One Designer + AI. Hundreds of Deliverables. — Vincent Wendy, AI Engineer

All right. All right. Hello everyone. Hope you guys having a Hello everyone. Hope you guys having a Hello everyone. Hope you guys having a good time at the conference. good time at the conference. good time at the conference. So, before we start So, before we start So, before we start how many of you are actually uh how many of you are actually uh how many of you are actually uh designers? Like a product designer. Hey, designers? Like a product designer. Hey, designers? Like a product designer. Hey, one hands and another. Okay. one hands and another. Okay. one hands and another. Okay. And how many I assume that the rest of And how many I assume that the rest of And how many I assume that the rest of you are engineers? Is that correct? you are engineers? Is that correct? you are engineers? Is that correct? Yeah, pretty much. Okay. Yeah, pretty much. Okay. Yeah, pretty much. Okay. So, today's talk is a non-technical So, today's talk is a non-technical So, today's talk is a non-technical talk, but more of a real-world talk, but more of a real-world talk, but more of a real-world experience how I created the design for experience how I created the design for experience how I created the design for AI Engineer this conference and AI Engineer this conference and AI Engineer this conference and our other past conference as well and our other past conference as well and our other past conference as well and how AI has helped me. And so, the talk how AI has helped me. And so, the talk how AI has helped me. And so, the talk today is one designer plus AI, which is today is one designer plus AI, which is today is one designer plus AI, which is me as the designer, me as the designer, me as the designer, and hundreds of deliverables. and hundreds of deliverables. and hundreds of deliverables. All right, let's start. All right, let's start. All right, let's start. So, my name is Vinson Weng. I am a So, my name is Vinson Weng. I am a So, my name is Vinson Weng. I am a senior creative designer at AI Engineer. senior creative designer at AI Engineer. senior creative designer at AI Engineer. And at AI Engineer, it's a very small And at AI Engineer, it's a very small And at AI Engineer, it's a very small team. So, we only have around 12 people team. So, we only have around 12 people team. So, we only have around 12 people to 15 people at the moment. And to 15 people at the moment. And to 15 people at the moment. And everyone has been doing their own thing everyone has been doing their own thing everyone has been doing their own thing and and and I think AI has been like has been a I think AI has been like has been a I think AI has been like has been a really helpful way to like helping really helpful way to like helping really helpful way to like helping everybody doing everything.

everybody doing everything. everybody doing everything. And And And at if for if an at this scale at if for if an at this scale at if for if an at this scale we have a problem, obviously, right? we have a problem, obviously, right? we have a problem, obviously, right? And the problem is the scale problem or And the problem is the scale problem or And the problem is the scale problem or I would call the challenges. I would call the challenges. I would call the challenges. And how to overcome it? And how to overcome it? And how to overcome it? It's basically automation and we get to It's basically automation and we get to It's basically automation and we get to that in the later part of this talk. that in the later part of this talk. that in the later part of this talk. So, when I prepared this talk, we only when I prepared this talk, we only expected 6,000 attendees and now it's expected 6,000 attendees and now it's expected 6,000 attendees and now it's 7,000. Well, 7,000. Well, 7,000. Well, good for us. good for us. good for us. And then we have 140 sponsors. More. And then we have 140 sponsors. More. And then we have 140 sponsors. More. 140 plus sponsors. And then 300 plus 140 plus sponsors. And then 300 plus 140 plus sponsors. And then 300 plus speakers, 600 plus sessions, and one speakers, 600 plus sessions, and one speakers, 600 plus sessions, and one designer. designer. designer. And everybody needs And everybody needs And everybody needs every designs, right? Like every single every designs, right? Like every single every designs, right? Like every single thing needs design. Sponsor needs thing needs design. Sponsor needs thing needs design. Sponsor needs assets, speaker needs graphic. assets, speaker needs graphic. assets, speaker needs graphic. You need sign it so you don't get lost. You need sign it so you don't get lost. You need sign it so you don't get lost. And And And this is basically what we do, what I do. this is basically what we do, what I do. this is basically what we do, what I do. So, from stickers, do you like your So, from stickers, do you like your So, from stickers, do you like your swag, your stickers?

