The End of the Designer–Engineer Divide

Ryo Lu 0:00 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 say getting everything perfect. You actually start by building. 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. As we break the boundaries between these tools, as everyone can start talking with the code, magical things can happen.

Aaron Epstein 0:33 [upbeat music] Today, I am excited to welcome Ryo Lu. 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. Ryo, welcome to Design Review.

Ryo Lu 1:04 Thank you.

Aaron Epstein 1:04 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?

Ryo Lu 1:09 Mm-hmm. 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-

Aaron Epstein 1:30 Mm-hmm

Ryo Lu 1:30 ... uh, in China, um, that got, like, 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. Um, I made a couple startups myself, and then I got an offer from Asana, so I came, and then I became a designer.

Aaron Epstein 1:59 Were you technical all those years, like, when you first started to design?

Ryo Lu 2:03 [laughs] Um, 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.

Aaron Epstein 2:22 Mm-hmm.

Ryo Lu 2:22 Like, how I learned is really by just making stuff, building things without knowing what, what the fuck I'm doing. Like, I did not know the, the concept, the words. I just, "Ha, 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.

Aaron Epstein 2:40 Yeah.

Ryo Lu 2:40 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, prototype, I need to learn all of these, like, low-level concepts that are kind of dependencies. It's kind of scary.

Aaron Epstein 3:07 And that'll take forever, right?

Ryo Lu 3:08 Mm-hmm. It will take, like-

Aaron Epstein 3:09 That's the fear

Ryo Lu 3:10 ... it will take, like, month, almost like you need to, like, really focus on this and then go to a bootcamp and whatever.

Aaron Epstein 3:18 Mm-hmm.

Ryo Lu 3:18 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.

Aaron Epstein 3:42 Yeah.

Ryo Lu 3:43 So that's the difference.

Aaron Epstein 3:44 It sounds like you went through this journey of being frustrated that you-

Ryo Lu 3:48 Mm-hmm

Aaron Epstein 3:48 ... were kind of put in the design box-

Ryo Lu 3:49 Mm-hmm

Aaron Epstein 3:50 ... of, like, this is the little piece that you should focus on.

Ryo Lu 3:52 Mm-hmm.

Aaron Epstein 3:52 And now you have all these tools, and you're able to actually build the thing that you-

Ryo Lu 3:56 Yeah

Aaron Epstein 3:56 ... envision, that you've designed. You can make it come to life and be real.

Ryo Lu 4:00 Mm-hmm.

Aaron Epstein 4:00 And I know you kind of have a personal mission this year.

Ryo Lu 4:02 [laughs]

Aaron Epstein 4:03 Te-tell us more about that.

Ryo Lu 4:04 Yeah. So my personal KPI at Cursor this year is to turn all the designers into coders.

Aaron Epstein 4:10 Mm-hmm.

Ryo Lu 4:11 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, 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 you don't have to think about it anymore.

Aaron Epstein 5:01 So for anybody watching, maybe they're a designer.

Ryo Lu 5:04 Mm-hmm.

Aaron Epstein 5:04 They feel stuck in that box. They haven't been able to build the thing-

Ryo Lu 5:07 Yeah

Aaron Epstein 5:08 ... and break out. What's, like, the first step? Like, what are the things-

Ryo Lu 5:11 Mm-hmm

Aaron Epstein 5:11 ... that they should do-

Ryo Lu 5:12 Yeah

Aaron Epstein 5:12 ... to put them on that path to your KPIs-

Ryo Lu 5:14 Yeah

Aaron Epstein 5:15 ... of turning them into-

Ryo Lu 5:16 I think-

Aaron Epstein 5:16 ... good developers too?

Ryo Lu 5:17 ... it's actually fine or it's good to play with the more, like, vibe coding tools.

Aaron Epstein 5:23 Mm-hmm.

Ryo Lu 5:23 So like Figma Make or v0. Like, those kind of help you get started in a more constrained fashion.

Aaron Epstein 5:32 Mm-hmm.

Ryo Lu 5:32 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.

Aaron Epstein 5:47 Mm-hmm.

Ryo Lu 5:47 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, 'cause it's just, like, we're kind of un-un-unopinionated. It is just, like, a suite of tools and agent with an editor that can write any code, anything. iOS, web, you can even write a novel, like a book with it.

Aaron Epstein 6:19 Mm-hmm. How long have you been at Cursor? And tell us more about-

Ryo Lu 6:22 Uh

Aaron Epstein 6:22 ... your role and, and what you do in the day-to-day there.

Ryo Lu 6:24 I've been at Cursor for almost 10 month, but it feels like five years.

Aaron Epstein 6:29 Mm-hmm [chuckles] .

Ryo Lu 6:30 Like, in AI time. So I'm the head of design. I was, like, the first product/design person at Cursor. When I joined, we had, like, 20 people.

Aaron Epstein 6:40 Wow.

Ryo Lu 6:40 Now we have 250 people.

Aaron Epstein 6:42 Yeah.

Ryo Lu 6:42 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, uh, Justin, who works on the brand. We're trying to expand the team a little bit.

Aaron Epstein 6:54 Mm-hmm.

Ryo Lu 6:54 Um, 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, a-at its core, it is still, like, a tool designed for professional developers-

Aaron Epstein 7:14 Mm-hmm

Ryo Lu 7:14 ... to do stuff with AI and kind of augment themselves.

Aaron Epstein 7:17 Right. You have a lot of your own users at the company, right?

