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

Episode Date: March 5, 2025

In this episode, I test Polymet AI, an AI product designer tool, by creating a YouTube analytics prediction SaaS concept inspired by a viral tweet about predicting tweet performance. I compare Polymet AI with V0, keep in mind that while Polymet required multiple prompts and offered less feedback during the design process, both tools ultimately produced usable designs. Timestamps: 00:00 - Intro02:33 - First Impressions of Polymet03:57 - Startup Idea: Predicting YouTube Engagement05:03 - Initial Design Prompt10:11 - Polymet’s First Design Output: TubePredict11:04 - UI and Functionality Issues and Debugging16:08 - Polymet’s Second Design Output17:44 - Debugging pt 220:48 - Prompting v0 22:30 - v0’s Design Output 23:41 - Polymet’s Third Design Output24:49 - Comparing v0 and Polymer and Final Thoughts on Design Outputs27:36 - Conclusion and Recommendations for AI Design ToolsKey Points• I test Polymet AI, a new AI product designer tool, that claims to help non-designers create production-ready designs• I compare Polymet AI with v0 by having them design a YouTube analytics prediction tool• Both tools produced functional designs, but with different user experiences and output quality1) First impressions of Polymet AI:• Clean interface similar to ChatGPT• Includes voice input (huge plus!)• Image upload capability for reference designs• Credit-based system (250 free credits to start)• 50 credits per page generation2) The design process with Polymet was... interesting.PROS:• Named the product "TubePredict" automatically• Created decent landing page copy• Saved version historyCONS:• Slow generation (2+ minutes)• No progress indicator (frustrating!)• Initial designs missed the mark completely 3) After 3 attempts with increasingly specific prompts, Polymet finally delivered:• Clean, modern interface• Detailed A/B testing dashboard• Statistical confidence indicators• AI suggestions for optimizationBut the communication was ONE-WAY. No feedback loop!4) Meanwhile, v0 showed its strengths:• Real-time reasoning as it designed• Conversational approach ("I'll create a SaaS that...")• Faster FEELING process (transparency helps!)• Ability to ask clarifying questionsThe difference in experience was NIGHT and DAY.5) The final designs were surprisingly similar in quality!Polymet's strengths:• More detailed product features• Hover states built in• Actual code generationv0's advantages:• Slightly more polished visually• More "glassy" as requested• Better feedback loop6) MAJOR INSIGHT: The future isn't about finding ONE perfect AI design tool.It's about using MULTIPLE tools strategically:• Generate initial concepts in one• Refine in another• Mix and match their strengthsJust like we do with ChatGPT, Claude, Gemini, etc.7) The REAL lesson? Knowing design terminology matters!When I specifically requested "glassmorphism" instead of just saying "glassy," both tools performed MUCH better.The more precise your design vocabulary, the better your AI design results.8) Would I recommend these tools? YES - but with expectations in check.Two years ago this would have been MIND-BLOWING.Today, our standards are higher.But for quick prototyping or inspiration, both tools deliver value in different ways.Notable Quotes:"Two years ago, if I would have seen this, I would have been like, 'Oh my God, everything has changed.' And now our bar for all these AI products is so high that the output needs to be incredible for you to really use it in your workflow.""How do you get the most out of them is just you use all of them, you realize what's best for each individual product... There's these nuances that make these products better."Want more free ideas? I collect the best ideas from the pod and give them to you for free in a database. Most of them cost $0 to start (my fav)Get access: https://www.gregisenberg.com/30startupideasLCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/BoringAds — ads agency that will build you profitable ad campaigns http://boringads.com/BoringMarketing — SEO agency and tools to get your organic customers http://boringmarketing.com/Startup Empire - a membership for builders who want to build cash-flowing businesses https://www.startupempire.coFIND ME ON SOCIALX/Twitter: https://twitter.com/gregisenbergInstagram: https://instagram.com/gregisenberg/LinkedIn: https://www.linkedin.com/in/gisenberg/

Today's episode, for the first time ever, I had heard about this AI product designer, YC startup called Polymet.A.I. 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 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 an incredible multi-million dollar a year startup idea in the process. And at the end of this episode, I compare it to V0 by Versel, which is probably the most well-known product in the AI designer space. The question is, are AI product designers here? You'll find out in this episode.