swag, your stickers? swag, your stickers? Well, I hope you do because I create Well, I hope you do because I create Well, I hope you do because I create that design, too. And that design, too. And that design, too. And to a landing page, to a landing page, to a landing page, speaker announcement, track mascot, all speaker announcement, track mascot, all speaker announcement, track mascot, all the stuff that you see, the stuff that you see, the stuff that you see, most of the stuff that you see most of the stuff that you see most of the stuff that you see here, from a sign it to a here, from a sign it to a here, from a sign it to a digital sign it, landing page, digital sign it, landing page, digital sign it, landing page, everything is a deliverable. everything is a deliverable. everything is a deliverable. And a thousand details means a thousand way a thousand details means a thousand way to fail, right? to fail, right? to fail, right? Because I'm missing sponsor logos, going to be a I'm missing sponsor logos, going to be a huge issue. And speakers that have a huge issue. And speakers that have a huge issue. And speakers that have a wrong schedule, also a huge issues, wrong schedule, also a huge issues, wrong schedule, also a huge issues, right? And it seems impossible to handle right? And it seems impossible to handle right? And it seems impossible to handle that many kind of deliverables, but that many kind of deliverables, but that many kind of deliverables, but yeah, meet my design team. yeah, meet my design team. yeah, meet my design team. So, it's me and Devin, GPT, and Figma. And right now we are at the stage where And right now we are at the stage where tools isn't the like it's not a problem tools isn't the like it's not a problem tools isn't the like it's not a problem anymore, but having a real problem is anymore, but having a real problem is anymore, but having a real problem is our advantage.

our advantage. our advantage. So, for example, So, for example, So, for example, when someone asked me, "What inspired when someone asked me, "What inspired when someone asked me, "What inspired you when designing in AI engineer?" you when designing in AI engineer?" you when designing in AI engineer?" I don't know the answer back then, but I don't know the answer back then, but I don't know the answer back then, but after I think about it, it's actually a after I think about it, it's actually a after I think about it, it's actually a problem that inspired me to like problem that inspired me to like problem that inspired me to like designing in this AI engineer. And we'll designing in this AI engineer. And we'll designing in this AI engineer. And we'll get to that in the latter part of this get to that in the latter part of this get to that in the latter part of this talk. talk. talk. So, So, So, have you guys seen the talk by Simon have you guys seen the talk by Simon have you guys seen the talk by Simon Wilson like in 2025? Wilson like in 2025? Wilson like in 2025? >> Yeah. >> Yeah. >> Yeah. >> Yeah, and it's pretty interesting, >> Yeah, and it's pretty interesting, >> Yeah, and it's pretty interesting, right? He asked to right? He asked to right? He asked to He asked every LLM to create He asked every LLM to create He asked every LLM to create an a vector file, which is basically a an a vector file, which is basically a an a vector file, which is basically a pelican riding a bicycle. pelican riding a bicycle. pelican riding a bicycle. And it is basically to test and I tested And it is basically to test and I tested And it is basically to test and I tested again and it's still doing this for the again and it's still doing this for the again and it's still doing this for the basic model. basic model. basic model. And it's not usable for me as a And it's not usable for me as a And it's not usable for me as a designer. But as a designer, we have to designer. But as a designer, we have to designer. But as a designer, we have to think outside the box. think outside the box. think outside the box. And we could simply ask ChatGPT create a And we could simply ask ChatGPT create a And we could simply ask ChatGPT create a still image like a PNG for a pelican still image like a PNG for a pelican still image like a PNG for a pelican riding a bicycle and then I can riding a bicycle and then I can riding a bicycle and then I can vectorize it on on Figma.

