The End of the Designer–Engineer Divide

1. 0:00 – 4:11

   Designers Becoming Builders

   1. RLRyo Lu0:00

      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.

   2. AEAaron Epstein0:33

      [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.

   3. RLRyo Lu1:04

      Thank you.

   4. AEAaron Epstein1:04

      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?

   5. RLRyo Lu1:09

      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-

   6. AEAaron Epstein1:30

      Mm-hmm

   7. RLRyo Lu1:30

      ... 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.

   8. AEAaron Epstein1:59

      Were you technical all those years, like, when you first started to design?

   9. RLRyo Lu2:03

      [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.

   10. AEAaron Epstein2:22

       Mm-hmm.

   11. RLRyo Lu2:22

       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.

   12. AEAaron Epstein2:40

       Yeah.

   13. RLRyo Lu2:40

       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.

   14. AEAaron Epstein3:07

       And that'll take forever, right?

   15. RLRyo Lu3:08

       Mm-hmm. It will take, like-

   16. AEAaron Epstein3:09

       That's the fear

   17. RLRyo Lu3:10

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

   18. AEAaron Epstein3:18

       Mm-hmm.

   19. RLRyo Lu3:18

       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.

   20. AEAaron Epstein3:42

       Yeah.

   21. RLRyo Lu3:43

       So that's the difference.

   22. AEAaron Epstein3:44

       It sounds like you went through this journey of being frustrated that you-

   23. RLRyo Lu3:48

       Mm-hmm

   24. AEAaron Epstein3:48

       ... were kind of put in the design box-

   25. RLRyo Lu3:49

       Mm-hmm

   26. AEAaron Epstein3:50

       ... of, like, this is the little piece that you should focus on.

   27. RLRyo Lu3:52

       Mm-hmm.

   28. AEAaron Epstein3:52

       And now you have all these tools, and you're able to actually build the thing that you-

   29. RLRyo Lu3:56

       Yeah

   30. AEAaron Epstein3:56

       ... envision, that you've designed. You can make it come to life and be real.
2. 4:11 – 8:39

   Learning by Building, Not Studying

   1. RLRyo Lu4:11

      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.

   2. AEAaron Epstein5:01

      So for anybody watching, maybe they're a designer.

   3. RLRyo Lu5:04

      Mm-hmm.

   4. AEAaron Epstein5:04

      They feel stuck in that box. They haven't been able to build the thing-

   5. RLRyo Lu5:07

      Yeah

   6. AEAaron Epstein5:08

      ... and break out. What's, like, the first step? Like, what are the things-

   7. RLRyo Lu5:11

      Mm-hmm

   8. AEAaron Epstein5:11

      ... that they should do-

   9. RLRyo Lu5:12

      Yeah

   10. AEAaron Epstein5:12

       ... to put them on that path to your KPIs-

   11. RLRyo Lu5:14

       Yeah

   12. AEAaron Epstein5:15

       ... of turning them into-

   13. RLRyo Lu5:16

       I think-

   14. AEAaron Epstein5:16

       ... good developers too?

   15. RLRyo Lu5:17

       ... it's actually fine or it's good to play with the more, like, vibe coding tools.

   16. AEAaron Epstein5:23

       Mm-hmm.

   17. RLRyo Lu5:23

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

   18. AEAaron Epstein5:32

       Mm-hmm.

   19. RLRyo Lu5:32

       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.

   20. AEAaron Epstein5:47

       Mm-hmm.

   21. RLRyo Lu5:47

       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.

   22. AEAaron Epstein6:19

       Mm-hmm. How long have you been at Cursor? And tell us more about-

   23. RLRyo Lu6:22

       Uh

   24. AEAaron Epstein6:22

       ... your role and, and what you do in the day-to-day there.

   25. RLRyo Lu6:24

       I've been at Cursor for almost 10 month, but it feels like five years.

   26. AEAaron Epstein6:29

       Mm-hmm [chuckles] .

   27. RLRyo Lu6:30

       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.

   28. AEAaron Epstein6:40

       Wow.

   29. RLRyo Lu6:40

       Now we have 250 people.