Ryo Lu 7:19 Yeah, yeah, yeah. Like, every single person at the company is a user.

Aaron Epstein 7:22 Yeah.

Ryo Lu 7:22 And then every single person has an... 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. Um, 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? 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.

Aaron Epstein 8:23 Yeah, it's like layers of an onion.

Ryo Lu 8:25 Mm-hmm.

Aaron Epstein 8:25 You want it to seem simple at first glance-

Ryo Lu 8:27 Yes

Aaron Epstein 8:27 ... but if you want power tools-

Ryo Lu 8:28 Yes

Aaron Epstein 8:28 ... you're able to uncover those.

Ryo Lu 8:30 Exactly.

Aaron Epstein 8:30 Talk about, um, you've been there 10 months now.

Ryo Lu 8:32 Mm-hmm.

Aaron Epstein 8:33 You've shipped a lot of really major things and worked-

Ryo Lu 8:35 Mm-hmm

Aaron Epstein 8:35 ... on and designed a lot of really important changes. Can you talk about some of those?

Ryo Lu 8:39 Yeah. Two biggest thing that I've done, one is the first day I joined. The problem was Cursor, maybe earlier this year, it was more like a couple features slapped on top of VS Code. There is the tab, which is the inline completion thing.

Aaron Epstein 8:55 Mm-hmm.

Ryo Lu 8:56 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 just gives you, like, a textual output. It doesn't do anything. That was, like, the primary interface-

Aaron Epstein 9:15 Mm-hmm

Ryo Lu 9:15 ... 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 only thing it d-it did. 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.

Aaron Epstein 9:41 Mm-hmm.

Ryo Lu 9:42 And then, like, November last year, Cursor added Agents. That was actually what hooked me to Cursor. Like, I tried Cursor three times before. I, I churned every time. I had to search on the web how to turn on the agent. I couldn't find it myself.

Aaron Epstein 9:59 [chuckles]

Ryo Lu 10:00 It was, like, a little checkbox in the composer tab that says normal. It's like normal versus agent. Nobody knows what normal means.

Aaron Epstein 10:08 Right.

Ryo Lu 10:09 And there was, like, other things. So like, there was a bug finder. There was some random crap around. 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 where... Like, how, how, how I think about it is they're all agents, same agent, but with different settings applied to them.

Aaron Epstein 10:42 Mm-hmm.

Ryo Lu 10:42 Say, 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, build the stuff, you have to hit a button. We just block you from doing that. 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 on the page.

Aaron Epstein 11:21 Mm-hmm [chuckles] .

Ryo Lu 11:22 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-

Aaron Epstein 11:45 Mm-hmm

Ryo Lu 11:45 ... but then it's kind of assisting you, to now the agent writes most code.

Aaron Epstein 11:50 Mm-hmm.

Ryo Lu 11:50 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. So you have a list of files-You have the editors that show the file themselves, and then the agent is kinda 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 r- review. This one's blocked. This one's still ongoing. Maybe it 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. 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.

Aaron Epstein 13:02 Oh, wow.

Ryo Lu 13:02 A blank file tree. It's really hard for, like, a person who, who isn'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.

Aaron Epstein 13:21 You've talked a lot about, you know, simplifying UIs, simplifying interactions.

Ryo Lu 13:25 Mm-hmm.

Aaron Epstein 13:25 Is there a lesson in there for, uh, design founders as they're building their products?

Ryo Lu 13:28 Yeah. I think of, like,

Ryo Lu 13:30 design, you can do it in two ways. One way is more like... Like, I 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, um, and then you can design, like, a little world for them that way. The problem with that is, like, as you start working on more problems, and then you... As you make more of these specific features, it's really hard to kinda 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. Then a thing that you were designing for this small group of people that solve their problem becomes something really massive that's hard to understand-

Aaron Epstein 14:19 Mm-hmm

Ryo Lu 14:19 ... that doesn't really work, that doesn't conceptualize as well. Versus you design in a more, like, systems first way, meaning you kinda decompose the problems into what are the parts, the primitives, the low-level concepts. When they work together, they solve the problems, and you try to keep that core concepts, the, the core set of concepts and primitives, as simple as possible. But they all are somewhat flexible. Say for, for example, when we were working on, on Notion, like, the core concepts are just blocks, pages, databases, and the people, the, 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 kinda 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.

Aaron Epstein 15:25 Mm-hmm.

Ryo Lu 15:25 But they will evolve. They will, you know, make new connections. Each of them will get better. And then how do you map your, you know, user problems, 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.

Aaron Epstein 15:53 Yeah. I think one of my takeaways is, um, as products scale, and certainly-

Ryo Lu 15:57 Mm-hmm

Aaron Epstein 15:57 ... you know, you... Probably Cursor is one of the fastest-

Ryo Lu 16:00 [laughs]

Aaron Epstein 16:00 ... growing products ever in history.

Ryo Lu 16:02 Yeah.

Aaron Epstein 16:02 Um, the tendency is to keep adding more features.

Ryo Lu 16:05 Mm-hmm.

Aaron Epstein 16:05 And the, the product expands in complexity as-

Ryo Lu 16:09 Mm-hmm

Aaron Epstein 16:09 ... the, as the user base scales-

Ryo Lu 16:10 Yeah

Aaron Epstein 16:10 ... and, you know, all the use cases-

Ryo Lu 16:12 Yeah

Aaron Epstein 16:12 ... expand. And if you're not intentional about going back through and rethinking things and paring it back down to the simpler state-

Ryo Lu 16:19 Yeah

Aaron Epstein 16:20 ... it's very easy for these products to get out of control.

