaker 00 Yeah, so one thing that I think we're gonna fix, maybe like even in the next two weeks is like when you start Cursor, like you're faced with like three buttons, at least the version before, where it says like open project clone repo connect to SSH. Like you don't really know what the hell like those things mean.
32:32 Speaker 01 Yeah.
32:33 Speaker 00 And then our new like landing page is just like boom, you just start. And then the agent is gonna help you start a new project if it's not there.
32:42 Speaker 01 Yeah, that's great. So you obviously, you know, you design, your process is very different at Cursor, and I'm sure you see lots of people that are working with Cursor to design as well. Talk about how design process is changing overall in the age of AI, and certainly Cursor as a tool.
32:58 Speaker 00 Yeah, the roles will start blurring.
33:02 Speaker 00 The designers will start coding, the engineers will start designing. And then our shared language is code. It is not just picture frames, not pixel values, but code. You start not by getting everything perfect, every single bit of detail. You actually start by building. You start with a vague idea, you put it in the agent. It comes out maybe like sixty percent, seventy percent. You need to be comfortable with like a somewhat bad output and figure out a way to turn that into the thing you want. And as the models and agents get better, that process will just get quicker.
33:46 Speaker 00 Maybe like the first time it comes up is actually the thing that you wanted. But then, you know, what's next? How do I get to somewhere even better? The agent is able to do that too for you.
33:58 Speaker 01 You've described this as like sculpting, right? Is that a way that designers should think about this?
34:03 Speaker 00 Like the difference before was like, we started from, uh, let's do some wireframes and sketches. Then we paint each of the layers and boxes with like styles, when colors and type and you're like painting, stroke by stroke.
34:22 Speaker 00 But you're painting on a, on an artifact, on a canvas that's not real. Versus the new way that's 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, you 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 that is the whole thing, that is the full thing. It is not an artifact, it is not like pixels stuck in a canvas.
35:03 Speaker 01 And I think we saw that when you were, um, you were adding the shared sheet, right? It was like the button appeared, but then clicking it didn't do anything. So you got it like sixty, seventy percent of the way there. Then you're like, okay, now I need it to do this thing. So you told it what to do and then next time it works.
35:18 Speaker 00 Yeah, it's like if you get something bad or like ugly, it's actually your job to make it pretty, the way you want it. And that's the part that the AIs can't really do right now. Then we can actually focus on our craft. Like figuring out like how to push this thing even further, focusing on the details, making everything fit together.
35:38 Speaker 01 One thing that I find, um, there's some projects we've been doing internally and using a very similar process to what you're describing here. And I, I think one of the things that I find is we pay a lot more attention to like even the interactions and motion and all these things that are really hard to do when you're just in a frame somewhere. And when you get to experience it, now all of a sudden, all these other layers come alive that you get to experiment with and test and it feels like everything is just gonna level up so much more because of this.
36:08 Speaker 00 Yes, it's like, like it's not even just for designers. It also includes say like your PM's writing some Google Doc that's stuck. It never gets updated. It's always like destroying it from the real thing.
36:21 Speaker 01 Right.
36:21 Speaker 00 As we kind of fit these so different parts of making software together, as we break the boundaries between these tools, as everyone can start talking with the code, magical things can happen. Like people don't feel the barriers anymore. People can start understanding each other. People can help each other better.
36:42 Speaker 01 Yeah. And so in that world, what are the skills that designers should be focused on becoming great at?
36:48 Speaker 00 One, you need to really go deep into the details and the craft. Because that is the part that the AI will probably like take some time to catch up. And you need to be almost like a more system thinker, not just focusing on one slice of the problem. The more you understand that the other layers or the other concepts that maybe you don't know yet,
37:11 Speaker 00 the better you can, you know, piece things together better with the, with the agents. You might not know the best way to do like, I don't know, front end app, web app applications. But you know, as you learn more about the constraints in your production technical systems, you can also instruct the agent better so that it can reuse better patterns and tools. Then the thing you build is better versus you don't really know much. Then it might just give you something mediocre.