   30. AEAaron Epstein6:42

       Yeah.
3. 8:39 – 13:30

   Inside Cursor’s Design Team

   1. RLRyo Lu8:39

      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.

   2. AEAaron Epstein8:55

      Mm-hmm.

   3. RLRyo Lu8:56

      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-

   4. AEAaron Epstein9:15

      Mm-hmm

   5. RLRyo Lu9:15

      ... 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.

   6. AEAaron Epstein9:41

      Mm-hmm.

   7. RLRyo Lu9:42

      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.

   8. AEAaron Epstein9:59

      [chuckles]

   9. RLRyo Lu10:00

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

   10. AEAaron Epstein10:08

       Right.

   11. RLRyo Lu10:09

       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.

   12. AEAaron Epstein10:42

       Mm-hmm.

   13. RLRyo Lu10:42

       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.

   14. AEAaron Epstein11:21

       Mm-hmm [chuckles] .

   15. RLRyo Lu11:22

       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-

   16. AEAaron Epstein11:45

       Mm-hmm

   17. RLRyo Lu11:45

       ... but then it's kind of assisting you, to now the agent writes most code.

   18. AEAaron Epstein11:50

       Mm-hmm.

   19. RLRyo Lu11:50

       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.

   20. AEAaron Epstein13:02

       Oh, wow.

   21. RLRyo Lu13:02

       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.

   22. AEAaron Epstein13:21

       You've talked a lot about, you know, simplifying UIs, simplifying interactions.

   23. RLRyo Lu13:25

       Mm-hmm.

   24. AEAaron Epstein13:25

       Is there a lesson in there for, uh, design founders as they're building their products?

   25. RLRyo Lu13:28

       Yeah. I think of, like,

4. 13:30 – 17:40

   Designing Systems, Not Features

   1. RLRyo Lu13:30

      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-

   2. AEAaron Epstein14:19

      Mm-hmm

   3. RLRyo Lu14:19

      ... 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.

   4. AEAaron Epstein15:25

      Mm-hmm.

   5. RLRyo Lu15:25

      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.

   6. AEAaron Epstein15:53

      Yeah. I think one of my takeaways is, um, as products scale, and certainly-

   7. RLRyo Lu15:57

      Mm-hmm

   8. AEAaron Epstein15:57

      ... you know, you... Probably Cursor is one of the fastest-

   9. RLRyo Lu16:00

      [laughs]

   10. AEAaron Epstein16:00

       ... growing products ever in history.

   11. RLRyo Lu16:02

       Yeah.

   12. AEAaron Epstein16:02

       Um, the tendency is to keep adding more features.

   13. RLRyo Lu16:05

       Mm-hmm.

   14. AEAaron Epstein16:05

       And the, the product expands in complexity as-

   15. RLRyo Lu16:09

       Mm-hmm

   16. AEAaron Epstein16:09

       ... the, as the user base scales-

   17. RLRyo Lu16:10

       Yeah

   18. AEAaron Epstein16:10

       ... and, you know, all the use cases-

   19. RLRyo Lu16:12

       Yeah

   20. AEAaron Epstein16:12

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

   21. RLRyo Lu16:19

       Yeah

   22. AEAaron Epstein16:20

       ... it's very easy for these products to get out of control.

   23. RLRyo Lu16:22

       Mm-hmm.

   24. AEAaron Epstein16:22

       And then it becomes something that is for nobody-

   25. RLRyo Lu16:24

       Yes

   26. AEAaron Epstein16:25

       ... because it doesn't have an opinion.

   27. RLRyo Lu16:26

       Yes.

   28. AEAaron Epstein16:26

       And it's impossible to work with these primitives-

   29. RLRyo Lu16:28

       Yep, yep, yep

   30. AEAaron Epstein16:28

       ... like you describe. And it sounds like that is an exercise that you are regularly going through.
5. 17:40 – 23:15

   Rebuilding Cursor Around Agents

   1. RLRyo Lu17:40

      So I just pulled up Cursor when it started in 2023.

   2. AEAaron Epstein17:45

      Mm-hmm.

   3. RLRyo Lu17:45

      Wow. What is this? What does it do? Cool.

