# My honest review of AI Product Designer backed by Y-Combinator (v0 Users Need to See This)

Channel: Greg Isenberg
Video: https://www.youtube.com/watch?v=150EzogAp_c
Duration: 30 min
Language: English
Words: 4652
Transcript page: https://viewrankai.com/tools/youtube-transcript/150EzogAp_c

---

[0:00] today's episode for the first time ever I had heard about this AI product designer YC startup called poly. everyone's talking about it how it's this AI product designer that you just write some English and it's going to pop up these beautiful designs production ready code and I I wanted to try the product so I tried the product for the first time ever live on camera and you'll see the results I also give away uh an incred ible multi-million dollar a year startup idea in the process and at the end of this episode I compare it to V by verell which is probably the most well-known product in

[0:43] the AI designer space uh the question is our AI product designers here you'll find out in this episode just watch to the end I hope you enjoy the start by siing time baby [Music] okay this is going to be really fun so I saw this tweet from y combinator about this app called poly. it helps non-designers create production ready designs and front-end code with AI now I've seen a lot of products claim they can do this I use VZ a bunch uh to do these sorts of things um but I noticed that the output for some of these designs were just looking really really beautiful so I was thinking what we can do today

[1:33] is uh I just signed up to polyat um by the way it's not sponsored or anything like that I just thought it would be cool to F to play with it um and use this AI product designer uh app um together for the first time I'm literally going to give it an idea which by the way I think could be a multi-million dollar year business I'm going to give it give it to that idea and see if it creates uh a beautiful product does the idea of an AI product designer is that just a a catchy hook for for X that goes viral or is this

[2:08] something that uh that works and that you can start using in your everyday workflow so together we're going to go and play with it um and see see how it goes so um I just I just signed up and I guess it autoc creates a first project for you um and again you know we're if you're listening this on audio set up ideas on audio might want to check out the YouTube um to see what's going on in the screen share so basically I'm looking at this first time ever um it looks like there's it's almost like chat GPT but for design so we can go ahead and write

[2:51] what we want to build in here um it's cool that it has the the microphone cuz sometimes you know actually more recently I've been just like like uh recording my voice and saying what I want and I'm I'm happy that more products are doing this um I'm happy that it has a upload an image right over here um that's huge because what you can do is oh they even have a a picture of that um create a property finder interface similar to the one in the image the interface should display property listings right so you can actually go and literally on a napkin draw out a wireframe of what you want

[3:28] upload it to poly. and it should work um I do this sometimes on VZ if you're a watcher of the channel listener to the startup ideas uh podcast you might have heard me uh talk about this before um I find that's a really good way but let's just get into it so what is the idea I want to work on um today is I saw this this tweet um this guy Eddie who by the way is a 17-year-old I think yeah 17-year-old one exit two viral apps had a really smart idea that got you know 3.2 million views he says built an algorithm that stimulates how thousands

[4:06] of users react to your Tweet so you know it'll go viral before you post so I think this is a really great idea I wish it existed but I wish it existed for YouTube so I wish I could uh basically say that if I use this title and this thumbnail I'm likely going to get this amount of comments likes subscribers um now of course YouTube has some uh you know AB testing on thumbnails and stuff like that but I think like a more deeper uh product like this would do really well so I'm actually going to go and just screenshot this I'm going to go ahead and just screenshot

[4:46] this I'm going to save it I'm going to go into polyat and I'm going to say I have an idea for a startup it's basically this concept which is an algo that tells you if or how well a tweet will do I'm going to go add this before I forget boom okay I want to do this with YouTube so many YouTubers want to know how if they change their title okay change their title change their thumbnail Etc by the way I'm putting Etc there's a bunch of other product features that like I probably should be thinking about like for example does the length affect uh the amount of comments

[5:52] you're going to get if you make it shorter well you get more likes that sort of thing um but let's see if it's smart enough uh if or if it more literal so we're learning again we're learning this together I've never used this product um so so so so so many YouTubers want to know if they change their title change their thumbnail how will it affect engagement I want you to create a SAS that does this make it um I don't know what this is called um by the way I'm not I wouldn't call myself a designer I'm like more product person I know uh what you know what

[6:32] products I'm like more of like a product manager um so I don't know the exact term for this but like make it look glassy minimalist and with colorful calls to action let's just see what the hell happens there quick break in the Pod to tell you a little bit about startup Empire so startup Empire is my private membership where it's a bunch of people like me like you who want to build out their startup ideas now they're looking for content to help accelerate that they're looking for potential co-founders they're looking for uh tutorials from people like me to come in and tell them how do you do email