Ryo Lu 16:22 Mm-hmm.

Aaron Epstein 16:22 And then it becomes something that is for nobody-

Ryo Lu 16:24 Yes

Aaron Epstein 16:25 ... because it doesn't have an opinion.

Ryo Lu 16:26 Yes.

Aaron Epstein 16:26 And it's impossible to work with these primitives-

Ryo Lu 16:28 Yep, yep, yep

Aaron Epstein 16:28 ... like you describe. And it sounds like that is an exercise that you are regularly going through.

Ryo Lu 16:33 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 month.

Aaron Epstein 16:43 Mm-hmm.

Ryo Lu 16:43 And then things that were maybe, like, disjointed, they get unified as we go. There's, like, a healthy tension. There'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, like, 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.

Aaron Epstein 17:17 Awesome. I, I would love for you to walk us through your design process-

Ryo Lu 17:20 Yes

Aaron Epstein 17:21 ... uh, at Cursor and how you've built some of these things.

Ryo Lu 17:23 Uh-huh.

Aaron Epstein 17:23 So one thing I would love to see here is if you can time travel us back to Cursor-

Ryo Lu 17:28 Mm-hmm

Aaron Epstein 17:28 ... maybe before you joined or around the time that you joined. Talk about your feedback looking at the site, especially now.

Ryo Lu 17:34 [laughs]

Aaron Epstein 17:35 And, and then pull up the most recent one and talk about some of the changes that you made-

Ryo Lu 17:38 Yeah

Aaron Epstein 17:38 ... along the way.

Ryo Lu 17:39 Let's go.

Ryo Lu 17:40 So I just pulled up Cursor when it started in 2023.

Aaron Epstein 17:45 Mm-hmm.

Ryo Lu 17:45 Wow. What is this? What does it do? Cool.

Aaron Epstein 17:50 It's very dark also.

Ryo Lu 17:51 Yeah, very dark, very, like... I'm not sure what these gradients are.

Aaron Epstein 17:55 Yeah.

Ryo Lu 17:56 Not sure what this is either.

Aaron Epstein 17:58 Mm-hmm.

Ryo Lu 17:59 It's like...

Aaron Epstein 18:00 Yeah, I see some blurry code, which-

Ryo Lu 18:01 Very, very not sure

Aaron Epstein 18:02 ... a text box.

Ryo Lu 18:04 Looks like the fonts are not loaded, but it might be something-

Aaron Epstein 18:07 Okay

Ryo Lu 18:07 ... not that great. "Chat with your project. Ask Grapt L codebase."

Aaron Epstein 18:12 All right, now we're getting-

Ryo Lu 18:13 Oh, whoa

Aaron Epstein 18:13 ... into a little bit more specifics

Ryo Lu 18:14 This thing is kind of crazy

Aaron Epstein 18:15 The line follows you

Ryo Lu 18:16 Yeah, yeah, yeah.

Aaron Epstein 18:17 [laughs]

Ryo Lu 18:17 So extra. Like, what are you trying to do? Like, you want people to focus on this line?

Aaron Epstein 18:23 Right.

Ryo Lu 18:24 Like, what the hell?

Aaron Epstein 18:25 Yeah, it's distracting, huh?

Ryo Lu 18:26 Yeah.

Aaron Epstein 18:27 Or it makes you think you're living in the future right now.

Ryo Lu 18:29 Right. Sure.

Aaron Epstein 18:29 It's like Tron or something.

Ryo Lu 18:31 But if you look at all this UI, like, I just, just don't know what I'm looking-

Aaron Epstein 18:34 Yeah, that's always the problem with showing specific screenshots-

Ryo Lu 18:37 Mm

Aaron Epstein 18:37 ... especially of code, is it's impossible for somebody to get-

Ryo Lu 18:39 Yeah

Aaron Epstein 18:40 ... the context of it.

Ryo Lu 18:41 And a lot of the code examples and stuff is, like, so foreign.

Aaron Epstein 18:44 Yeah.

Ryo Lu 18:45 Like, as a reader-

Aaron Epstein 18:46 Yep

Ryo Lu 18:46 ... 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.

Aaron Epstein 18:53 Mm-hmm.

Ryo Lu 18:53 Like, I, I just don't... It doesn't talk to me.

Aaron Epstein 18:56 Right. It's not your code. Right?

Ryo Lu 18:57 Yeah. Ah. Sure, sure, sure.

Aaron Epstein 19:00 All the fine developers. All right, we got a bunch of social proof here.

Ryo Lu 19:01 Okay. Back in the days, Cursor, what it's really good at is the tab, but there's no tab.

Aaron Epstein 19:06 Yeah.

Ryo Lu 19:07 What the hell?

Aaron Epstein 19:08 Yeah. What's the biggest thing-

Ryo Lu 19:09 So at this point

Aaron Epstein 19:09 ... like, you're going to make a change on this, what's, like, the number one thing that you wanna change and, and get right on-

Ryo Lu 19:14 Ah

Aaron Epstein 19:14 ... the next version?

Ryo Lu 19:16 Kill all the gradients.

Aaron Epstein 19:17 Why?

Ryo Lu 19:18 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 in really, like, disoriented.

Aaron Epstein 19:28 Mm-hmm.

Ryo Lu 19:29 Like, you don't know what, what is this? Or...

Aaron Epstein 19:32 Yep. That second section is the thing that I would most change.