Just watch to the end. I hope you enjoy. Okay, this is going to be really fun. So I saw this tweet from Y Combinator about this app called Polymet.AI. It helps non-designers create production-ready designs in front-end code with AI. Now, I've seen a lot of products claim they can do this. I use V0 a bunch to do these sorts of things. 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 is I just signed up to PolyMet. By the way, it's not sponsored or anything like that. I just thought it would be cool to play with it and use this AI product designer app 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 your business. I'm going to give it to that idea and see if it creates a beautiful product. does the idea of an AI product designer, is that just a catchy hook for X that goes viral?

Or is this something that works and that you can start using in your everyday workflow? So together we're going to go and play with it and see how it goes. So I just signed up. And I guess it auto creates a first project for you. And again, you know, if you're listening this on audio, startup ideas on audio, you might want to check out the YouTube to see what's going on

screen chair. So basically I'm looking at this first time ever. It looks like there's almost like chat GPT, but for design. So we can go ahead and write what we want to build in here. It's cool that it has the microphone because sometimes, you know, actually more recently, I've been just like recording my voice and saying what I want. And I'm happy that more products are doing this. I'm happy that it has a upload and image right over here.

That's huge because what you can do is, oh, they even have a picture of that. 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, upload it to polymet.AI, and it should work. I do this sometimes on V0, if you're a watcher of the channel, listener to the Startup Ideas podcast.

You might have heard me talk about this before. 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 today is I saw this tweet. 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 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 basically say that if I use this title and this thumbnail, I'm likely going to get this amount of

comments, likes, subscribers. Now, of course, YouTube has some you know, A-B testing on thumbnails and stuff like that, but I think like a more deeper 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 this. I'm going to save it. I'm going to go into Polymet and I'm going to say I have an idea for a startup. up. 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. know how if they change their title. Okay. Change their title. Change their thumbnail, et cetera. By the way, I'm putting et cetera. There's a bunch of other product features that like I probably should be thinking about. Like for example, does the length affect the amount of comments you're going to get? If you make it shorter, will you get more likes, that sort of thing? But let's see if it's smart enough or if it's more literal. So we're learning, again, we're learning this together.

I've never used this product. 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 SaaS that does this. Make it. I don't know what this is called. By the way, I'm not, I wouldn't call myself a designer. I'm like a product person.

I know what products. I'm like more of like a product manager. 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 tutorials from people like me to come in and tell them, how do you do email 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 that they need. So you can check out the link to startup empire.com in the description. So, okay, we've upgraded to 3-7 sonnet. Generations can take a little bit longer. Okay, so I'm guessing that this is going to take a few minutes here. But while that's doing there, I'm just going to look around. Let's 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. Okay. So now I'm looking here, font, radius colors. These are probably things that I'll allow you to edit the, once it gets created, it'll allow you to edit what happens here.

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 made it really smart. And instead of saying it's going to cost you $2 to do something, they're just like, it's going to cost you credits. And you really don't know how much you're spending. But kudos to the AI companies who, who, who, make it easy to spend money and make it really, yeah, fun to spend money.

But waiting for this to still load, it's kind of taking longer than I had hoped. I wish it took like a minute or less. It can take up to a minute to generate, but it'll be worth it. I wish it was telling me, like it's given me no sense, like no progress bar. Like, where is the progress bar? You would think that for a design app that they would have a progress bar to let people know how long this is going to take, 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.

