Flora Guo - How to accelerate your design career with AI

0:00How can we use AI to just really supercharge our own process as winners and biggers and designers? What AI is really great at is giving us a map of the territory. It's like when you're playing a video game and you see that there's clouds surrounding areas of the map that you haven't looked at, yeah, it's really good at blowing those clouds away. Basically now you have a very clear idea of what is possible, but it's still up to us to walk the terrain. Welcome to dive club, my name is Rid, and this is where designers never stop learning. Today's episode is with Flora Guo, who's had one of the more impressive career trajectories of anybody that I've interviewed on this show. She's currently the founding design engineer at Paradigm, and before that, Guillermo, the versatile CEO, personally DMed her to get her to join the team. So we're gonna do a deep dive into career growth, design engineering, what it's like being the founding designer at an AI native startup

1:00and a lot more. But I wanted to start this episode a little differently. So I asked Flora to share some of her favorite takeaways from the recent Tokyo design conference. Brian Bennett's basically brought 50 of the most interesting designers in the space, so people like Rio, Leu, Leu, Leu, Leu, Leu, Leu, Leu, and Gabriel Baldimia, a lot of your guests, and it was just such an incredible opportunity to learn from everyone across those two days. I'm someone who was always taking notes, whether it's online on my one side or physically on my notebook, and I just really wanted to create a place for these notes to live. And recently, Sam has been living in my head, red-free, thanks to some incredible artists. And I was also really inspired by one of my friends, Josephine Ong, who just ships such a cool portfolio with this internet-grade interaction. The same one that you'd see, maybe I'm like, it's better by Cosmo, it's like public dot query. And I just knew I had to sit down and build something out for myself, just to scratch that create a bit. So this is ultimately looking out of it.

2:01I was totally someone who wanted to go, couldn't make it, had incredible FOMO. And then you released all of your notes like this and I was like, oh, thank you. I made these little stamps for each talk that I had notes for, and three that really resonated with me are if I go into like this view where I can see them more as pages. Brian Loven did this incredible session about building software with AI. And I think it was just so incredible to share about how AI has been empowering this team at Notion with prototype playground. And just the way that we're moving at this industry, it's going from creating pretty images and artifacts that are just for show to designers being able to showcase interactions and really get into the nitty-gritty of how things will display and be experienced by the end youth. One that really stood out was Reo's talk on building the next cursor. Cursors are a tool that we all use, but just getting to see the philosophies

3:02that underlie what we striving with the team. So this idea of black box AI interfaces versus class interfaces. How can we really surface the intent that the user has? Also when we look back at the history of software with both like Bill Atkinson and Alan Kay, in the very early days, the people who were creating the designs and bringing it to life and code were one and the same. And because of that, we just had such a tight integration of their original intention and that people actually got to see an experience. Real quick message and then we can jump back into it. One thing that dive club has made abundantly clear to me over the last year is that the practice of design is changing and the old process of getting feedback just doesn't quite cut it in today's world. That's why I'm excited to announce that InFlight is officially in open beta. It's the feedback tool that I've always wanted and it's built for a world that moves at the speed of AI. So I can share my prototypes, give context and video walkthroughs and InFlight makes it easy to get the exact feedback that I need to move forward,

4:05whether it's voting on directions or maybe even getting the green light to ship a new idea. And all of this is available in a single link that I can drop into Slack or maybe even share with power users to test out a new prototype. I use InFlight every day and it's totally transformed the way that I share work. So I'm excited for you to try the product and if you ever want to jam about it, just email me at ridatinflight.co. If you've been listening to this show for a bit then you've heard me profess my love for Raycast multiple times by now. So I want to highlight a couple people who started using Raycast after hearing about it on dive club. The first is Rex Harris. He says Raycast is the tool that most shapes how he uses his computer and keeps him in flow. The next is Greg Hunton. He called it a life changing product and says every time he pulls a thread on something in Raycast it wildly deepens the power and experience of using his computer. I couldn't agree more and I can't recommend Raycast enough.