vectorize it on on Figma. vectorize it on on Figma. And we can ship that now. And we can ship that now. And we can ship that now. So, we have to think outside the box So, we have to think outside the box So, we have to think outside the box here here here regardless the capabilities of the LLM. regardless the capabilities of the LLM. regardless the capabilities of the LLM. And And And So, how to solve this scale problem, So, how to solve this scale problem, So, how to solve this scale problem, right? Basically five five things. So, Basically five five things. So, foundation first, reusable designs, foundation first, reusable designs, foundation first, reusable designs, automated workflows, automated workflows, automated workflows, validated output, and also remove validated output, and also remove validated output, and also remove frictions. frictions. frictions. The foundation is definitely the core The foundation is definitely the core The foundation is definitely the core part that we need to set up right. Like part that we need to set up right. Like part that we need to set up right. Like the design system, typography, colors, the design system, typography, colors, the design system, typography, colors, components, like other stuff. components, like other stuff. components, like other stuff. And once this is set up, like for And once this is set up, like for And once this is set up, like for example, when we create the website, example, when we create the website, example, when we create the website, it's all set up within this thing. it's all set up within this thing. it's all set up within this thing. And yeah, this is just an example. Like And yeah, this is just an example. Like And yeah, this is just an example. Like we have the colors, primary, and then we have the colors, primary, and then we have the colors, primary, and then also the accent colors, also the accent colors, also the accent colors, the typography, the typography, the typography, and also the tagline, all the other and also the tagline, all the other and also the tagline, all the other stuff. stuff. stuff. And And And also, have you guys Are you guys also, have you guys Are you guys also, have you guys Are you guys familiar with the atomic designs?

familiar with the atomic designs? familiar with the atomic designs? So, yeah, my previous background is I'm So, yeah, my previous background is I'm So, yeah, my previous background is I'm a product designer. So, I'm pretty a product designer. So, I'm pretty a product designer. So, I'm pretty familiar with the familiar with the familiar with the thing where we need to create a thing where we need to create a thing where we need to create a user-centric design and also like atomic user-centric design and also like atomic user-centric design and also like atomic designs, right? Where we create the designs, right? Where we create the designs, right? Where we create the smallest part possible and then smallest part possible and then smallest part possible and then combining it into like basically a LEGO combining it into like basically a LEGO combining it into like basically a LEGO pieces and then into a deliverables. pieces and then into a deliverables. pieces and then into a deliverables. And this is pretty useful in my job desk And this is pretty useful in my job desk And this is pretty useful in my job desk right now. right now. right now. So, once we set up all of those So, once we set up all of those So, once we set up all of those foundation, we basically need to create foundation, we basically need to create foundation, we basically need to create for example, we use Defont a lot. In at for example, we use Defont a lot. In at for example, we use Defont a lot. In at the office, we everybody use Defont. the office, we everybody use Defont. the office, we everybody use Defont. Everybody like Everybody like Everybody like abusing Defont for example. abusing Defont for example. abusing Defont for example. Yeah. And Yeah. And Yeah. And So, in this case, I just need hey, we So, in this case, I just need hey, we So, in this case, I just need hey, we use this desktop typography and this use this desktop typography and this use this desktop typography and this mobile typography because we know Cloud or like any other LLMs love to Cloud or like any other LLMs love to like throwing some random like throwing some random like throwing some random font size, right? And if we don't define font size, right? And if we don't define font size, right? And if we don't define it, it just delivering a slope like the it, it just delivering a slope like the it, it just delivering a slope like the previous slope.

previous slope. previous slope. And And And yeah. yeah. yeah. Typography, color and stuff and Typography, color and stuff and Typography, color and stuff and and then it comes to reusable design. and then it comes to reusable design. and then it comes to reusable design. So, once we set up it right, like the So, once we set up it right, like the So, once we set up it right, like the website is has the website is has the website is has the the branding to it, all the other teams the branding to it, all the other teams the branding to it, all the other teams on the AI engineer, like for example, on the AI engineer, like for example, on the AI engineer, like for example, the marketing teams the marketing teams the marketing teams can create everything basically. Like can create everything basically. Like can create everything basically. Like they can create an email design based on they can create an email design based on they can create an email design based on that. They can create a flyer, a that. They can create a flyer, a that. They can create a flyer, a document document document just based on the website because it's just based on the website because it's just based on the website because it's already defined already defined already defined like it defined early. like it defined early. like it defined early. And yeah, once you get the design, you And yeah, once you get the design, you And yeah, once you get the design, you can just rinse and repeat. can just rinse and repeat. can just rinse and repeat. For example, the mascot, it's all has For example, the mascot, it's all has For example, the mascot, it's all has the pretty much the same design and it's the pretty much the same design and it's the pretty much the same design and it's rinse and repeat. And if you already defining those things, you can already defining those things, you can basically like create one design that basically like create one design that basically like create one design that works for all. works for all. works for all. And this is the part that I'm most And this is the part that I'm most And this is the part that I'm most interesting to talk about, which is the interesting to talk about, which is the interesting to talk about, which is the automated workflows.