Ryo Lu 19:36 This one?

Aaron Epstein 19:37 Yeah.

Ryo Lu 19:38 Yeah. It doesn't show you anything, right?

Aaron Epstein 19:39 Yeah, I can't figure out what it's trying to-

Ryo Lu 19:40 There is actually, like-

Aaron Epstein 19:41 ... convince me of, and it's prime real estate

Ryo Lu 19:42 ... zero information-

Aaron Epstein 19:43 Yeah

Ryo Lu 19:43 ... about what the Cur-

Aaron Epstein 19:44 Yeah

Ryo Lu 19:44 ... what Cursor can do.

Aaron Epstein 19:45 Yeah.

Ryo Lu 19:46 Add the chat tab, the composer.

Aaron Epstein 19:48 Mm-hmm.

Ryo Lu 19:48 When you toggle these things on, it actually defaults you to the chat tab.

Aaron Epstein 19:52 Mm-hmm.

Ryo Lu 19:52 You have to click composer.

Aaron Epstein 19:54 Mm-hmm.

Ryo Lu 19:54 You have to find this normal/agent toggle.

Aaron Epstein 19:58 Right.

Ryo Lu 19:58 You hit on agent, then you can do something.

Aaron Epstein 20:01 Right.

Ryo Lu 20:02 Versus this.

Aaron Epstein 20:04 Right.

Ryo Lu 20:05 You can just do something.

Aaron Epstein 20:06 Yep, and it defaults-

Ryo Lu 20:07 That's, that's it

Aaron Epstein 20:07 ... to agent. You don't have to go through and click all the things.

Ryo Lu 20:09 Yeah, yeah, yeah.

Aaron Epstein 20:10 Yep.

Ryo Lu 20:11 That's it.

Aaron Epstein 20:11 Okay, let's take a look at, um, the latest version.

Ryo Lu 20:14 Yes. We kind of clean up all the... It's, like, the foundation of the brand.

Aaron Epstein 20:19 Mm-hmm.

Ryo Lu 20:20 Like, fine-tuned every single detail from the logo, the typeface. We have, like, a custom typeface called Kurtha Gothic.

Aaron Epstein 20:28 Mm-hmm.

Ryo Lu 20:29 Um-

Aaron Epstein 20:29 I notice it's not dark mode also.

Ryo Lu 20:31 Uh-huh, but it's like, the idea is it, it should follow-

Aaron Epstein 20:35 Of course

Ryo Lu 20:36 ... your, your system.

Aaron Epstein 20:36 Ah, okay.

Ryo Lu 20:37 So that's the default.

Aaron Epstein 20:39 Yep.

Ryo Lu 20:39 But if you're dark, it's still dark.

Aaron Epstein 20:41 Yeah.

Ryo Lu 20:42 But I don't want to kind of, you know, give people brightness in the day if they want.

Aaron Epstein 20:48 Right. Right.

Ryo Lu 20:48 Yeah. Make Cursor feel a little less alienating. One of the ideas of, like, say, behind these, what we call, like, wallpapers-

Aaron Epstein 20:56 Mm-hmm

Ryo Lu 20:56 ... is that they're, they're now, like, just great art created by humans.

Aaron Epstein 21:01 Mm-hmm.

Ryo Lu 21:02 Um, like, a lot of these pictures-

Aaron Epstein 21:04 Yeah, you don't wanna lose the human connection, right?

Ryo Lu 21:05 Yeah. Like, they're not AI generated.

Aaron Epstein 21:07 Yeah, yeah.

Ryo Lu 21:07 They're actually, like, from past artworks-

Aaron Epstein 21:09 Yep

Ryo Lu 21:09 ... from the '80s, like, in the, in the 1800s and stuff. One thing that's cool with, like, our new site is that, like, all of these are interactive.

Aaron Epstein 21:19 Oh, that's cool.

Ryo Lu 21:20 They are real.

Aaron Epstein 21:21 I thought it was a screenshot or something.

Ryo Lu 21:21 They're actually real code.

Aaron Epstein 21:23 Uh-huh.

Ryo Lu 21:23 I made a lot of these as, like... You can actually click this one.

Aaron Epstein 21:26 So you can just try it out live.

Ryo Lu 21:27 Yeah, yeah. And then, like, a lot of these things actually work, so you can swap between different examples.

Aaron Epstein 21:32 Mm-hmm.

Ryo Lu 21:33 So maybe, like, this is more for, like, ML training.

Aaron Epstein 21:36 Yep.

Ryo Lu 21:36 This is almost like you're, you're learning how Cursor works.

Aaron Epstein 21:39 Yep.

Ryo Lu 21:39 There's, like, a rule that's being edited.

Aaron Epstein 21:41 Yep.

Ryo Lu 21:41 We show, like, a bunch of different, like, industries.

Aaron Epstein 21:45 That's so important because you wanna get people to the aha moment-

Ryo Lu 21:48 Mm-hmm

Aaron Epstein 21:48 ... of using the product, and the best way to do that is not download it and-

Ryo Lu 21:52 Yeah

Aaron Epstein 21:52 ... install it, and then set it up-

Ryo Lu 21:54 Yeah

Aaron Epstein 21:54 ... and figure out what project you're gonna work on. It's just like, here it is right here in the browser. You can start using it immediately.

Ryo Lu 22:00 Yeah. And then you can actually type in it, and then boom, you can download.

Aaron Epstein 22:03 Yeah. Yeah.