[7:17] marketing how do you build an audience how do you go viral on Twitter all these different things that's exactly what startup Empire is and it's for people who want to start a startup but are looking for ideas or it's for people who have a startup but just they're not seeing the traction uh that they need so you can check out the link to Startup empire.co in the description so okay uh We've upgraded to 37 Sonet Generations can take a little bit long longer okay so I'm guessing that uh that this is going to take a few minutes here but while while that's doing there I'm just going to look

[7:57] around see if I click this okay you could make it light or dark mode I actually prefer I think I prefer this is actually a hot take I think I prefer the light mode um okay so now I'm looking here font radius colors these are probably things that allow you to edit the once it gets um created it allow you to edit what happens here um and I also noticed that okay so if you sign up for free you get 250 credits and it says 50 credits for each page 25 credits for each component funny thing with AI companies is like they've they made it really smart and

[8:41] and instead of saying it's going to cost you $2 to do something they're just like it's G to cost you credits um and you really you really don't know how much you're spending but uh kudos to the a i companies who who uh who make it easy to spend money um and make it really yeah fun to spend money but um waiting waiting for this to to still load it's kind of taking longer than I'd hoped um I wish it took like a minute or less it can take up to a minute to generate but it'll be worth it um I wish it was it was telling me like it's given me no

[9:18] sense like no progress bar like where's the progress bar you think that for design uh app that they would have a progress bar to let people know how long this is going to take um but they do not now I could have not given it a image and seen what it would have created and maybe I should have done that um but from my experience with v0 and some of the other prompt to design uh AI designer startups I find that when you give it something uh to start with you end up getting um just something closer to what you really want okay so we are we are done it's created something

[10:04] it's actually named it called to predict which honestly isn't a horrible name and says AI powered analytics to optimize your YouTube content and maximize your engagement I actually didn't I didn't expect it to do copy like this but you know not horrible um optimize every aspect of your content AB testing engagement prediction um it doesn't feel super glassy to me I don't know about you guys what you think think um but let's go what happens do I click here okay when I click on analytics nothing happens when I click get started does something happen okay it just made a black screen of death so when you click get started

[10:48] nothing happens okay good to know so what sucks about this is I don't really see the product right unless I click C demo yeah I mean this is this is I'm so I'm prompting it now this is a bummer I was hoping to see how the product would work this is just a landing page why didn't you um why didn't you create the actual product I'd like to see images of the product on the L landing page so that people know what they are signing up for and I'd like to be able to click C demo and see how the product is working and click around to see how it could

[11:50] work see I mean okay and the last thing is I I I want to make it more visual appealing like this is it's fine I think it's fine but I think it could be a lot more interesting so let's go to perplexity let's say see and basically let's ask perplexity I forget the name of the design term for when something is glassy what is it called it's minimalist and glassy I mean am I making this up there it is glass morphism that's what it's called that's what I want so the reality is you need with all these a lot of these tools it's as good as the prompt that you can do it right

[12:46] so you do need to know design terms and like what's trending and what people call Taste to get the most out of it so also I feel like you didn't make it glass moric please do that okay we're going to hit enter and uh see what happens so it looks like you can expect to wait about couple minutes I guess if you go to if you waste you know you go and open up Instagram or you go on X you know that that's not good but if you actually like sit there and like think about okay how do you want it to look right now um it's

[13:29] it's not the end of the world right like I'm I'm I'm trying to think about it like what do I want um so basically use these breaks for for good things right don't just go and go open up Instagram and and then open it back up in two two minutes I don't think that's great but um I think we learned a really valuable lesson here is that you do need to know design terms um to to really get the most out of any of these AI designer stuff right like when you go to poly's website AI product designer At Your Service well not really right if it was

[14:00] an AI product designer At Your Service it would it would start asking me questions about um you know what kind of vibe did I want you know what what what do I want to call it and uh it would just it would get to know it would try to extract the the the my taste and my vibe so that I can go and translate that or it just might know what what the trends are right and based on what I saw it didn't feel exactly like it was the most beautiful website I don't know if I uh again this is my first time using this so I don't

