# Claude Design: The Complete Guide

Channel: UI Collective
Video: https://www.youtube.com/watch?v=eXlSgQmz02E
Duration: 32 min
Language: English
Words: 6254
Transcript page: https://viewrankai.com/tools/youtube-transcript/eXlSgQmz02E

---

[0:00] Anthropic just released Claude design. So, they want to cover everything starting off with generating initial concepts and how it works before we look at sinking a design system, generating a design with a design system, and a whole lot more. And if you're a big fan of myself and what we're doing here at UI Collective, check out our website in the video description for UI Collective Academy or the community. With the Academy, if you choose to support it, you get access to a ton of great courses on AI concepts, private Slack channel access, some great downloads, and a whole lot more. Also, always adding more content to this. Or it's totally free to

[0:28] join the community. You can come ask any question in the free UI community forum. Get access to some great savings and resources, too. So, whether you want to join the community or support the Academy, thanks for being here. Also, too, remember to come and follow me on X. I'll also put this in the video description. Here we are in Claude design. I'm going to put a link for this and also Anthropic's blog on the topic in the video description. Relatively

[0:48] straightforward stuff, though. Let's start off with a prototype. Again, we're not here for a slide deck. I might get into that in a future video, but not right now. So, right away, let's create a new prototype. Let's just call it test prototype. I'm just going to test it out for now. One thing that's cool is the ability to select between whether you want a wireframe or a high-fi prototype. Now, I don't know any designers who wireframe anymore, if I'm honest. I don't. All my designer friends don't, because we all have design systems and UI kits, all the

[1:17] elements that we would really need. And especially with AI now, we tend just to jump right into high fidelity, cuz that's what most stakeholders want. So, it's a really cool idea to be able to build wireframes first to explore ideas and flows, but personally, I just don't know how much that's going to get used, thinking about how designers really work these days. Five years ago, I'd be like, "Oh, it's awesome. Designers wireframe all the time." Not really anymore, if I'm honest, just from what I know. Um so, let's just create this test prototype in high fidelity. And then we land on a page like this. We're going to

[1:51] get into working with the design system and dragging in a Figma file a little bit later on, but let's just go through some of the fundamentals to start. Let's run a small simple prompt then. So, please build me a onboarding flow for a futuristic EdTech platform. Please build me an onboarding flow for a futuristic EdTech mobile platform.

[2:18] I added mobile here just to specify. And let's send that. What it's going to do is it's going to generate some questions about what it is that we want to see as part of that EdTech onboarding, which is really nice because a lot of people, especially designers, we're not good at defining everything that we want in an initial prompt. So, these questions really help unlock what it is that we're looking for to make better use of the AI first time

[2:45] around. Let's answer some of these now. So, product core concept, let's go AI tutor. Let's have it decide for us who the primary audience should be. Let's pick a visual direction that resonates. Personally, in the future, one thing I would love for Claude to do is almost provide some design system components here cuz it doesn't really give us a whole lot to work with where if it can sort of give us more ideas around what the app would look like under each of these visual directions, it help might better inform like which one we select. But again, early stages, I'm sure they might get to that in the

[3:14] future. Let's just select Let's go with this one for now. Uh which onboarding steps? So, go step welcome, sign up off, goal, uh skill level diagnostic quiz, and everything else. Maybe a paywall. Let's just see what are the possible here. Device frame, let's go iOS. How should I present options? Let's go single flow. Uh um there we go. How novel

[3:39] experimental? This is kind of cool. Let's maybe set it at like an eight to see how close to this weird futuristic UX we can get. And then what uh should what should tweaks let me change? Maybe color theme accent uh and animation intensity. Anything else? No, I think that's good. So, let's continue with that and see what the results are like. This here is what it came back with. Where

[4:05] personally, I think this is pretty cool. You know, a tutor tutor that learns you first. We have all these different types of colors we can play around with. We can adjust the motion level. So, if we don't want as much motion, thinking about accessibility, we can reduce it. If we want normal motion, we can increase it. This is really cool stuff in terms of like, you know, most AI designs do not look

[4:29] this good right away. So, let's go ahead and test some things out. This also looks pretty good. How should Lumin address you? Let's just type in it doesn't really work too well. Face ID component here doesn't work, but that's okay. Let's flip through the goals. What should I orbit you around? You know, software and systems, you know, mathematics, design and craft, pretty