Ryo Lu 22:05 Each of the pages are also really simple.

Aaron Epstein 22:07 Mm-hmm.

Ryo Lu 22:07 It's just like boom, boom, boom, and then you can dive into them if you want.

Aaron Epstein 22:11 Yeah, and it seems like you have one key point for each one that you're trying to make.

Ryo Lu 22:15 Yes.

Aaron Epstein 22:15 And something that you are showing with a screenshot visually-

Ryo Lu 22:17 Yes

Aaron Epstein 22:17 ... to illustrate as well.

Ryo Lu 22:18 Yes. It's like kind of calling back to, like, the, the core concepts-

Aaron Epstein 22:23 Mm-hmm

Ryo Lu 22:24 ... that I just talked about-

Aaron Epstein 22:25 Mm-hmm

Ryo Lu 22:25 ... is, like, the slide should also just show those.

Aaron Epstein 22:28 Yeah.

Ryo Lu 22:28 Yeah. And then-

Aaron Epstein 22:29 Yeah, so go back to the homepage for a second.

Ryo Lu 22:30 Yes.

Aaron Epstein 22:31 Let's, let's look at all of those.

Ryo Lu 22:32 Mm-hmm.

Aaron Epstein 22:33 And I'm curious which you picked and why.

Ryo Lu 22:35 Yeah.

Aaron Epstein 22:35 So okay, agent.

Ryo Lu 22:36 Agents.

Aaron Epstein 22:36 Yep.

Ryo Lu 22:37 The tab.

Aaron Epstein 22:38 Yep. Tab auto-complete.

Ryo Lu 22:40 And this is, like, the ecosystem/Cursor is everywhere.

Aaron Epstein 22:44 Right, it's connected with all the other tools that you use.

Ryo Lu 22:47 Mm-hmm. Yep. Some testimonials.

Aaron Epstein 22:49 Mm-hmm.

Ryo Lu 22:50 These are more, like, ways for you to kind of go into different spots.

Aaron Epstein 22:55 Okay.

Ryo Lu 22:55 There's one for enterprise, one for learning models.

Aaron Epstein 22:58 Mm-hmm. I would love for you to walk us through your design process-

Ryo Lu 23:01 Yes

Aaron Epstein 23:02 ... uh, at Cursor and how you've built some of these things.

Ryo Lu 23:04 Uh-huh. I'll first show you, like, something I do for work, and then I'll show you something for fun.

Aaron Epstein 23:10 Great.

Ryo Lu 23:10 The first thing I showed is Baby Cursor.

Aaron Epstein 23:13 Mm-hmm.

Ryo Lu 23:14 And the idea

Ryo Lu 23:16 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-

Aaron Epstein 23:34 Mm-hmm

Ryo Lu 23:34 ... than, say, you just build a little environment for you to play with your ideas. You can kind of reconstruct parts of the UI and the inter-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.

Aaron Epstein 23:52 So Baby Cursor is, like, a scaled down, simplified version-

Ryo Lu 23:56 Mm-hmm

Aaron Epstein 23:56 ... of Cursor-

Ryo Lu 23:57 Yes

Aaron Epstein 23:57 ... that is like it in many ways.

Ryo Lu 24:00 Mm-hmm.

Aaron Epstein 24:00 And it becomes your own personal playground-

Ryo Lu 24:02 Yes

Aaron Epstein 24:02 ... for you to just add new features and explore different ways of doing things-

Ryo Lu 24:05 Mm-hmm

Aaron Epstein 24:05 ... to try to get it right before you eventually wrap it back in-

Ryo Lu 24:09 Yeah

Aaron Epstein 24:09 ... into, uh, grown-up Cursor.

Ryo Lu 24:11 Yep. So I built this in-I think an afternoon, maybe like couple hours.

Aaron Epstein 24:17 Hmm.

Ryo Lu 24:17 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.

Aaron Epstein 24:39 Mm.

Ryo Lu 24:40 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.

Aaron Epstein 24:50 Mm-hmm.

Ryo Lu 24:50 We added the internal browser, so maybe that's like how this thing ended up.

Aaron Epstein 24:55 Mm-hmm.

Ryo Lu 24:55 Um-

Aaron Epstein 24:56 And that started in Baby Cursor?

Ryo Lu 24:57 Mm-hmm. And, uh, one example that's kinda cool is I was trying to like explore some ideas of how we can run multiple agents-

Aaron Epstein 25:07 Mm

Ryo Lu 25:07 ... 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-

Aaron Epstein 25:18 Nice. Yeah

Ryo Lu 25:18 ... it will run the agent at the same time.

Aaron Epstein 25:20 Cool.

Ryo Lu 25:21 Um, you can see both live outputs. You can kinda pick and compare different changes.

Aaron Epstein 25:26 Mm-hmm.

Ryo Lu 25:27 And like this kind of stuff, for you to, to make in Figma is gonna be like insane. Like-

Aaron Epstein 25:34 Yeah

Ryo Lu 25:35 ... 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-

Aaron Epstein 25:43 Well, the problem is you would spend forever designing-

Ryo Lu 25:46 Mm-hmm

Aaron Epstein 25:46 ... this as a mockup-

Ryo Lu 25:47 Yeah

Aaron Epstein 25:47 ... with fake data.

Ryo Lu 25:48 Exactly. It's like-

Aaron Epstein 25:49 And, and you would have no way to like actually test what-

Ryo Lu 25:52 Mm-hmm

Aaron Epstein 25:52 ... it feels like to use it.