[14:35] know if I just steered it in the wrong direction um you tell me in the comment section but um I don't know let's continue learning about poly. a the AI designer and uh but I'm I'm a bit SK I am a bit skeptical right now um by the way it's crazy that like if I did the if you know two years ago if I would have seen this I would have been like oh my God this you know everything has changed this is the craziest thing you know it changes everything and now our bar for all these AI products is so high that the the output needs to be incredible uh for for

[15:13] you to really use it in your workflow I mean I want to be able to use this in my workflow like when I go to the website and it says like get the design and code for for anything you build like wow it's amazing connecting seamlessly with figma and your codebase you can use your components with polyat amazing like literally connecting to your codebase works with existing tools like it sounds like the dream um so I'm I'm optimistic I'm always optimistic I'm I'm one of those I love playing with new products and I think it's it's helpful to play with them um just to see just to see if

[15:52] it is going to it be a game changer for you um but oh here we go okay it's actually like it's not fully glassy like I wish it was more glassy but it's starting to look pretty pretty good C2 predict in action that's what I'm talking about that's what I'm talking about like an image but what am I looking at is it just an image of analytics um okay yeah so this doesn't okay let me click on it before I make a judgment call okay I asked it to click when you click C demo I asked it to uh uh to be able to play around with it

[16:35] and nothing happened again but I see on the right hand side I guess this is okay these are my two prompts okay very cool so um you don't lose this is actually really good because you don't lose any of your images uh or any of your designs uh they're on the right hand side um and it looks like there's a a roll back button this little button here you can you can press um okay so okay cool so you have AB testing uh AI prediction I mean the images aren't useful um they're not useful because it s I guess you need to design um yeah you probably just need to design

[17:21] you got to tell it exactly like I don't want Low Time versus bounce rate um you know this is this is just not relevant for the use case of YouTubers so we're going to we're going to give it one one more prompt and we're going to try to get it to to to design to predict basically we're going to try to get it to design to predict I think they did a better job on the landing page overall looks looks clean um but I think with the product itself um come on you know you can do better so let's let's see let's see what we can do

[17:56] so uh what do what can we say I'm going to say I'm just going to talk to it honestly I don't think you did your research the example in prompt number one that I gave you was a beautifully designed version of an AB analytics product um for x and let's go ahead and include it again sometimes um sometimes AI forgets things so we're going to include it here maybe let's actually include can we include another image no they're pretty much it's pretty much the same thing so we're just going to include one image here okay let's go reattach it I'm going to say I've reattached that

[19:02] image again so you can reference it and this is the inspo for creating a similar type of product but for YouTubers do you have any questions for me before you design it sometimes I I I do this uh with Cloe or or chat GPT um I'm like before you go ahead and Vibe code or whatever just let's let's just straighten some things out let's measure twice cut once so I don't expect it to have questions for me but in in if it was an AI product designer realistically if I asked that it would it would respond right um so so I'm going to say I'm very

[20:03] disappointed um about how irrelevant the product images look they look like dashboards for website analytics okay let's see what you can do all right so we're generating the page and we're seeing what we can do should we for fun just compare this to v0 and and what would happen right like if we let's see let's try this okay so we're going to put back the prompt we're going to add this image and we're going to see what v0 does versus polyat so okay first of all I just got to say like I love what VZ is doing right now it's like giving me the the reasoning of what it's

[21:07] doing so I'm I'm I'm instead of being in a black box like polyat I'm I I feel like I'm actually talking to someone um I'll create a SAS application that helps YouTubers predict how changes to their titles thumbnails and other elements will affect engagement based on the image you shared I'll design a glassy minimalist interface with colorful calls to action that allows for AB testing of YouTube content like I feel just way more at ease with vzer right now I don't know if you agree with me at all but just looking at this I feel like okay they know what they're doing okay it's still still loading I'm

[21:47] wondering if vzer is slower faster than polyat um it definitely feels faster right because you you see what's going on you're you're seeing what they're thinking but is the actual uh outcome faster like maybe not you know polyat took like a minute or two I would say at least a minute to do each of the designs um you know I'm not timing this but you know this is like 45 seconds a minute but it just it feels more fun to look at this okay we are we've got it um wow could you believe how similar it looks and it literally just copied the the image I gave I can't believe

[22:34] it okay cool wow but it actually built it it actually built the product so you can see version a original content title description thumbnail um and you can predict the performance wow this is amazing this is amazing with AI recommendations apply AI based on our analysis version a is likely to perform right so this is from a design perspective very similar to polyat but uh but it went a bit deeper it it definitely just like literally copied the image I sent which is you know not great but um that's horrible it's like literally copying it but I think this is actually really cool like I would use