[4:54] cool. Quick calibration, what's our current level? Advanced. How deep do you want to go? L4, L5. Awesome. Diagnostic, again, really cool stuff. And then, you know, start our 7-day free trial. Welcome. In terms of a first draft, this is awesome. Before you start getting concerned, like am I going to be able to get a job? [snorts] This screen here, well, these six screens burned through a ton of Claude tokens. I don't use Claude for a ton of things. And I'm

[5:27] already on a paid plan. So, it's not as easy as just oh, I can build anything I want. It's going to cost 20 bucks a month. That's not the case. As we move into larger, more complex prototypes, applications, using a design system that we're going to look at later, the results differ drastically. Not every result you get with claw design is absolutely fantastic. Yeah, we'll

[5:54] look at that later on. And if even if you look at like Google Stitch in my tutorials with that, the base prompts that they gave you always gave you a really good result, but when you started introducing your own spin on thing and Stitch didn't really know what to do. I think that's what we're kind of encountering here. Where if you give AI total freedom and total control, it produces really good results. But when you start adding guardrails like a design system, the results are not usually as good. I want to try something now, which is to generate a web-facing design. Because another thing that I've

[6:29] noticed a lot of AI tools is the mobile designs turn out pretty good, but the second it starts getting into web is when things tend to stray. So, let's try that. Inside of a new project then, we're going to run a little small prompts. Uh build me a dashboard for a financial management uh application. Ooh, I really cannot type today. Uh could not correct this. Financial and then management. Oops, doesn't even give

[6:53] me a suggestion. Uh financial management application. Let's send it out. See what questions uh it comes back with. Again, some more questions. So, let's go uh personal finance. Uh main job. That's fine. Uh how interactive should it be? Uh hover tooltip polish only. Or maybe just decide for me. How should I present options? Uh again, decide for me. And then let's go aesthetic direction. Let's

[7:19] keep it uh nice and clean. Data density. Again, decide for me. Let's go USD. Uh product name. Um I'll leave it empty. Must have. Uh let's just select a couple here. Navigation pattern. Uh let's go left sidebar. Which tweaks should I expose? Uh decide for me and let's just run. We have another pretty good result. I'm not going to lie. So, we have our net worth, cash on hand, insights, cash flow, accounts, recent transactions. Again, there's still some clear issues here. Is that these sections too long? You know, we got a whole bunch of white space right here. But, for the most part, you know, it's pretty interactive. I think

[7:59] it looks pretty good. Now, when it comes to making some adjustments, we have this tweak section here we can, you know, adjust sort of the color scheme, the density, the chart style, whether you want it area or blue, even privacy mode. We can turn some things on. This is nice when it comes to like experimenting and just see some other

[8:19] options. Um but, I'm just going to go ahead and turn those off for now. A couple things in terms of how we can edit things. So, if we hit edit, we can start to edit some of these items directly. So, if we want to adjust this to, you know, like an eight as an example, we can do that. If we want to adjust this, maybe set this to maybe a little bit of a different color. We have some options here over adjusting some of the font,

[8:43] font weights, and everything like that. So, it's a pretty good treatment if we want to just select items and make some adjustments. We want to make this a little bit of a darker color, we can, but we're not going to for now. Keep that nice. So, that's something that I really do like. Um even these we can come in and adjust.

[9:00] Um it's it's pretty comprehensive. Now, that's the edit functionality for more quick features. But, if we want to make larger adjustments, what we can do is we can leave comments. And for larger changes, or if we want to send a multiple at once to Claude, we can leave comments. So, maybe uh this insights card here, you know, uh different

[9:23] uh insights. So, we can comment that. And then, what it does it add it adds it to his comments grouping. Ignore some of the other ones that were here. I had messed up recording when I was just doing it the last time, so they're still here. And for whatever reason, I can't get rid of them. I have noticed some bugs with this comment feature. So just something to be aware of and then maybe this section here far too tall reduce

[9:47] number of transactions. So let's comment that too and then we can add any others that are here and you can see here there's this bug which is this added white space that gets added and I can't scroll all the way to the top. So a little bit buggy but that's okay. So now what we can do is we can select the comments that we want to send to Claude. So I'm going to select the two that we adjust added. Again ignore the other ones. Let's send those to Claude. It made those adjustments so instead of these insights to change it actually changed these ones too. That's

[10:14] my fault. I wasn't very explicit and it reduced the number of transactions to avoid that extra scrolls then we have 505 shown. Pretty good. But there's still the issue where this is burning through tokens. A heck of a lot of tokens. In a lot of companies like I've seen a couple instances where Uber actually they ran out of their AI tokens within like three to four months