automated workflows. automated workflows. Before, for example, Before, for example, Before, for example, if you take a look outside the room, if you take a look outside the room, if you take a look outside the room, there's a schedule, right? The schedule there's a schedule, right? The schedule there's a schedule, right? The schedule for each and everyone. for each and everyone. for each and everyone. So, we used to do it manually on Figma, So, we used to do it manually on Figma, So, we used to do it manually on Figma, but now we use Devin for it. but now we use Devin for it. but now we use Devin for it. And And And let me show you. Hey. Hey. So, right now we just pull the latest So, right now we just pull the latest So, right now we just pull the latest data. I just asked Devin like, "Hey, data. I just asked Devin like, "Hey, data. I just asked Devin like, "Hey, I want this room I want this room I want this room at these days." And then we can just at these days." And then we can just at these days." And then we can just export it, download it PNG, and the data export it, download it PNG, and the data export it, download it PNG, and the data is all accurate, and then we can just is all accurate, and then we can just is all accurate, and then we can just ship it to the flash drive, and then ship it to the flash drive, and then ship it to the flash drive, and then put it on the screen. put it on the screen. put it on the screen. And And And it was like impossible before because it was like impossible before because it was like impossible before because the friction is just too much between the friction is just too much between the friction is just too much between the designers and the developers. the designers and the developers. the designers and the developers. We [snorts] cannot make things like We [snorts] cannot make things like We [snorts] cannot make things like pixel perfect because pixel perfect because pixel perfect because once we tell the designer, "Hey, this is once we tell the designer, "Hey, this is once we tell the designer, "Hey, this is the design." And then the design." And then the design." And then Sorry, the the engineers that created Sorry, the the engineers that created Sorry, the the engineers that created the design, for example. "Hey, I need the design, for example. "Hey, I need the design, for example. "Hey, I need this to be delivered." And then they this to be delivered." And then they this to be delivered." And then they don't create it pixel perfect, it's a don't create it pixel perfect, it's a don't create it pixel perfect, it's a lot of lot of lot of feedback loop, right? But with Devin, we feedback loop, right? But with Devin, we feedback loop, right? But with Devin, we just say, "Hey, just say, "Hey, just say, "Hey, can you make this more accurate?"

can you make this more accurate?" can you make this more accurate?" We can just connect it to MCP, and then We can just connect it to MCP, and then We can just connect it to MCP, and then if it doesn't work, we can just always if it doesn't work, we can just always if it doesn't work, we can just always like like like give a spec sheet or something that give a spec sheet or something that give a spec sheet or something that can be defined like what's the spacing, can be defined like what's the spacing, can be defined like what's the spacing, what's the what's the what's the font size, etc. And this is what we do to for the speaker this is what we do to for the speaker announcement. So, announcement. So, announcement. So, we have 300 plus speakers, and it's we have 300 plus speakers, and it's we have 300 plus speakers, and it's impossible for me to like handle one by impossible for me to like handle one by impossible for me to like handle one by one, right? So, we create this thing, one, right? So, we create this thing, one, right? So, we create this thing, which is called which you can also which is called which you can also which is called which you can also access to speaker announcement, and you access to speaker announcement, and you access to speaker announcement, and you can also try can also try can also try it yourself. it yourself. it yourself. Like this one, for example. Like this one, for example. Like this one, for example. You can select it right here. You can select it right here. You can select it right here. And then you can also change your name. And then you can also change your name. And then you can also change your name. Well, that Well, that Well, that Yeah. For example, this you can change Yeah. For example, this you can change Yeah. For example, this you can change the name to whatever you want. And we the name to whatever you want. And we the name to whatever you want. And we also have the landscape mode also have the landscape mode also have the landscape mode which can be also loaded. If the speaker which can be also loaded. If the speaker which can be also loaded. If the speaker also have the headshot and all the also have the headshot and all the also have the headshot and all the details, it will automatically export. details, it will automatically export. details, it will automatically export. And we also have the trading cards And we also have the trading cards And we also have the trading cards which is surprisingly pretty popular.