5:05It's totally free to start. Just head to dive.club slash Raycast to check it out now onto the episode. So there's one talk that really brought the FOMO for me which is Salayo's geometry of luck and he was teasing on Twitter and I just wish I was in the room. So what was your experience with that one? Maybe you could share a little bit of your notes there. I think this is definitely a talk that really resonated with me because Salayo proposed that luck is in something that you're born with or just falls in your lab. But it has a specific shape and a geometry. What that means is that like any other skill it's something that we can just learn about and invite more of into our lives. So he walked us through a few different examples. People like John Chapman or Johnny Appleseed. So someone who was from the outside looking in you're like, oh wow, he had so much pressience and like scattering these Appleseeds and planning these orchids before he was sellers came in to the States, but he was actually someone who just studied the maps where the river is going.

6:07What seasons will people be coming in and then just being so aware of like everything that was happening around him. Kind of like for us, you know, we see this constant deluge of contact coming in from back. He's being linearly aware of what the possibilities are. So that you're well positioned as someone to just really jump in and start exploring with these tools. People who move just perceive themselves to be lucky are also able to identify the opportunities as they come to them. They're creating a greater surface area of this luck whether it's being in rooms or creating those rooms where serendipity can happen. I think it's oftentimes just like one moment that can completely change your trajectory. This project in itself is almost an inception of that very idea because you've shared this thing that you enjoyed, you put it out on the internet. I don't remember how many impressions I got on Twitter, but it was a lot. It was like almost like a hundred thousand or something. People obviously enjoyed your work, this resonated with them. And that makes me wonder how intentionally you are

7:11stewing your own surface area for luck. And maybe you could talk a little bit about the role that sharing online has played in your own career journey. There's this quote that I often return to, but I think either Royal or Charles Eames, which is that the role of a designer is that of a very good host. And I think showing up in today's world where like you said, it is ultra competitive and there is a lot of stuff going on all the time with all these new tools. I think just really asking like what can we give? Whether it's holding space for an event or creating an artifact about something that we're excited about and want to share, really flipping the script of like, instead what can I ask this person, like what can I offer them? I think has been just something that I want to keep returning to in the ways that we show up online or in person for that matter, especially when we host events, inviting people into a space, thinking about like what can I gather them around? Like what is the intention that I can set around this? The ways that we host space online is very similar,

8:11whether it's gathering people around a common interest or like we're gonna screen a design film or whether we're inviting them to show off their own work. I think it's really figuring out like what are the threads that connect all of us together? Like what is the reason for us to be together in this space? And then figuring out like how can I pull this out of others as well? I am just incredibly grateful to the people that I've gone to meet online. People who start off, maybe you're just like seeing each other's projects. You're like, wow, this is really cool. Then you send them a DM and it kicks off maybe a conversation IRL over coffee or a phone call. And then it sparks either collaboration over projects or even roles when I was working as an independent designer for a couple of years. I would say the vast majority of my clients came in from Twitter and as someone who's just always loved experimenting, trying things out for the heck of it. It's been such a great way to meet people with similar interests. And even my curve role,

9:12it just felt very serendipitous with how Anna, my CEO, found me online on Twitter and when I was at her cell as well, it was just through conversations that started off in the end. So I think any designer who's building projects, it's just such an incredible time that we live in to get to share with it online. Can you go a little bit deeper into how intentionally are you nurturing that community that you built for yourself on Twitter? Because I think a lot of people look at where you're at and it's really inspiring, but also a bit of a black box in terms of how do you even get to that point where all of a sudden Twitter really is a very big deal for your career. I remember a way back in March of 22, that's when I first got onto Twitter and it was just me sharing things that I was really excited about, going to a retired L and being like, oh wow, I just learned about X thing in design. Like here my takeaways and just showing on being excited

10:13and really down to have conversations, I think just led one thing to another, like different roles that I think started off from a DM would evolve into in person things like hosting an event together or eventually working together. People can really feel the excitement that you have, whether it's through a project or through notes or something that you're hosting. So just creating things that are artifacts of what you love and what you're passionate about and putting it online. There's putting things out there on the internet and being a magnet for people who care and then there's also proactively messaging others and being the one that initiates, how much are you doing the latter? Cause I think that's like something that's so valuable and yet a little bit scary, probably for a lot of people listening. Whenever there's a designer who's work, you really admire. I love just like dropping a quick note of saying like, hey, I loved what you shipped. Here in particular is what really resonated with me. So I think whenever I get those in my inbox it really makes my day. I would say that hosting events is also a really great way