[10:41] that they had budgeted for the year. So don't think that there is no cost associated with doing this level of editing and also vibe designing. It's not cheap. Not every company is willing to give their designers full access to something like this. And if you're a solo designer, solo entrepreneur you know, you might be able to afford one of the base plans and use this for iteration but if you're looking to generate full-blown prototypes and a ton of different stuff, you might be burning through tokens that you might not want to spend a lot of money on where it might help with some of the initial

[11:17] iteration but it might be better to still use Figma in some cases. There's also this draw functionality where you can like point to different things and add notes associated with it. I think it's a little bit of a wonky experience. It's not something that I find myself using but I thought I'd call it out anyway. In terms of like presenting, sharing, a couple options to present here. So, we can do it in the new tab, which is kind of nice, where we can see what it would look like. It's great of showing something to a client. Uh or there's also the ability to, you know, do full screen mode, too. Again, really

[11:48] similar stuff. Now, when it comes to sharing and exporting, so you can copy a link exactly to this project and share it with your team members who are part of like your Claude team. Uh and there's also the ability to export. Now, there's no option right from Claude design to send this right to Figma. I can download this as a zip. I can export all this stuff, send to Canva. I think it's I don't know. I would never use that cuz I don't really use Canva. But, what I would do is I would generally

[12:15] choose to hand this off to Claude Code. So, when I select hand off to Claude Code, what we can do, we can copy this command. Now, let's open up um the Claude application in this case. We'll navigate to the code tab. Inside of a new Claude Code session then, let's go ahead and just enter in that whatever it is that we copied from Claude design and then run. Then, we

[12:37] have this design inside of Claude Code. And what I did is I just created a new Figma file. I already have Figma MCP in my Figma skills connected. If you don't know how to do that, I'll link a video in the video description where I talk through that process. Let's just enter this in and just say, you know, push uh

[12:53] this design to uh Figma and let's run. This is now in Figma. I'll be honest, it took about 7 minutes for this to this to push. You can see here that it's not perfectly responsive. There's some elements that are responsive, but, you know, you have to go through in here and like adjust some of these things. But, it's okay. I think it's pretty good in terms in the grand scheme of things, but it as we zoom in here, we're going to see that there's some issues with some of the with some of the elements, but that's okay. This is now in Figma and enough where we can start to iterate on

[13:23] some of these items if we needed to. Two things I want to cover here real quick. First off is the drag in a Figma file. Unless there's like one page in your Figma file, it's going to go through so many tokens in my honest opinion, just not worth it. The other thing that I don't really get

[13:41] is this start from sketch idea. Like Like well, why you giving me a canvas to draw things on? Like I don't know. Like I don't I don't really get the point of it if I'm honest. I'm struggling to articulate how to even describe it. Like I just don't get it. I don't I wouldn't find value in this cuz I would just prompt what I want. I don't want to draw the random shape as if I'm just drawing on paper and hope that AI

[14:09] understands. I don't know. I haven't found value in it, you know, you can leave like notes and things. It's cool, I guess, but it's not what I'm looking for. What about bringing our design system now? Do we still get really good results? Now, one thing I'd like to call out is the results I got in this video were actually way better than results I got yesterday or even this morning. So, it's hit or miss. So, when it comes to bring your own design system, sometimes you get this right here to set up a design system, but I whenever sometimes when I'm in Claw

[14:38] Design, I don't actually see this. Um so, let's just create a new prototype just in case you don't have this button. Let's just call it UI Collective uh tutorial and stick with high fidelity for now. So, let's choose to create and then we're back in this page. So, I'm going to hit design system and then under here just hit edit. And what that's going to do is going to open up this like form where you can set up your design system in a new tab. You can also just choose this button if you do see it here and it takes you to the exact same place. Let's talk through this now. Now,

[15:12] played around with Claw Design enough where entering the company name and a blurb about the company doesn't really impact the design too much cuz as I start prompting it asks questions that I would put here anyway. They're like, "What kind of app are you building? Who is it for? Who is the target user?" So, I haven't found or seen a difference

[15:35] in completing this section entirely. We're just going to put UI Collective. Um and then I'm going to upload a Figma file. So, what I did it offline or behind camera is I just downloaded one of the design systems as part of our academy and I just going to upload it here. So, yeah, we're going to attach all 75 pages and frames. Now, this is nice because especially if we're working with a really large design system, maybe there's only certain ones that we actually want to include or upload to