   4. AEAaron Epstein17:50

      It's very dark also.

   5. RLRyo Lu17:51

      Yeah, very dark, very, like... I'm not sure what these gradients are.

   6. AEAaron Epstein17:55

      Yeah.

   7. RLRyo Lu17:56

      Not sure what this is either.

   8. AEAaron Epstein17:58

      Mm-hmm.

   9. RLRyo Lu17:59

      It's like...

   10. AEAaron Epstein18:00

       Yeah, I see some blurry code, which-

   11. RLRyo Lu18:01

       Very, very not sure

   12. AEAaron Epstein18:02

       ... a text box.

   13. RLRyo Lu18:04

       Looks like the fonts are not loaded, but it might be something-

   14. AEAaron Epstein18:07

       Okay

   15. RLRyo Lu18:07

       ... not that great. "Chat with your project. Ask Grapt L codebase."

   16. AEAaron Epstein18:12

       All right, now we're getting-

   17. RLRyo Lu18:13

       Oh, whoa

   18. AEAaron Epstein18:13

       ... into a little bit more specifics

   19. RLRyo Lu18:14

       This thing is kind of crazy

   20. AEAaron Epstein18:15

       The line follows you

   21. RLRyo Lu18:16

       Yeah, yeah, yeah.

   22. AEAaron Epstein18:17

       [laughs]

   23. RLRyo Lu18:17

       So extra. Like, what are you trying to do? Like, you want people to focus on this line?

   24. AEAaron Epstein18:23

       Right.

   25. RLRyo Lu18:24

       Like, what the hell?

   26. AEAaron Epstein18:25

       Yeah, it's distracting, huh?

   27. RLRyo Lu18:26

       Yeah.

   28. AEAaron Epstein18:27

       Or it makes you think you're living in the future right now.

   29. RLRyo Lu18:29

       Right. Sure.

   30. AEAaron Epstein18:29

       It's like Tron or something.
6. 23:15 – 30:52

   Prototyping With “Baby Cursor”

   1. RLRyo Lu23:16

      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-

   2. AEAaron Epstein23:34

      Mm-hmm

   3. RLRyo Lu23:34

      ... 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.

   4. AEAaron Epstein23:52

      So Baby Cursor is, like, a scaled down, simplified version-

   5. RLRyo Lu23:56

      Mm-hmm

   6. AEAaron Epstein23:56

      ... of Cursor-

   7. RLRyo Lu23:57

      Yes

   8. AEAaron Epstein23:57

      ... that is like it in many ways.

   9. RLRyo Lu24:00

      Mm-hmm.

   10. AEAaron Epstein24:00

       And it becomes your own personal playground-

   11. RLRyo Lu24:02

       Yes

   12. AEAaron Epstein24:02

       ... for you to just add new features and explore different ways of doing things-

   13. RLRyo Lu24:05

       Mm-hmm

   14. AEAaron Epstein24:05

       ... to try to get it right before you eventually wrap it back in-

   15. RLRyo Lu24:09

       Yeah

   16. AEAaron Epstein24:09

       ... into, uh, grown-up Cursor.

   17. RLRyo Lu24:11

       Yep. So I built this in-I think an afternoon, maybe like couple hours.

   18. AEAaron Epstein24:17

       Hmm.

   19. RLRyo Lu24:17

       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.

   20. AEAaron Epstein24:39

       Mm.

   21. RLRyo Lu24:40

       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.

   22. AEAaron Epstein24:50

       Mm-hmm.

   23. RLRyo Lu24:50

       We added the internal browser, so maybe that's like how this thing ended up.

   24. AEAaron Epstein24:55

       Mm-hmm.

   25. RLRyo Lu24:55

       Um-

   26. AEAaron Epstein24:56

       And that started in Baby Cursor?

   27. RLRyo Lu24:57

       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-

   28. AEAaron Epstein25:07

       Mm

   29. RLRyo Lu25:07

       ... 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-

   30. AEAaron Epstein25:18

       Nice. Yeah
7. 30:52 – 36:10

   Design as Sculpting, Not Painting

   1. AEAaron Epstein30:52

      Cool.