11:14to reach out to people and have them reach out to you as well. Whether it's hosting like a design film night or a design engineering PowerPoint night or something about agentic interfaces, I think creating like very specific things that you can offer people so like, oh, come into my home or come into my office. I'd love to host you or sending them thing that you think they'd enjoy. Just creates moments where it feels so much more natural. You're just talking to your new friend on the internet. I think the reason why I had so many follow up questions on this category of topics is I look at your journey and I see an incredibly steep trajectory. Like how fast you've been able to really insert yourself and build momentum in this space and now you're at paradigm and working this high profile role. It's really cool, right? And so like a goal of mine in this conversation is to help people find little pieces of that equation that they can use to reverse engineer your trajectory. So maybe we could even just talk a little bit more

12:17about what that journey has looked like starting with the design engineering internship at Versailles. Versailles is a company that I've looked up to for many, many years, even before what I knew and what a deployment was. I remember being on the homepage and thinking, wow, this is just so beautifully built out. I actually started this design engineering journey with B0. I remember back in 2024, I was looking around and seeing such incredible projects popping up in my timeline and having no idea where to start. I think the incredible thing about these tools is that you can go on with just an idea and start newling out what does the path look like to creating something that I'm really proud of. So I shared it off with the making shaders, the things that look like sunrise and then moving on to personal projects in B0 as well. One that I really had a lot of fun making was this idea with digital gift box.

13:17And I feel like this was the first project that I just sat down and was like, okay, today I'm gonna make something. I really love the idea of software as a gift. And I think B0 was just such an incredible way for me to translate that intention of creating like a space on the internet where I could package things up for my friends, whether that's images, links and then send it over to them. And sharing it on like this basically found its way to the B0 team and we would just like have these one-out conversations and eventually about a month later. So in January, G, DM, the on Twitter and it was like, haven't you ever heard about working at Bristol? No way. And that was really crazy. I had, you know, messaged him in the past, I think just saying like, hey, really appreciate you. Thank you for building B0. Like I'm having so much fun using it. Okay, that's really cool. I'm just gonna underline that for everybody listening. The fact that you de-end the CEO of for sale just to say thank you says so much

14:19about you and how you, like this is kind of what I was getting at earlier, right? Like that's a big deal. And then you know what probably happened? I bet he forgot. There's no way that he actually remembered. There's no way. But then he saw the project or maybe somebody sent it to him, he clicked in, he said, okay, maybe I'll reach out to this person and then at the top of that page was your thank you message. And it was like, oh, wow. Now I really want to talk to that person. So that's amazing. I just am shining a light on it. I think it's amazing just the way that you are positioning yourself in this community. I think you've also someone who's just incredibly proactive with reaching out to people online. So many of our hires at Versaul were just people that he saw like on the internet. And it was like, we need to talk to this person. He has an old club like Rashi or like G Brain, where she just like puts all these little notes and then it's like, okay, now what's recruiting? What's well, what? Just being the type of person that he is, he creates like so much their identity both after someone in the world as well. I'm sure you're freaking out. You get this DM. It's like, unbelievable, right?

15:19You end up joining the team. You spend this chunk of time earlier in your career surrounded by some of the best makers on the planet. And my assumption is you're probably thinking a little bit about who you even want to become in this space. So how did that experience shape your mental model for the type of designer that you wanted to grow into? I think it was such a surreal experience to get to work alongside people, James Clemmons, my tools, Sean, and Ronald. I think just seeing the level of care that they put into their work, whether it's crafting directions for a marketing site or really diving into the performance of the app, it really shows you that design engineering goes much deeper than the surface of how something looks. It's really having the context and the ability to take an intention and translate it into what the user is actually experiencing. At Paradigm as well, it's something we're always thinking about like, how can we make sure that the vision that we have is what people actually get to play with in front. And I think there's just so much to learn from the designers

16:22who are always picking up new technologies at tools as well, people who are just doing it because they're really curious. And something that really stood out to me about Ronald is how he's always cooking on side projects, whether it's devouring details or his personal websites. I think it's so inspiring to be surrounded by people who make for the love of making, not because you're looking to wrap a specific project or just get something done because that's the finish line. It's really appreciating design as this journey and this practice that never ends. And I think there's a lot of beauty and just walking that path. I was clicking through to Ronald's website randomly the other day and it was different, again, just a completely different everything. And the joke as designers as we can never find the time to update our portfolio. And this dude has a new personal website that is dripping in craft every six months. And you can tell it's like, it's not even about the end output for him, like it is that act of creating, which I don't know, has always been something