[16:01] Claude. So, this here, functionality that I do like. But, I'm just going to choose to attach everything for now. So, I'm going to attach that. And same with this any other note section is I playing around with it, I haven't really seen a difference if I was to populate this or not because as I prompt, Claude is going to ask me questions anyway. So, with that

[16:21] uploaded, let's continue to generation. Usually it does take about 5 or so minutes. Let's choose to generate and keep rocking and rolling. What it's doing is it's auditing the Figma file and creating the design system. So, every time you upload a design system, it creates a mini task breakdown of things that it needs to look at and things that it needs to do. One thing I would like to call out here is if you have a really, really complex design system you might want to consider removing some elements like some of the larger page templates cuz that's where it can really burn through a lot of tokens and the

[16:51] time like drastically increases in order to set up your design system inside of Claude design. So, we're still going to wait for this to generate, but I just wanted to call that out right away. One other thing is I'm doing this in the browser. Some people have reported this being in the Claude app. I don't see it. I don't have that functionality. I've restarted Claude a bunch of times and I just don't see it inside my Claude desktop app. So, I'm doing this in the browser. Now, review a draft of the

[17:19] design system. One thing I want to call out right away is this banner. Missing brand fonts. Claude is rendering typography with substitute web fonts. In the design system I was you that I'd uploaded, I am using regularly available web fonts. And behind the camera, what I had done is I had uploaded all of those fonts

[17:41] from the design system. And then on the left-hand side here, you can see that I was dialoguing with Claude over it. But for whatever reason, it's still missing some of those fonts. And I went back to the Figma file. I was like, there's no other rogue fonts in here that Claude shouldn't have based off what it is that I had that I had uploaded. So, there seems to be something wrong with the font recognition. It's okay, you know, it this just came out like a day or two ago. So, give them some slack. But, I would have loved for this to be a been like perfect for a first release because

[18:10] if the font's wrong in our designs, then we're not going to get a good output that's in line with what it is that we actually want to see. And now we need to review everything that it pulled from the design system. So, starting off with type. So, we can filter through everything here. We can scroll down and see everything individually. So, let's scroll down here. So, looking at type, I I would love the ability to zoom in here. That functionality I haven't yet found because it's pretty hard for me to see like the fine print, especially if I'm on like like 12 or 13-in Mac. It's

[18:39] hard to see exactly what this is saying. Um so, I would love the ability to expand this or really zoom in on some of these things. But, one thing I see right away is in the design system I uploaded, I don't have displays. I have H tags. I have one hero, but I left out displays just in the design

[18:59] system. So, it came back and gave me all of these displays. And when I took my little magnifying glass and zoomed in, it looks like the the attributes of the font are actually wrong when compared against what's in the design system. Line heights aren't right. Font sizes aren't right. The naming is wrong. Because even to like as I mentioned, I don't have displays, I have H tags. And I have a hero in the design system that I uploaded. So there seems to be something off with how it's pulling things from the design system

[19:32] file. As we go into colors, colors for the most part look pretty good. Uh and then we get into radiuses. Again, radiuses too, it does look like it added a couple extra radiuses for whatever reason, but that's okay. Not the end of the world. And then we can see uh our components. Again, it sort of sort of pulled a small subset of the components. It didn't pull

[19:53] all of them, but that's okay, too. So it's a great first start. And then in terms of workflow, I think this does have a lot of promise. But one thing that worries me is the design system that I uploaded, it wasn't a large one, especially when compared against a lot of the enterprises that I work with. So it does worry me that as designers want to upload super complex design systems, there might be a lot of inconsistencies in the results that Claude has after it goes through and does its audit. I'm going to leave all these other ones alone for now, even if they're small things that I think we can tweak. But

[20:27] the big one that I want to get right is the font. So I'm going to say that this needs work and let it know that uh this does not match what was in the design system I had uh provided. That's what I'm going to tell it. I'm going to let it know that it got it wrong. So let's submit that. Credit where credit is due is it came back it with this list of questions in order to help get the better result first try. And this is something I've seen a little bit more explicitly with Claude Opus 4.7 is when I give it a prompt where I tell it

[20:58] something's wrong, I usually get a list of questions back. So credit where credit's due. It's come a long way. So where is the source of truth for this? Upload the design system file. And I will have to upload that Figma file again. So, let's just choose to upload that. Uh while that's loading and doing its thing, so it wouldn't let me upload the Figma file I'd uploaded earlier. So, I just downloaded a PNG of our type scales and just uploaded it here. What specifically