37:42 Speaker 01 It's like a new, more powerful tool to use and you need to learn how to use it effectively.
37:47 Speaker 00 It's almost like the more domain knowledge you have.
37:51 Speaker 00 Plus the agent, plus you know, knowledge of the codebase and everything that connects to it. The more things you can do, and it's not just for designers, it's for everyone.
38:01 Speaker 01 How do you think interfaces are gonna change in the future? There's a lot of talk of adaptive UIs and generative UIs. How do you think about that? Where do you think that's going?
38:09 Speaker 00 The interfaces will stay, but they get completely decomposed. And then maybe the AI composes it, or maybe the AI kind of figures out what's your preference and then applies it. We used to say, ah, when I want to make some dogs, I go to Google Dog, like an app, and then it's kind of fixed. Or like, I need to track some issues, I go to Jira. It's also kind of fixed. Like, they have their own views, their own data models, all the concepts. When the AI, or the agent, or cursor is really good at just kind of breaking apart all of these things, and then kind of summarize, synthesize everything back together.
38:51 Speaker 00 But the problem is, I don't think, say, just showing text or raw output is the most efficient way for people to, say, parse the information or do stuff with it. When it makes sense, I still want a to-do list, I still want a table, I still want to see the picture, the preview, the states in track with it even. Instead of doing that in separate apps and I need to stitch them together myself, it's just in one place, maybe in the same agent, in the same chat. And then the tool itself can also morph to what you're, like, your way of thinking, how you see the things. Maybe for a designer, the cursor they use might look or feel a little different than the cursor that your devs use,
39:37 Speaker 00 but it is still the same thing, it's just the same thing reconfigured. Certain things get hidden by default. Certain things get shown by default.
39:46 Speaker 01 The dream of the adaptive UIs is that they can show the right thing at any moment. The problem with it is that how do you get comfortable and set user expectations around what it is? And it sounds like what you're saying is it's not about generating it different every single time. It's about generating the right thing for the right user, the right context.
40:05 Speaker 00 Exactly.
40:05 Speaker 01 They can be familiar and the same for them.
40:07 Speaker 00 Right.
40:08 Speaker 01 It might be different for me than it is for you, right?
40:10 Speaker 00 It's like the fundamental system and how, say, what are the pieces? How they fit together, how they're laid out is the same. But then maybe like, you know, the user can also set their own preferences. The AI can kind of help them find their spot. And then they can start there, but as they use the tool, as they do more things, it might change. It just fits them better as they use it.
40:36 Speaker 01 Any advice for designers starting companies and building products? Just high level advice that you think would be most helpful for them going forward?
40:45 Speaker 00 I think the most important design problem is to think about, like, given the thing you want to do now and 10 years from now, what are the core concepts that won't change? How do they fit together? And then from there, you can kind of see what is the first step? What is the most essential pieces I need to start? And then as you go, you kind of figure out how things will evolve. And where you are today, what are the little steps to get there? The closer you get, the clearer it is. But also this thing there, there might also be pretty clear and it doesn't change as much.
41:30 Speaker 01 It's interesting, there's a quote from Jeff Bezos. Somebody asked him, like, what do you think is going to change over the next decade around Amazon's business? And his answer was like, well, I can tell you the three things that are not going to change.
41:43 Speaker 00 Yes.
41:43 Speaker 01 People are always going to want more selection, lower prices, faster delivery.
41:48 Speaker 00 Exactly.
41:48 Speaker 01 And so it sounds like what you're saying is finding those core elements is like, that's the thing to focus on and making sure that that is always accessible, even though the way people interact with it may change and evolve over time.
41:59 Speaker 00 Yep.
42:00 Speaker 01 Those are the important things to make sure you get right.
42:03 Speaker 00 Yeah, like that kind of defines what the thing is, what the company is about even.
42:08 Speaker 01 Rio, really appreciate you joining us today. Great.
Previous From Pivot Hell To $1.4 Billion Unicorn Next How Intelligent Is AI, Really? Page updated October 12, 2026 · transcript and summary are machine-generated