17:24that I aspire to grow into as a designer. It's just being somebody who creates because it is life-giving for my very soul, you know? I think especially when we're testing things out, just having people online that we can look towards like, oh, wow, they built this really cool project. They're talking about how they built a huge stack of these tools that they're playing with. It just gives us that extra notch to be like, okay, today I'm going to sit down and figure out how exactly this paper MCP words are like, to name it sit down and set up like slide code files. Just having, you know, role models like that, I think has been incredibly powerful for me. Before we move on, just take us through a few of your favorite experiments as an example of what it looks like to just create for the sake of creating and putting it out there on the internet just because I think your Twitter feed is beautiful. So I don't want to move on quite yet. One that I thought was really silly was my friend's favorite movie is Wallace and Gromit and I wanted to make it just a little, I think you could play with on his home screen,

18:24which was, you know, his favorite character, which is others, McGraw. And, you know, having little things of the plot details, this is just something that more of like a visual artifact that you can hook up, you know, create like a 3D model and then create like a 3D model viewer and just give something to people as a gift. I think that's an idea. You're rosary with me. This is a project from way back when, where basically when I was starting off with making projects, I wouldn't really know how to approach it. So just a very simple web app that you take any idea and it breaks it down for you in terms of like, here are things that you might want to think about in the front end, like here, what you can learn about in the back end just to serve as more of a map maker for me. I think this was a project that I really enjoyed just returning again to this idea of software as a gift. Like, what are ways that we can create things that feel tactile and create things that you can send to people and to say, hey, this made me think of you. Recently, what I really love as well has been,

19:26like, what are ways that I can play with things like animations, whether it's in a product or the Tokyo project. It was really figuring out like, what are cool effects I can play with. This one, I really have to shout like Daniel Pizzo, you put out this CSS like little snippet of, how can we create these like 3D moving, I guess 3D infinite canvas to explore like things come about you. And when I was playing with the 2D canvas as well, I think this is experimenting with like performance, Maxim Peckle with a friend who's just incredible design engineer and you know, I sent it over to him, he's like, oh, by the way, if you change the CSS class, the transform, it'll be a lot more performant. So I think I'm just always playing around with like, what are new things that have been sitting in my cache? And I now want to translate into a project that I'm actually working on. It's clear that you're learning a ton about, even just front end, you know, like just, the more you build your ideas,

20:26I'm seeing a lot of examples of like little technologies or you had that 3D render for walls and grommet kind of thing like, I have no idea how that works. You know, I'm putting your figuring it out for each individual project and it's obvious that those are helping you reach that next ladder of learning, which then kind of makes me wonder, like where was the starting point for all of this? Like how much technical understanding did you have when you first opened V0 and then maybe we can use that as a launching point to understand what some of those mile markers of understanding have been for you? I remember when I first started taking around with V0, I had like a very basic grasp of HTML, CSS, JavaScript. I'm also someone who loves speaking out internet courses. One was UI 101 by Mariana Castillo. Oh, cool, yeah, I went to that. I loved how they walked me through like, here's a component, here's how you translate it, just HTML and CSS and a little bit of JavaScript. And eventually along the way, I was reading a lot of react documentation and try to figure out like, ah,

21:27when I react free words, what's next to us? And the way that I think about it is that there's always a minimum viable amount of learning that you need to get you to the next step and then you backfill a lot. I think what AI is really good at doing is giving us artifacts, but they're not necessarily grounded in understanding of the system, which I think can be really great with making prototypes, a little one-up experiments, but the moment you need to debug something, you're like, oh man, I don't even know where to start. And I think that's where, you know, it's really helpful to push yourself to feel like you don't have a complete grasp with these tools and then step back like, okay, what do I need to zoom out in? Or what do I need to zoom out on and really deepen my understanding of now? For me, I know when I started off playing around with these different tools, I just didn't grasp how components should be structured. Like when should we break things down into modules or when can we pass down props versus sharing context?