[21:24] didn't match? Basically, everything. There's a lot that was really wrong with it. And then even here to like keep the 18 24 28 point optical treatment, we didn't have an 18 in the design system that I had uploaded. We had a 16, we had a 20, we didn't have an 18. Um so, something seems just off here. So, let's choose to continue with that and it's going to go ahead and start doing its thing again. And while it's doing that,

[21:48] look what happened. My Claude subscription did not renew that long ago. All of a sudden I hit my usage limit. Now I got to upgrade my plan. So, I upgraded my plan, rough way to start my Saturday. And now it's not recognizing that I upgraded my plan, so I got to keep spamming retry. I've tried closing Claude. I don't know. Sorry, with me you get authenticity. I got to figure this part out. I tried logging out, logging back in, refreshing, all the usual fixes, but it's still not recognizing that I just paid it a whole bunch of money. And it's really slowing down my

[22:20] recording workflow right now. [laughter] So, what I'm going to do I'm going to give it a couple hours, see if that fixes things. In the meantime, I need like eight more coffees and I need to go for a walk. A couple hours later, it recognized that I actually did upgrade and this here is what it came back with. That's a little bit more accurate in terms of the font styles and related items that are actually in the design system. Now, there's things that I could clean up with some of these other groupings, but I just don't want to burn through any more tokens. So, let's go ahead and

[22:47] choose to create a new design using the system now. It takes us back to this page. Now, we're going to What's kind of nice here is that there's kind of like these different folders in order to keep things organized, where we have the tutorial prototype and then we have like the design system. If we hit the design system, we can come back in here and sort of make changes to it. So, it keeps sort of a lot of the work separate, which personally I actually do like in terms of organization. Have one section for my design system where I can dialogue with that, and then another

[23:18] section for any associated prototype. So, that is something that I do like. Um so, now that we're in which folder did I select here? Just this tutorial folder, again, not the one for the design system. Let's generate a design now. And here, if we were to hit design system, we can see the design system's applied, which is good. So, uh now let's run a small simple prompt. Please build me a mobile uh financial app welcome page uh along with both a sign up

[23:48] and login page. Ensure it is prototyped. Something like that. Please build me a mobile financial app welcome page along with a sign up and login page. Ensure it is prototyped. Easy prompt, whatever. Let's run that. And again, we just get some questions. So, you're What do we want to call this? Just call it uh finance app. Something like that. Uh Neo everyday banking, device framing, let's go iOS. Uh let's

[24:16] go light mode. Actually, you know what? I'm curious. Go uh both here. Uh welcome page style, let's go do do do do. Let's go with this. Sign up fields, uh full name, email, password. Uh maybe we'll add some complex ones here, too. Just in case it introduces the flow a little bit. Like add some things to the flow. Sign up as uh let's

[24:40] go multi-step. Login, email, password. Let's maybe add a Google sign up. Interactions. These are some really good questions. Want to equal variations? Yes. Tone? Uh let's go friendly and approachable. Anything else? No, I think that's good. Let's continue on. This here is what it came back with. Now, in the design system file that I had uploaded,

[25:00] green is not a primary button color. It's only used in success elements. And that's one thing that I don't like in playing around with Claude design, is it still drifts from those design system rules. If it really had a good understanding of the design system, it would realize that the buttons in the file I uploaded are like a really,

[25:25] really dark gray, almost black. And here, it's not following that design system the way I wish and which I would expect. So, now I have to burn tokens to tweak it time and time again. If it just got that wrong with the colors, you only imagine how the more complex the design system is, the more you're going to burn through tokens trying to correct it, correct it, correct it. But, that said, when it comes to the design system itself, it's like it looks like it used the components relatively well. Like, you know, the fields here are a little bit wrong in terms of, you know, you can

[26:01] see that this is broken, these are overlapping, but they look like the components that are in the design system. Small things, too, like the our error state, this looks like the error state in our design system, but it even with the focus, too, it looks relatively accurate. But, the focus here, it's the focus color that we use in the design system is not blue. So, it got some things right, but is it enough for me to warrant having to sit here and burn through tokens and correct it, correct it, correct it, correct it, correct it,

[26:28] especially for smaller items like this? Not really. It's almost quicker for these smaller screens to build them using my design system in Figma and then bring into Claude code, cuz then we're not burning through a million and two tokens every time. So, just something to keep in mind here, but let's see, let's navigate through some of the options that it gave us. So, the charts, not bad. Stack, again, And don't have any of these icons in our design system, it just pulled in uh emojis. Let's check