which is surprisingly pretty popular. which is surprisingly pretty popular. And we have a different team. And this And we have a different team. And this And we have a different team. And this is all pixel perfect. is all pixel perfect. is all pixel perfect. All right. For example, this one. All right. For example, this one. All right. For example, this one. This is inspired by TBPN, so Yeah. And how do I deliver this in pixel Yeah. And how do I deliver this in pixel perfect? Let's jump into it. perfect? Let's jump into it. perfect? Let's jump into it. So, So, So, the process here is the process here is the process here is before before before when I start my career as a product when I start my career as a product when I start my career as a product designer, it used to be just designer, it used to be just designer, it used to be just okay, we need to research, we need to okay, we need to research, we need to okay, we need to research, we need to build product like design thinking in build product like design thinking in build product like design thinking in general, right? And then feedback loop general, right? And then feedback loop general, right? And then feedback loop and stuff like that. But right now, it's and stuff like that. But right now, it's and stuff like that. But right now, it's it's just outdated for me. Like in my it's just outdated for me. Like in my it's just outdated for me. Like in my case, case, case, we just go to Slack, we just go to Slack, we just go to Slack, Figma, and then send it back to Slack Figma, and then send it back to Slack Figma, and then send it back to Slack because Devin or Devin live in Slack, because Devin or Devin live in Slack, because Devin or Devin live in Slack, and then ship all the things that he and then ship all the things that he and then ship all the things that he need. need. need. >> [snorts] >> [snorts] >> [snorts] >> Like for example, if we can connect the >> Like for example, if we can connect the >> Like for example, if we can connect the MCP or also the MCP or also the MCP or also the spec document, which is for example the spec document, which is for example the spec document, which is for example the spec sheet like this, spec sheet like this, spec sheet like this, which is which is which is uh plugin in Figma if you interested.

uh plugin in Figma if you interested. uh plugin in Figma if you interested. It's free and it's basically give an It's free and it's basically give an It's free and it's basically give an annotation to the PDF. annotation to the PDF. annotation to the PDF. And And And yeah, all designers don't name their yeah, all designers don't name their yeah, all designers don't name their layers, so yeah, this is just like layers, so yeah, this is just like layers, so yeah, this is just like some random frame three, frame four, but some random frame three, frame four, but some random frame three, frame four, but the LLM will get it. the LLM will get it. the LLM will get it. And it's basically defining all this And it's basically defining all this And it's basically defining all this spacing, all this spacing, all this spacing, all this font size, and then all the font size, and then all the font size, and then all the colors and stuff. It's definitely going colors and stuff. It's definitely going colors and stuff. It's definitely going to help you develop a pixel-perfect to help you develop a pixel-perfect to help you develop a pixel-perfect product. product. product. And we also have just recently like today we also have just recently like today have uh photos which we have to create have uh photos which we have to create have uh photos which we have to create the thumbnail for its the thumbnail for its the thumbnail for its speaker, right? And then we ask Devin speaker, right? And then we ask Devin speaker, right? And then we ask Devin like, "Hey, who is this person?" And like, "Hey, who is this person?" And like, "Hey, who is this person?" And yeah, it kind of did. Like I make a yeah, it kind of did. Like I make a yeah, it kind of did. Like I make a Tinder kind of Tinder kind of Tinder kind of you know, detection you know, detection you know, detection if this is the same person or not. And I if this is the same person or not. And I if this is the same person or not. And I think it's pretty accurate. think it's pretty accurate. think it's pretty accurate. It's Jason Liu. Yes. It's Jason Liu. Yes. It's Jason Liu. Yes. And then we can use this to like And then we can use this to like And then we can use this to like for context. Like before, when we create for context. Like before, when we create for context. Like before, when we create the thumbnail, we have to search all the the thumbnail, we have to search all the the thumbnail, we have to search all the codes that photographer have and search codes that photographer have and search codes that photographer have and search it one by one and maybe by time it one by one and maybe by time it one by one and maybe by time if possible. But now we can just like, if possible. But now we can just like, if possible. But now we can just like, "Oh, this is Jason Liu. Download that "Oh, this is Jason Liu. Download that "Oh, this is Jason Liu. Download that photo." And then we can paste it into photo." And then we can paste it into photo." And then we can paste it into the thumbnail, right? And it's pretty the thumbnail, right? And it's pretty the thumbnail, right? And it's pretty amazing. I mean, the world that we live amazing. I mean, the world that we live amazing. I mean, the world that we live in right now is actually like the state in right now is actually like the state in right now is actually like the state for me as a designer is already at the for me as a designer is already at the for me as a designer is already at the peak because