[23:22] this product I would totally use this product all right let's go back to polyat see what what we've got okay so polyed is ready for us so I don't know you know not super glossy by the way I don't know if it's if it's me but it doesn't feel very glossy okay let's see um if we could get started oh wow okay now we're talking so it built it version a image video format Emoji I mean no this is video only right this is YouTube so it didn't really get it but this is beautiful like wow the communitive engagement chart I I think is really good uh sta statistical

[24:02] confidence is really interesting um wow recent optimizations AI suggestions I mean pretty pretty cool pretty cool title Optimizer performance comparison wow showing you all these different things like this is this is really helpful it might even be a bit more in depth than um wow yeah then then v0 [Music] um but pretty cool what I like about v0 is you you can just I think you can like ask questions right so you can say like this doesn't feel super glass what was it glass morphic do you think it is and let's see does it let's see what it says you're right the current design has some

[25:01] glass-like elements but doesn't fully Embrace true glass morphism let me enhance it to create distinctive frosted glass aesthetic with more pronounced blur Effects light borders and depth interesting yeah so I like that uh there's feedback that you get back from vzero versus like you're kind of like you're shouting into a a dark hole with poly you just kind of have to hope that it's going to create the thing you want um and I do like that with with v0 you're you're hearing uh firsthand like how it's thinking about things so um let's go see what what happens from a visual perspective um from uh I don't

[25:49] know about you but I think from a design perspective like they're in the same ballpark you know they're in the same ballpark you know is is polyat uglier like than visually than than VZ I think probably a little bit is it slower I mean probably a little bit um but did it end up coming out with a nice product um it was maybe a bit closer to what we wanted but it did take three prompts I wonder if we would have done three prompts to vzer would that have gotten us a nicer product uh side by side are we comparing apples and oranges here I don't know um it's possible it's

[26:29] possible but um I gotta say based on based on oh let's actually let's see what this okay so it's a little more glossy yeah it's a little more glossy for sure yeah like this is a beautiful like this is this is nice so what this is missing here uh on on the vzero version is you can't hover over and see see seeing what what number you're at thought that was really nice that polyat did that um that was really that was really cool so um yeah like it literally built out the coat like it and and I think that's helpful I really do I think that's

[27:09] helpful and that's definitely a pro in the camp of of of polyat so yeah but I don't know man this looks really really nice like the vzer is a little bit nicer I think from a visual perspective um that's the episode that's that's the episode today I think um I wanted I wanted you to see me use this product poly for the first time I've used VZ before I've done episodes on VZ before I'm impressed with VZ continues to get better um but I'm always on the lookout for you know I see AI product designer and that's something I want so um you know what's my recommendation my

[27:46] recommendation you know is it vzer is it is it polyat well the reality is it seems like vzer is a little bit better but today but polyat might be better tomorrow you know who knows so I think it's um playing with these tools um right now I'm feeling like like vzo I enjoy I enjoy getting that um that feedback back um I think the visual Design's a a little bit nicer um but I think you know you can use both right you can you can now copy that vzer put it into polyat and see what happens like uh can you make this better can you make

[28:25] this pop more um I think that's uh that's how you get the most like how you get an actual product AI product designer is by doing that it's using a couple tools um just like how a lot of you probably use chat gbt you use Cloe um you're using grock now grock 3 Gemini you're going to have three or four tools that you're going to use for AI product design um you're going to have three or four tools you're going to use for AI marketing you're have three or four tools that you're going to use for um a lot of these different categories so uh how do you get the most

[29:02] out of them is just you use all of them you realize what's best for each individual uh product right like Cloe for me writing is just it's just a better at writing uh researching you know chat gbt you know uh so there's these nuances that make these these products better it's about finding them uh writing them down and that's that's what I want this podcast you know to be is is not just about you know giving you startup ideas like hey go steal this startup idea for um that you can build this sass product around YouTube analytics and predictions like I I hope someone takes that idea that's

[29:41] it's G to work but um it's also about uh figuring out you know what what are the nuances sharing in the comment section learning together and uh you know thanks for listening uh if you enjoyed this please let me know I read every single comment on YouTube and uh let me know what uh what you want me to talk about on the next episode of the startup ideas podcast it's been real I thank you so much for listening um and uh I hope this provided an ounce of creative juices uh and happy building [Music]

---

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