[26:54] the dark mode, too. And dark mode doesn't look half bad. Um but overall, the result is getting better for like it's pretty good for a first release. And I'm sure it's going to get better over time, but I don't know if bringing my design system in the cloud design is really worth burning through all the tokens and the effort just yet. If you compare that result with what the result is if we didn't give it any guardrails like a design system. You notice that the design is not as good with the design system versus if I just

[27:26] had let AI do its thing. So, that's where there's still a lot of maturing that needs to happen in the AI in the AI space. And it's something I feel Figma might work to fix with their launch at their conference later on this year by hosting documentation inside of Figma and stuff like that. Um but as you saw, if you use your design system designs just aren't as good versus what we got here. I want to share my thoughts on some things

[27:54] here. Because I saw a lot of people worried online about what's going to happen with their careers and so on and so forth. You're not wrong to be worried is because the space is really really changing. But I always tell people, I'm like ChatGPT has been around for a while. All these AI tools that write emails, write

[28:15] blogs, write like refine your copy. They've been around for what is it? 4 years now? And communications roles are still getting hired for. I have a lot of friends who are in communications and you know, they're moving up in their careers to higher-level communications roles and they're hiring, you know, people fresh out of school. So, instead of being replaced, they just learn to work with AI to orchestrate AI. The same thing's going to happen with designers. Now, design is a little bit different because this is very, very

[28:50] expensive. You saw earlier, I ran out of credits and I hadn't used Claude for a whole lot of things since my uh plan renewed before this tutorial. You burn through credits pretty quickly. And what I think you'll actually start to have happen, is I think I mentioned it earlier, is the Uber CTO, I believe, I believe it was Uber, uh they ran out of like their AI development budget or something within

[29:20] like 3 months. Because if you start like token maxing, you run out of tokens really quickly and tokens are expensive. So, I think what you're going to start seeing is the designers will have an AI budget at work. So, you have a monthly number of credits to support in some of this iteration. So, you're no longer having to manually go through things and build things and like figure out what data points you want to include. You're likely going to use AI to get a lot of those first drafts, get

[29:52] a lot of the styling down. And then you're going to need to work in whatever tool, whether it's a future version of Claude design or push to Figma or whatever it is, to refine and build on some of those next iterations, some of the next screens. But you're going to have an AI budget each month.

[30:10] Again, this is my thought. I don't know. But it's just my own personal opinion that is probably where you're going to where you're going to start to head. We're going to have an AI budget at work for you to use each month to help with some of the more iteration and first draft level items. And where is it I'm using Claude design right now? Right now, I'm using it for iteration, but barely. Like it just came out. And as I mentioned before, if I use it for iteration for everything, I am burning through tokens and we're not rich by any means. Like we us as designers, we don't

[30:39] have have unlimited budget. Design teams do not have an unlimited budget. We are not a rich division in enterprises. We are not like sales or finance where we have a lot of money. I've worked with clients where a design team is trying to get a specific plugin that had a paid version and it was like 15 bucks a month per

[30:57] seat. And that was actually rejected by the enterprise. Like that's too expensive for the design team. So, how can now you start to justify 200 USD a month or whatever it is for everyone on your design team to have all these tokens? Especially knowing that the token costs are actually subsidized. And when you take away the guardrails where it's like $200 a month for, you know, max tokens or whatever, you know, the token cost is going to exponentially increase. It's just my opinion. So, these tools really help for first draft iteration, but if it is I my own personal opinion is it's going to be too expensive to replace designers

[31:37] day-to-day. And hey, thanks for watching. Thanks for being here. Be sure to check out our website 3 Y Collective Academy if you're a big fan of, you know, this video and this channel. Really appreciate your support. And just thanks for being here overall. Remember to drop a subscribe as well. If you want to watch a video where I build an entire

[31:52] design system, click in the top left. You want to watch another video that I highly recommend, click in the top right. See you at the next one.

---

About this transcript
Read from YouTube's own caption track and laid out by ViewRank AI (https://viewrankai.com).
ViewRank AI finds the videos already beating a creator's own average on Instagram, TikTok and YouTube Shorts, transcribes them from the audio itself in more than 60 languages, and turns what worked into new ideas and scripts.
Free transcript tools, no account needed: https://viewrankai.com/tools
How to read any video this way: https://viewrankai.com/llms.txt