Ryo Lu 25:53 Yep.

Aaron Epstein 25:53 And then you'd have to wait forever for an engineer to free up-

Ryo Lu 25:56 Exactly

Aaron Epstein 25:56 ... and be able to prototype it for you-

Ryo Lu 25:58 Mm-hmm

Aaron Epstein 25:58 ... so you could compare different ideas.

Ryo Lu 26:00 Yeah.

Aaron Epstein 26:00 And you can just do that instantly right here.

Ryo Lu 26:02 Exactly. Like, it's so easy.

Aaron Epstein 26:04 Yeah.

Ryo Lu 26:05 This is kinda like how Cursor used to look like, like pre-1-

Aaron Epstein 26:09 Mm.

Ryo Lu 26:09 ... uh, pre-2.0. You know, we talked about like there's the files. There's some-

Aaron Epstein 26:13 Mm-hmm

Ryo Lu 26:13 ... editors. There's the chat that's kinda like on the side. And then let me show you like Cursor 2.0. So we kinda flipped the order of things, like you kinda 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. Um, you can keep m- like Cursor really clean, like if I'm just like doing stuff, say, in my little prototype, um, real OS, I just do this.

Aaron Epstein 26:46 Mm-hmm.

Ryo Lu 26:47 It almost feels like a lovable.

Aaron Epstein 26:48 Mm-hmm.

Ryo Lu 26:49 But the difference is you get the whole thing. Like you, you still get like all the files, the Git tools-

Aaron Epstein 26:55 Right

Ryo Lu 26:56 ... the search. You get the full, like command palette. You get everything, but you can always like, you know, s- start with a sim- simpler state, focus on, you know, ideating or planning or making stuff.

Aaron Epstein 27:11 I love this. This is real OS.

Ryo Lu 27:13 Mm-hmm.

Aaron Epstein 27:13 This is your own personal playground, right?

Ryo Lu 27:15 Yes. Yes, yes.

Aaron Epstein 27:16 Um, yeah, just sh- show us high level, like what have you built here?

Ryo Lu 27:19 It's kinda meta. I don't know what I'm doing.

Aaron Epstein 27:21 [laughs]

Ryo Lu 27:22 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.

Aaron Epstein 27:33 Uh-huh.

Ryo Lu 27:34 And I just asked the agent, "Hmm, put it in a window," and then it made this like draggable window thing, and then added the menu bar. And then I was like, "Hmm, why not just add more apps?"

Aaron Epstein 27:45 Mm-hmm.

Ryo Lu 27:46 And I kept a- kept at making new things. I made an iPod that actually works.

Aaron Epstein 27:51 [laughs]

Ryo Lu 27:51 Uh, I made a time traveling browser. Goes back in time, but also you can jump to the future, go back into like ancient times.

Aaron Epstein 28:01 [laughs]

Ryo Lu 28:01 These are like generated by AI.

Aaron Epstein 28:03 What happens if you go to 1000 BC?

Ryo Lu 28:04 Let's go.

Aaron Epstein 28:04 What did the internet look like back then?

Ryo Lu 28:06 Boom. Oh, wow, it's in Korean too, but you can actually change, you know, the generation.

Aaron Epstein 28:11 Mm-hmm.

Ryo Lu 28:11 You can also set like a scene. I don't know, maybe we're in the UK. And then let's try refresh. It's gonna fetch the latest apple.com content-

Aaron Epstein 28:21 Mm-hmm

Ryo Lu 28:22 ... pass it through to like a LLM, and then it's gonna generate the page for it.

Aaron Epstein 28:26 Hmm.

Ryo Lu 28:28 And as it does it, it makes like el- elevator music. So how I would, um, start a new thing, so in 2.0 we have a new mode called plan mode.

Aaron Epstein 28:37 Mm-hmm.

Ryo Lu 28:38 And then the idea is maybe you don't really know all the details of what you're doing. You kinda 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." Then we can try like s- see what, what the agent comes up with.

Aaron Epstein 29:07 Mm-hmm.

Ryo Lu 29:08 Um, what it's gonna do is it's gonna search through the whole code base, figure out what's, what's there, come up with a plan. It might a- also like ask a few questions back so that if there's something like ambiguous... Oh, here it is. You can just like talk, talk to it, and then at the end it will come up with a plan. So frictions to share. Let's see. Not obvious you can share an app that's saved. Two, what would help better? Maybe, let's see. 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.

Aaron Epstein 30:01 Mm-hmm.

Ryo Lu 30:02 And the plan looks almost like a PRD that your PM writes.

Aaron Epstein 30:05 Mm-hmm.

Ryo Lu 30:06 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. Mm.Add a button for the fee cards. Mm-hmm. 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.

Aaron Epstein 30:31 Mm-hmm.

Ryo Lu 30:33 And with our new composer model, like, it's four times faster than Sonnet, and it's, like, twice as cheap.

Aaron Epstein 30:42 Mm-hmm.

Ryo Lu 30:43 So things will happen, like, almost like pretty quick before our, before your eyes.

Aaron Epstein 30:49 Mm-hmm.

Ryo Lu 30:50 Um, ahaha.

Aaron Epstein 30:52 Cool.

Ryo Lu 30:54 Let's see what, what's, what's gonna happen. Adding more buttons. [laughs] Cards, let's see. Is there, like, a share button? Woo-hoo-hoo. Fixing some bugs. Oh, okay, let's see what happened. Share button in the toolbar. Output loaded. Let's see if I get this. Aha, a little share button.