22:31And I think just learning by building and like learning by asking has been such an incredible way, both like looking at reference material online and just, you know, asking your friends who might be good engineers or people who have done it before. There's a tension that I think a lot of people experience that hits on some of the things that you're talking about where it's like, how much do I actually invest in my own knowledge that like existed in my brain? Maybe some of that is syntax, you know, like code level knowledge versus just improving the way that I work with AI and maybe I abstract a lot of the details but I'm gonna focus all my attention on that front and with everything changing, you know, that's like an interesting spectrum to think about, like how you view learning and where you wanna concentrate your efforts. How do you think about where you wanna fall on that spectrum? For me, I think this is something that I experienced very acutely last year because I was making a bunch of personal projects, I'm like, oh, cool, like, look, it's a demo,

23:31but when it actually came down to debugging something if I was playing like with a map API and all of a sudden it wasn't loading well or everything's crashing, I just felt like I didn't have the necessary foundational knowledge to like actually hone in and dive deep into the levels of implementation. What AI is really great at is giving us a map of the territory. It's like when you're playing a video game and you see that there's like clouds surrounding areas of the map that you haven't looked at, yeah, it's really good at blowing those clouds away. Basically now you have a very clear idea of what is possible, but it's still up to us to walk the terrain. It's one thing to see what we can make and another thing to understand it in its full entirety. And I think with AI, we're also moving up the layers of abstraction. So we're not writing every function by hand, like no one's doing that. But the more context that you do have about how it works under the hood, so how react works, how our props being passed through

24:32were much better equipped to actually debug and build things our resilient. It depends on the level of abstraction that we're working at. So if we're, say someone who's working with a very strong team of engineers, what's most helpful for them is maybe like here is a prototype in code of like exactly how I want it. And the engineer is, you know, hulking up all of the detail for you. Maybe they sort of with PR that's just like the skeleton of like all the API calls and how the backend talks to the front end. And then as a designer, you can go in and like polish everything using Cloud Code and make sure that it's just exactly how you want it in terms of the micro interactions and the animations. Or if you're someone who wants to be deeper down in terms of implementation, like understanding how should this component be structured to be the most performant? I think really just going back to the basics and studying has been like something that I have returned to much more lately as well.

25:34There's one question that I can't stop asking myself. What if companies apply to talk to you rather than the other way around? And that question is the foundation for the all new dive talent network. And it's working, like right now I'm helping many of the most exciting startups that I know to hire the designers and builders who listen to this show. So if you're curious what might be out there and maybe you want to get on my list or maybe you're even looking for your next design hire, head to dive.club slash talent to join today. You're someone that takes learning seriously. Just listening to your talk, that is something that's very clear to me. So I want to ask a little bit of in the weeds question here, which is, if you would throw up how you work with AI on a daily basis when coding and you look at the version of yourself six months ago versus the version today, where do the biggest deltas exist? I think one of the biggest differences

26:34has been creating explainers as I go with cloud. For example, in the past, I'm not even about how we act works with React hooks. I would be building it to put in and think like, oh wait, this is totally something that can be abstracted out into its own custom hook. So then I would pull up some documentation, have a conversation with cloud, and at the end say like, okay, what are the key points that we should remember for next time or even just for my own learning? Because with like skill files, you can give cloud context, but I also think about how as we work with AI, these mental models that we're building up, like skill.md, full.md, it really encourages us to think about like, what are ways that we can build up our own context or what are ways that we can define our own invariant. So something that I really love doing is like, as I see like, I've tried something new or I learned something I didn't know before, I'll like quickly write out the work down file and just see that for next time for my own reference. And like sometimes I'll post these notes to my website, but just creating artifacts that I can continually return to. I think that's one of the biggest remarks.

27:36Is there an example that you posted to your website that we could look at? Should we go into notes? I remember like Monterey Post is something that we use a lot every cell, like everything that you see from the VERSEL marketing website to the app to all the ship conference websites is hosted in this like massive repository called front. And I remember, you know, poking in for the first time and I was like, wow, there's so many subdirectors. And for my own personal website, it's hosted on index3sapp, but I wanted to create like a shared component system that I could use cross projects. Treating out like, how do I do that? Where it's turbo repo, like how do I set this up? And then debugging things and just writing down notes for next time as well. I think that's been really helpful. I think the part of this that actually is the coolest is just the timestamps. Like how often you are contributing notes from your own learnings to your own website. I love to think of them upside and sensibly living artifact. You know, being able to just jot things down if there's a cooling that you saw, something that you want to save for next time.