peak because peak because what what else can you ask for, right? I what what else can you ask for, right? I what what else can you ask for, right? I mean, we already have things to mean, we already have things to mean, we already have things to automate, we already have things to automate, we already have things to automate, we already have things to create the design fast. create the design fast. create the design fast. Basically, all you need is a problem Basically, all you need is a problem Basically, all you need is a problem because once you have a problem that because once you have a problem that because once you have a problem that worth solving, you can worth solving, you can worth solving, you can basically solve anything. basically solve anything. basically solve anything. And back to my talk, I got sidetracked And back to my talk, I got sidetracked And back to my talk, I got sidetracked right there. right there. right there. Yeah. Yeah. Yeah. And then yeah. And this is also the And then yeah. And this is also the And then yeah. And this is also the amazing thing that we test. amazing thing that we test. amazing thing that we test. So, as you know, we have like hundreds So, as you know, we have like hundreds So, as you know, we have like hundreds of sponsors, right? Like 140 plus. And of sponsors, right? Like 140 plus. And of sponsors, right? Like 140 plus. And as you can see on the at the lobby, we as you can see on the at the lobby, we as you can see on the at the lobby, we have the banner with all the sponsors. have the banner with all the sponsors. have the banner with all the sponsors. And And And I basically tell Devin like I basically tell Devin like I basically tell Devin like "Hi, could you compare "Hi, could you compare "Hi, could you compare could you check if there are any missing could you check if there are any missing could you check if there are any missing logos in this graphic?" And the accuracy logos in this graphic?" And the accuracy logos in this graphic?" And the accuracy is 100% based on the test that I is 100% based on the test that I is 100% based on the test that I do. So, do. So, do. So, which is pretty well. And we use the which is pretty well. And we use the which is pretty well. And we use the same thing for the same thing for the same thing for the T-shirt that you got for your swag.