Aaron Epstein 31:22 Oh, there we go.

Ryo Lu 31:23 Let's see what happens when we click on it. Hey, it didn't work. Maybe, like, let's ask it to hook up the share button with the share model. Then it's gonna fix it. Let's see if it worked. Oh, oh, oh, oh. Oh.

Aaron Epstein 31:45 Ah.

Ryo Lu 31:45 Nice. There you go. Beautiful. Cool.

Aaron Epstein 31:50 That's great, and the cool thing is you didn't even have to touch any code, right?

Ryo Lu 31:53 Mm-hmm.

Aaron Epstein 31:54 You basically just spoke in English.

Ryo Lu 31:55 Mm-hmm.

Aaron Epstein 31:56 You got a PRD-

Ryo Lu 31:57 Yep

Aaron Epstein 31:57 ... which designers are used to today.

Ryo Lu 31:58 Yep.

Aaron Epstein 31:59 And you just kept telling it what to do to fix things-

Ryo Lu 32:02 Mm-hmm

Aaron Epstein 32:03 ... until it did it.

Ryo Lu 32:04 And if you want to look at code, it's here.

Aaron Epstein 32:05 It's there if you want it. That feels approachable for any designer to do, right?

Ryo Lu 32:10 Mm-hmm.

Aaron Epstein 32:10 And start building something themselves.

Ryo Lu 32:12 Yeah, so one thing that I think we're gonna fix maybe, like, even in the next two weeks is-

Aaron Epstein 32:17 Mm-hmm

Ryo Lu 32:17 ... like, when you start Cursor, like you're, you're faced with, like, three buttons, at least the, the version before.

Aaron Epstein 32:25 Mm-hmm.

Ryo Lu 32:26 Where it says, like, Open project, Clone repo, Connect to SSH.

Aaron Epstein 32:29 Yeah.

Ryo Lu 32:29 Like, you don't really know what the hell, like, those things mean.

Aaron Epstein 32:32 Yeah, many designers-

Ryo Lu 32:33 And then our new, like, landing page is just like, boom, you just start.

Aaron Epstein 32:38 Mm-hmm.

Ryo Lu 32:38 And then the agent is gonna help you start a new project if it's not there.

Aaron Epstein 32:42 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-

Ryo Lu 32:55 Mm-hmm

Aaron Epstein 32:56 ... in the age of AI and, and certainly Cursor as a tool enabling that.

Ryo Lu 32:59 Yeah. The roles will start blurring. The designers will start coding. The engineers will start designing.

Aaron Epstein 33:06 Mm-hmm.

Ryo Lu 33:06 And then our shared language is code. It is not just picture frames, not pixel values, but code. You start not by, say, 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, 60%, 70%. 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.

Aaron Epstein 33:45 Mm-hmm.

Ryo Lu 33:46 Maybe, like, the first time it comes up, it's actually the, the thing that you wanted. But then, you know, what's next? How do I get to somewhere even better? The agent's able to do that too for you.

Aaron Epstein 33:59 You've described this as, like, sculpting, right?

Ryo Lu 34:00 Mm-hmm.

Aaron Epstein 34:01 Is that a way that designers should think about this?

Ryo Lu 34:02 Yes. Like, the difference before was, like, we started from, ah, let's do some wire frames and sketches. Then we paint each of the layers and boxes with, like, styles, with colors and type, and you're, like, painting stroke by stroke, but you're painting on a, on an artifact, on a canvas that's not real. Versus the new way, it is you just ask the agent, and you get this lu- cl- clump 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 kinda 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 s- like pixels stuck in a canvas.

Aaron Epstein 35:04 And I think we saw that when you were, um, you were adding the share sheet, right?

Ryo Lu 35:08 Uh-huh.

Aaron Epstein 35:08 It was like the button appeared-

Ryo Lu 35:09 Yeah

Aaron Epstein 35:09 ... but then clicking it didn't do anything.

Ryo Lu 35:11 Yeah, yeah, yeah.

Aaron Epstein 35:11 So you got it, like, 60, 70% of the way there.

Ryo Lu 35:13 Mm-hmm.

Aaron Epstein 35:13 And then you're like, "Okay, now I need it to do this thing."

Ryo Lu 35:16 Yep.

Aaron Epstein 35:16 So you told it what to do, and then the next time it worked.

Ryo Lu 35:18 Yeah, it fixed it. Yeah. It's like if you get something bad or, like, ugly, it's actually your job to make it pretty-

Aaron Epstein 35:24 Mm-hmm

Ryo Lu 35:24 ... 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.

Aaron Epstein 35:38 One thing that I find, um, there's some projects we've been doing internally-

Ryo Lu 35:42 Mm-hmm

Aaron Epstein 35:42 ... and using a very similar process to what you're describing here.

Ryo Lu 35:45 Mm-hmm.

Aaron Epstein 35:45 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-

Ryo Lu 35:51 Mm-hmm, mm-hmm

Aaron Epstein 35:52 ... and all these things that are really hard to do when you're just in a frame-

Ryo Lu 35:56 Yeah

Aaron Epstein 35:56 ... somewhere.

Ryo Lu 35:57 Yeah.

Aaron Epstein 35:57 And when you get to experience it, now all of a sudden, all these other layers come alive-

Ryo Lu 36:01 Mm-hmm, mm-hmm

Aaron Epstein 36:01 ... that you get to experiment with-

Ryo Lu 36:04 Exactly

Aaron Epstein 36:04 ... and test and...