28:37I think just creating things that you can return to has been like such as the event I love. Any other mental models that influence the way that you collaborate with AI that you feel like you've refined over the last year or so that you think might inspire other people? I really love thinking about AI as infinitely patient to direct. I think it's one thing to ask for it to do something for me and not question anything about how it works or what assumptions it's building off of, but really adopting this posture of now we live in a time where I can ask any question and I can ask it to break it down into as fine of a fidelity as I need. I really encourage people to think about ways that they can use AI to scaffold their own learning and then to flesh it out by building projects trying to understand like what are ways that we can prompt ourselves to become better at learning? One of the ways that that inspires me is just looking at your own role right now. Like you are a design engineer and yet correct me if I'm wrong

29:40there's not like a traditional designer at paradigm, right? Like you are kind of the designer but you're also owning a lot of the front end. It's a journey that in theory a lot of people that are listening to this could go on. I actually think that I'm going on it myself maybe not as quickly on some of the engineering concepts but like I'm the designer but I'm just owning more and more of the front end. It can be scary you know for people who have had a code of version historically and yet the blueprint and some of the ways that you are leaning on the AI and leaning into your own curiosity I think is ultimately like that's the scaffolding that allows people to progress in this direction which even just from the comments and people listening to this show I can tell is inspiring like it's a journey that a lot of people want to go on but they're like trying to figure out like what are the right footholds to grab on my own journey. At paradigm I'm very very lucky to work alongside some extremely experienced and just knowledgeable engineers like Rikansh, our lead front end engineer in Jiren or CTO

30:40I think I'm always learning from them and as someone who still feels relatively much earlier in my engineering journey I think a lot of it has been figuring out as someone who's feeling out this design role at paradigm what does it look like for me to be able engineers who are working across older layers of the fact versus like what are PRs that make the most sense for me to make myself. I think it's really figuring out like what is the right level of abstraction and boundary to straddle and for some designers you know they really just want to tumble deep into how things work and I think some designers are incredibly skilled at just spitting out this exact vision that they have and then working closely with engineers or whoever they're working with they're bringing exactly to line. Can we talk a little bit about your practice maybe we could even look at recent release or even just hypothetically how you work on something that feels a little bit more ambiguous like how much are you exploring in code how much are you owning like all of the front end implementation

31:42details and what are the steps in between like for somebody that can reach for really any type of tool how do you think about the way that you work and maybe if there are certain ways that that has evolved over the last six months even. I think something that we are in the process of figuring out or what are the intermediate artifacts that you can collapse and what are the things that you should spend your time like really figuring out higher fidelity versions of and sometimes that doesn't even look like a string it's like sitting down with the team and having a conversation of like what is the right mental model. So for example at paradigm we recently shipped a workflows feature and for us notes figure out how do we define the primitives of workflow it's zooming all the way back out to like asking what are the objects that we're concerned with here like what defines a workflow what are the workflows that users are building out and then from there like what are the integrations that we want to have like what are the actions that we want to have and I think it's so important to really be aligned at a conceptual level before we even start moving

32:44into like visual experiments and prototypes because I think one trap that we can fall into as designers is coming up with like a bunch of options and then picking one too early I think it's what figuring out like what is the right thing to create when so paradigm once we're aligned on like what exactly to make then we can hop into through like cloud code or Figma and I recently been playing around with Tadeber a little bit as well to just like put down a bunch of screens sometimes in varying levels of fidelity like sometimes all you need for a meeting is to like draw things even as rectangles to be like conceptually like here's the dialogue that I want and then progressively getting just like more alignment as a team before you move into like a coded up prototype something we recently played with with what are ways that we can show this like once the civic workflow and then working with our engineers put up like prototype PRs playing around testing them and eventually converging into what we seem

33:46for all today for something like the workflows I'm just going to ask you to even go more specific into what were the main types of artifacts that you're exploring like once you were aligned with the team what were those first few visual artifacts that you made and why for me I still like to use Figma to you know visualize what are the different ways that we could display this interaction and then sometimes what I like to do as well is like take a few of the versions I'm working with and they'll get them into variant UI and to see like other ways that I could explore this and what I really love about variants product is that it works as a scrolling feed so once we've like defined here the concerns of what we need to see in this interaction like there might be a pattern that like I completely do not have in my realm of understanding and then just thinking like oh okay like that's interesting like why what might be a fitting use case for this because I think it's understanding like what should