   2. RLRyo Lu30:54

      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.

   3. AEAaron Epstein31:22

      Oh, there we go.

   4. RLRyo Lu31:23

      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.

   5. AEAaron Epstein31:45

      Ah.

   6. RLRyo Lu31:45

      Nice. There you go. Beautiful. Cool.

   7. AEAaron Epstein31:50

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

   8. RLRyo Lu31:53

      Mm-hmm.

   9. AEAaron Epstein31:54

      You basically just spoke in English.

   10. RLRyo Lu31:55

       Mm-hmm.

   11. AEAaron Epstein31:56

       You got a PRD-

   12. RLRyo Lu31:57

       Yep

   13. AEAaron Epstein31:57

       ... which designers are used to today.

   14. RLRyo Lu31:58

       Yep.

   15. AEAaron Epstein31:59

       And you just kept telling it what to do to fix things-

   16. RLRyo Lu32:02

       Mm-hmm

   17. AEAaron Epstein32:03

       ... until it did it.

   18. RLRyo Lu32:04

       And if you want to look at code, it's here.

   19. AEAaron Epstein32:05

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

   20. RLRyo Lu32:10

       Mm-hmm.

   21. AEAaron Epstein32:10

       And start building something themselves.

   22. RLRyo Lu32:12

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

   23. AEAaron Epstein32:17

       Mm-hmm

   24. RLRyo Lu32:17

       ... like, when you start Cursor, like you're, you're faced with, like, three buttons, at least the, the version before.

   25. AEAaron Epstein32:25

       Mm-hmm.

   26. RLRyo Lu32:26

       Where it says, like, Open project, Clone repo, Connect to SSH.

   27. AEAaron Epstein32:29

       Yeah.

   28. RLRyo Lu32:29

       Like, you don't really know what the hell, like, those things mean.

   29. AEAaron Epstein32:32

       Yeah, many designers-

   30. RLRyo Lu32:33

       And then our new, like, landing page is just like, boom, you just start.
8. 36:10 – 42:17

   The Future of Designers and Engineers

   1. RLRyo Lu36:11

      like it's not even just for designers.

   2. AEAaron Epstein36:13

      Mm-hmm.

   3. RLRyo Lu36:13

      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.

   4. AEAaron Epstein36:21

      Right.

   5. RLRyo Lu36:22

      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.

   6. AEAaron Epstein36:43

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

   7. RLRyo Lu36:48

      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.

   8. AEAaron Epstein37:42

      It's like a new, more powerful tool-

   9. RLRyo Lu37:44

      Mm-hmm

   10. AEAaron Epstein37:44

       ... to use, and you need to learn how to use it effectively.

   11. RLRyo Lu37:47

       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.

   12. AEAaron Epstein38:00

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

   13. RLRyo Lu38:04

       Mm-hmm

   14. AEAaron Epstein38:04

       ... adaptive UIs and generative UIs.

   15. RLRyo Lu38:06

       Mm-hmm.

   16. AEAaron Epstein38:07

       Like, how, how do you think about that? Where do you think that's going?

   17. RLRyo Lu38:09

       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-

   18. AEAaron Epstein39:02

       Mm-hmm

   19. RLRyo Lu39:02

       ... do stuff with it. When it makes sense, I still want a to-do list. I still want a table.

   20. AEAaron Epstein39:08

       Mm-hmm.

   21. RLRyo Lu39:08

       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.

   22. AEAaron Epstein39:46

       The dream of the adaptive UIs is that they can show the right thing at any moment.

   23. RLRyo Lu39:50

       Mm-hmm.

   24. AEAaron Epstein39:51

       The problem with it is that how do you get comfortable and-

   25. RLRyo Lu39:55

       Yeah

   26. AEAaron Epstein39:55

       ... set user expectations-

   27. RLRyo Lu39:57

       Yeah

   28. AEAaron Epstein39:57

       ... around what it is? And it sounds like what-

   29. RLRyo Lu39:58

       Yeah

   30. AEAaron Epstein39:58

       ... you're saying is it's not about generating it different every single time.

Episode duration: 42:19