T-shirt that you got for your swag. T-shirt that you got for your swag. And yeah, surprisingly, Devin knows how And yeah, surprisingly, Devin knows how And yeah, surprisingly, Devin knows how to like visualize things, right? Like to like visualize things, right? Like to like visualize things, right? Like how to detect things visually. how to detect things visually. how to detect things visually. And that is very surprising because And that is very surprising because And that is very surprising because as a human, we can like give errors. Oh, as a human, we can like give errors. Oh, as a human, we can like give errors. Oh, turns out there's one small something turns out there's one small something turns out there's one small something that is missing. But with this kind of that is missing. But with this kind of that is missing. But with this kind of thing, we can like double-check. So, thing, we can like double-check. So, thing, we can like double-check. So, human plus AI, combine it, human plus AI, combine it, human plus AI, combine it, well, you got your own QA team. well, you got your own QA team. well, you got your own QA team. And then remove fiction. And then remove fiction. And then remove fiction. So, this is just uh the way of thinking. So, this is just uh the way of thinking. So, this is just uh the way of thinking. So, as a designer, we have to think So, as a designer, we have to think So, as a designer, we have to think as a user, not as a designer, all right? as a user, not as a designer, all right? as a user, not as a designer, all right? Because every user has its needs. Because every user has its needs. Because every user has its needs. You can walk through the for example, You can walk through the for example, You can walk through the for example, the map plan here. So, basically, the map plan here. So, basically, the map plan here. So, basically, I'm imagining myself as an attendee to I'm imagining myself as an attendee to I'm imagining myself as an attendee to go to the registration, go to the go to the registration, go to the go to the registration, go to the see the wayfinding and the QR code and see the wayfinding and the QR code and see the wayfinding and the QR code and then all the stuff. Basically, then all the stuff. Basically, then all the stuff. Basically, everything needs to be connected so you everything needs to be connected so you everything needs to be connected so you guys don't get lost and knows how to guys don't get lost and knows how to guys don't get lost and knows how to find your rooms and find your rooms and find your rooms and other stuff.

other stuff. other stuff. And And And the real job is handling exceptions. the real job is handling exceptions. the real job is handling exceptions. So, for example, oh, I have Yeah. So, for example, oh, I have Yeah. So, for example, oh, I have Yeah. >> [snorts] >> [snorts] >> [snorts] >> For example, >> For example, >> For example, um um um there is a schedule update, all right? there is a schedule update, all right? there is a schedule update, all right? And And And when we create this thing, it doesn't when we create this thing, it doesn't when we create this thing, it doesn't has an edit button. And then one has an edit button. And then one has an edit button. And then one morning, it just "Hey, morning, it just "Hey, morning, it just "Hey, this schedule needs to be updated and we this schedule needs to be updated and we this schedule needs to be updated and we don't have those edit buttons." I could don't have those edit buttons." I could don't have those edit buttons." I could just ask Devin, "Hey, can you add me an just ask Devin, "Hey, can you add me an just ask Devin, "Hey, can you add me an edit button?" And then it did. So, we edit button?" And then it did. So, we edit button?" And then it did. So, we can change everything now and then ship can change everything now and then ship can change everything now and then ship it to PNG and replug it to the screen, it to PNG and replug it to the screen, it to PNG and replug it to the screen, which is pretty convenient, right? And which is pretty convenient, right? And which is pretty convenient, right? And those exceptions, right? It those exceptions, right? It those exceptions, right? It it's not possible before it's not possible before it's not possible before when we have to do it manually and when we have to do it manually and when we have to do it manually and stuff. stuff. stuff. But now it's just get easier. And But now it's just get easier. And But now it's just get easier. And so, the takeaway here is that to solve so, the takeaway here is that to solve so, the takeaway here is that to solve the scale problem, you have to actually the scale problem, you have to actually the scale problem, you have to actually think small. Think all the smallest think small. Think all the smallest think small. Think all the smallest thing possible. Think everything that thing possible. Think everything that thing possible. Think everything that can go wrong and will go wrong and then can go wrong and will go wrong and then can go wrong and will go wrong and then try to solve it before. And also, like try to solve it before. And also, like try to solve it before. And also, like yeah, right now basically you can yeah, right now basically you can yeah, right now basically you can automate everything.

automate everything. automate everything. And at this moment, having a problem is at this moment, having a problem is actually going to benefit you because actually going to benefit you because actually going to benefit you because that's going to help you ship that's going to help you ship that's going to help you ship a better product, going to ship uh a better product, going to ship uh a better product, going to ship uh things that are things that are things that are good. And yeah, I think that's all that good. And yeah, I think that's all that good. And yeah, I think that's all that I can share. Hope my talk has some I can share. Hope my talk has some I can share. Hope my talk has some benefits to you and benefits to you and benefits to you and yeah. yeah. yeah. That's all. Thanks, guys. That's all. Thanks, guys. That's all. Thanks, guys. >> [applause]