34:49the user be doing and then like what are the different four factors that can serve this up in the interaction now so after we play around with some kind of like static shots of like okay I want this fun to open up like this entry toy and to overflow dialogue then it's playing with a prototype that can either be in cloud code directly in our repository or sometimes we have people in the team who are more product focused and like to play around with other tools like directly in cloud to just show the interaction that they're thinking about and we all take like those food recordings and like little snippets and give each other like get out PR links to just test them on staging and then see what feel right before eventually we're like okay like working backwards like this is how we wanted to feel in the final version and and now we have like this little graveyard of PR links of Trilletown. Let's talk a little bit more about your role as the designer start up

35:49very AI native product a lot of unique challenges there so talk to us a little bit about how even the nature of the product has shaped your design practice. So paradigm we work on a way for new to prompt basically a thousand agents at once. There is this interface of the spreadsheet which people are so familiar with as knowledge records but it's just a completely different model thinking we're in the past you know you define a formula and the spreadsheet fills it out for you but now we see that as a way of interaction with this swarm of agents right so like how can you define a set of steps in your workflow once and then have these columns each columns is a prompt executed now across like tens or hundreds or thousands of rows. So for us something that we're always thinking about is scale and how can we bring this to an interaction that like feels good when you have like 200 agents versus just 20 running at once and I think a really

36:51great way that we've been offering it as well as just thinking about like what are things to parallel life. So for me like I love building lists I love collecting lists whether it's resources I love or learnings that I have I'll put them in like one column and then I'll create prompts to say like oh what are other ideas I can pull up related to this or what are other resources that you would recommend for example if I'm trying to learn animation like let's first build up a list of like animation resources and then like what are threads I can keep pulling and if really using the AI tool as a way to prompt myself to figure out like okay where do I want to move next. I want to double click on the scale piece for a second like what are some of the design possibilities that you find yourself exploring or reaching for to solve that type of problem. One thing that we've really held on is what are ways that you can represent things at scale and diverse structure matter and when we were trying to this idea like grids at rows and columns and makes a lot of sense because

37:55this is a paradigm that people are already familiar with so for us it's figuring out like if I want to have something at scale what does it mean to first like generate that list of items so like using an agent to scrape the web and help me build this list and then from there it's like what do I even need to extract or like what is the most optimal way of like interacting with this like body of knowledge now. So for us like something we're referencing is looking at like other very data heavy products so like what are ways that we've represented like vast flows of data that pass whether it's in a spreadsheet or you know maybe at some point looking at graphs and documents and he's like that. I think it's identifying with structured idling what are the invariants. What are ways that you can pull out something that is constant across all of them whether it's like a field that you want to have or a shape of the data that you can define so that AI can really help you build it out as you scaffold it. You're working on very cutting edge tech workflows,

38:58mental models like just the way that you are empowering humans to work is so different than what we're used to even as a society where my assumption is given your role as a designer how to start up you're having to keep a bit of a pulse on like what else is happening around and how do we think about the ways that this shapes our own product road map and patterns to pull from. I know the answer is scroll Twitter but like go a little bit deeper into what you're doing as a designer to healthily stay up to date with everything's happening in the world and hopefully being able to like identify the signal from the noise. You know Twitter can definitely get very overwhelming but I think being a pulse check on here's like what everyone's been talking about putting it on my list of like things to explore and then for me a really great filter is just

39:59chatting with my designer friends or design to your friends like I have a backlog of products and tools I want to try and just comparing notes with each other I think makes it a much more fun experience to just do it together as a collective or as a community. I really love in person events for this whether it's hosting them myself or going to ones of my friends put together it just creates places for people to share little snippets of the curiosity and demo to each other as well like here's something that makes me really excited and that I've been diving down this rabbit hole lately. I think sometimes it's a matter of picking one thing that you want to dive down into for a weekend or two and just trying to block things out for that period while you choose to go deep so staying broad keeping all this context and then what's something really got to your attention you're like okay now I have to build it right now I have to try it out and it's just continuing to return to like go broad and then go deep and repeating that process. I did that yesterday with a friend just kind of catching up we hadn't talked in I don't know six 12 months or something it's