Ryo Lu 36:05 Exactly.

Aaron Epstein 36:05 It feels like everything is just gonna level up so much more-

Ryo Lu 36:08 Mm-hmm, mm-hmm

Aaron Epstein 36:08 ... because of this.

Ryo Lu 36:09 Yes. It's like,

Ryo Lu 36:11 like it's not even just for designers.

Aaron Epstein 36:13 Mm-hmm.

Ryo Lu 36:13 It also includes, say, like, your PM's writing some Google Doc that's stuck. It never gets updated. It's always, like, disjointed from the real thing.

Aaron Epstein 36:21 Right.

Ryo Lu 36:22 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.

Aaron Epstein 36:43 Yeah. And so in that world, what are the skills that designers should be focused on becoming great at?

Ryo Lu 36:48 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 the, the other layers or the other concepts that maybe you don't know yet, 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 built is better. Versus you don't really know much, then it might just give you something mediocre.

Aaron Epstein 37:42 It's like a new, more powerful tool-

Ryo Lu 37:44 Mm-hmm

Aaron Epstein 37:44 ... to use, and you need to learn how to use it effectively.

Ryo Lu 37:47 Yeah. It's almost like the more domain knowledge you have, plus the agent, plus, you know, knowledge of the code base and everything that connects to it, the more things you can do. And it's not just for designers. It's for everyone.

Aaron Epstein 38:00 Mm-hmm. How do you think interfaces are gonna change in the future? There's a lot of talk of-

Ryo Lu 38:04 Mm-hmm

Aaron Epstein 38:04 ... adaptive UIs and generative UIs.

Ryo Lu 38:06 Mm-hmm.

Aaron Epstein 38:07 Like, how, how do you think about that? Where do you think that's going?

Ryo Lu 38:09 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 docs, I go to Google Doc." And 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. 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-

Aaron Epstein 39:02 Mm-hmm

Ryo Lu 39:02 ... do stuff with it. When it makes sense, I still want a to-do list. I still want a table.

Aaron Epstein 39:08 Mm-hmm.

Ryo Lu 39:08 I still want to see the picture, the preview, the states, interact with it even. Instead of doing that in separate apps and then 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 your... 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, but it is still the same thing. It's just the same thing reconfigured. Th- Certain things get hidden by default. Certain things get shown by default.

Aaron Epstein 39:46 The dream of the adaptive UIs is that they can show the right thing at any moment.

Ryo Lu 39:50 Mm-hmm.

Aaron Epstein 39:51 The problem with it is that how do you get comfortable and-

Ryo Lu 39:55 Yeah

Aaron Epstein 39:55 ... set user expectations-

Ryo Lu 39:57 Yeah

Aaron Epstein 39:57 ... around what it is? And it sounds like what-

Ryo Lu 39:58 Yeah

Aaron Epstein 39:58 ... you're saying is it's not about generating it different every single time.

Ryo Lu 40:02 Yes.

Aaron Epstein 40:02 It's about generating the right thing for the right user-

Ryo Lu 40:04 Yes

Aaron Epstein 40:04 ... in the right context.

Ryo Lu 40:05 Exactly.

Aaron Epstein 40:06 That can be familiar and the same for them.

Ryo Lu 40:07 Right.

Aaron Epstein 40:07 It's the... It might be different for me than it is for you, right?

Ryo Lu 40:10 Mm-hmm. 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.

Aaron Epstein 40:19 Mm-hmm.

Ryo Lu 40:19 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.

Aaron Epstein 40:36 Any advice for designers starting companies and building products?

Ryo Lu 40:41 Mm-hmm.

Aaron Epstein 40:42 Just high level advice that you think would be most helpful for them going forward.

Ryo Lu 40:46 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.

Aaron Epstein 41:19 Mm-hmm.

Ryo Lu 41:20 The closer you get, the clearer it is, but also this thing they're there might also be pretty clear, and it doesn't change as much.

Aaron Epstein 41:30 It's interesting. There's a quote from, um, Jeff Bezos. Somebody asked him, like, "What do you think is gonna change over the next decade-"

Ryo Lu 41:37 Mm-hmm

Aaron Epstein 41:37 ... "around Amazon's business?"

Ryo Lu 41:39 Mm-hmm.

Aaron Epstein 41:39 And his answer was like, "Well, I can tell you the three things that are not gonna change."

Ryo Lu 41:42 [laughs] Yes.

Aaron Epstein 41:43 People are always gonna want more selection-

Ryo Lu 41:46 Mm-hmm

Aaron Epstein 41:46 ... lower prices, faster delivery.

Ryo Lu 41:48 Exactly.

Aaron Epstein 41:48 And so it sounds like what you're saying is finding those core elements-

Ryo Lu 41:51 Mm-hmm

Aaron Epstein 41:52 ... is, like, that's the thing to focus on and making sure that that is always accessible-

Ryo Lu 41:56 Yeah

Aaron Epstein 41:56 ... even though the way people interact with it may change-

Ryo Lu 41:58 Yeah

Aaron Epstein 41:58 ... and evolve over time.

Ryo Lu 41:59 Yep.

Aaron Epstein 42:00 Those are the important things to make sure you get right.

Ryo Lu 42:03 Yeah. Like, that kind of defines what the thing is, what the company is about even.

Aaron Epstein 42:08 Mm-hmm. Ryo, really appreciate you joining us today.

Ryo Lu 42:10 Great. [outro music]