41:00another designer and he was sharing his workflow with pencil and I was sharing my workflow with paper and it was so interesting to just see the different things that he was tinkering with and experimenting with and both of us had arrived at this similar point where it's like gosh in the last two months how I'm exploring on a canvas is fundamentally different than it's ever been at any point in our career and we were both so excited about it and then he's like have you tried this like no I'm like oh have you tried conductor he's like no and he's just so valuable to have those little sessions with people because I feel like we're kind of all just blazing around trail and figuring it out right now. Absolutely yeah I think getting to share your like personal workflows with friends is just such a fun thing to do because you can dive into like wow like this project that you made recently like how did you do that like what are the tools that you're playing with and continuing to like have this demo culture I think it's so powerful as well like in Canada and I guess we'll why now we have to think of Chicago Cup where basically people get together every Sunday they cohort for three hours and then at

42:02the end people demo what they've been working on. I think green spaces where you can foster that curiosity to make things like not necessarily for work or for a specific project just having dedicated space where you're carving out to be like okay today I'm gonna light something new today I'm gonna make something new and having that just because a lot of the process I think is such a powerful thing to do. I want to connect back to a lot of the things that you were talking about earlier where like when you were scrolling your Twitter feed it's so much of you just saying I learned something new here's what it is you know and people really like that really resonates with people and there's totally this moment in time like gosh if you're listening and you're inspired by your journey on social media and putting yourself out there in the community this is the moment where you could do something similar where you just explore and tinker and try different tools and try different workflows and like what if I did this instead or what if I use this as a starting point and then just dumping your takeaways and your experience like people are hungry for that

43:02right now even my own journey like that's kind of how I started it was back in like 2019 when figment was a little bit newer and it was becoming a much more technical product and a lot of more powerful like functionality component props and I would just explore I would just get up and I would just do weird things with components and then make it you know tweet about it and I would just do it again and again it was fun and I think that same opportunity is definitely present in today's world just because everything's changing so quickly your things for the fun of it is probably the most powerful thing and just always keeping that spirit off the line and building like how does the shape of our tools shape us as the users of them like what are the interactions that they're affording or the ways of thinking that are really becoming embedded in our psyche something you really love is the cloud code like ask user a tool or basically you can use AI as an interviewer to really help you crystallize your own thoughts so I think with AI there's like two paths they can go down one in which you're kind of like okay just like do this when we

44:03eat two six we say six we six and you're caught in this like infinite loop where you feel like you're not really breaking your ground or you're hitting the same bugs again and again but I really encourage us to flip it and be like ask how can we use AI to help us still the right mental models that we need like to first figure out like what is the level of the of absorption that I should exist at and what is the necessary context I need to acquire in order to be effective here whether it's you know actually going into react and understanding how does this component work like how should components be structured how should I be writing these prompts and the way it's passing them down to you know if I'm working with like a shinder or something like how much math do I really need to know I think with AI we're getting much better at figuring out what is a minimum viable level of knowledge I need to make something but then like what is a null level of knowledge I need to become someone who actually feels well versed in this specific technology or the specific tool and I think for everyone you know it really depends on the context

45:05of like whether you just want to create a fun demo or a fun type or whether this is a product that you want to sustain over time yeah it goes back to what you're talking about in terms of viewing AI as the ultimate personalized tutor you know exactly actively finding ways to lean into that rather than just to accomplish your next goal and then your next goal absolutely it's like how can we use AI to just really supercharge our own process as winners and bickers and designers I feel confident in saying that you have supercharged a lot of people's process listening because the way that you think about these tools but also just the way that you approach your own journey and your hunger for learning and experimentation it's super inspiring for us so I really really appreciate you coming on and sharing it with us today yeah thank you so much for it it's been such a pleasure before I let you go I want to take just one minute to run you through my favorite products because I'm constantly asked what's in my stack framework is how I build websites genway is how I do research granola is how I take notes during crit jitter is how I animate my designs loveable is how I

46:10build my ideas in code mobin is how I find design inspiration paper is how I design like a creative and raycast is my shortcut every step of the way now I've hand selected these companies so that I can do these episodes full time so by far the number one way to support the show is to check them out you can find the full list at dive dot club slash partners