But from my experience with V0 and some of the other prompt to design AI designer startups, I find that when you give it something to start with, you end up getting just something closer to what you really want. Okay. So we are done. It's created something. It's actually named it called ToPredict, 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 expect it to do copy like this, but not horrible. Optimize every aspect. of your content, AB testing, engagement prediction. It doesn't feel super glassy to me. I don't know about you guys, what you think.

But let's go, what happens? Do I click here? 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, 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. 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, why didn't you create the, actual product. I'd like to see images of the product on the 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 work. Let's see. I mean, okay, and the last thing is 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. Let's 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 self up?

There it is, glassmorphism. That's what it's called. That's what I want. So the reality is you need, with a lot of these tools, it's as good as the prompt that you can do it, right? So you do need a no design terms and what's trending and what people call taste to get the most out of it.

Also, I feel like you didn't make it glass morphic. Please do that. Okay, we're going to hit enter and see what happens. So it looks like you can expect to wait about a couple minutes. I guess if you go to, if you waste, you know, you go and open up Instagram or you go on X. 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 it's not the end of the world right like i'm i'm trying to think about it like what do i want um so you 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 to really get the most out of any of these AI designer stuff, right? Like when you go to Polymet's website, AI product designer at your service, well, not really, right? If it was an AI product designer at your service, it would start asking me questions about, you know, what kind of vibe did I want? You know, what do I want to call it? and it would just, it would get to know, it would try to extract my taste and my vibe

so that I can go and translate that. Or it just might know 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'd, again, this is my first time using this. So I don't know if I just steered it in the wrong direction. You tell me in the comment section, but I don't know. Let's continue learning about polymet.AI, the AI designer. But I'm a bit skeptical

right now. By the way, it's crazy that if I did the, you know, two years ago, if I would have seen this, I would have been like, oh my God, you know, everything has changed. It's the craziest thing, you know, it changes everything. And now our bar for all these AI products is so high that the output needs to be incredible for 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 code base, you can use your components with polymet. Amazing. Like literally connecting to your code base, works with existing tools. Like it sounds like the dream.

So I'm optimistic. I'm always optimistic. I'm one of those. I love playing with new products. And I think it's helpful to play with them just to see if it is going to be a game changer for you. 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 good. See to predict an 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? 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 be able to play around with it. 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 you don't lose, this is actually really good because you don't lose any of your images or any of your designs.

They're on the right-hand side. And it looks like there's a rollback button. This little button here, you can press. Okay, so, okay, cool. So you have A-B testing, AI prediction. I mean, the images aren't useful. they're not useful because it's I guess you need a design yeah you probably just need a design you got to tell it exactly like I don't want load time versus bounce rate you know this is this is

just not relevant for the use case of YouTuber so we're going to we're going to give it one more prompt and we're going to try to get it 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 so uh 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 AI forgets things.

So we're going to include it here. Maybe let's actually include another image. No, 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 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 do this with Clode or, or chat GPT. I'm like, before you go ahead and vibe code or whatever, just 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 if it was an AI product designer, realistically, if I asked that, it would respond, right? So I'm going to say I'm very disappointed 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 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 polymet so okay first of all i just got to say like i love what v0 is doing right now it's like giving me the reasoning of what it's doing So instead of being in a black box like Polymet, I feel like I'm actually talking to someone.

I'll create a SaaS application that helps YouTubers predict how changes to their titles. Sometimes 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 A-B testing of YouTube content. I feel just way more at ease with V0 right now. 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 loading. I'm wondering if V0 is slower, faster than Polymet. It definitely feels faster, right? Because you see what's going on. You're seeing what they're thinking, but is the actual outcome faster? Like, maybe not. You know,

Polymet took like a minute or two, I'd say at least a minute to do. each of the designs. 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. Wow. Could you believe how similar it looks? And it literally just copied the image I gave.

I can't believe 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. 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 Polymet. but it went a bit deeper. It definitely just literally copied the image I sent,

which is not great, but that's horrible. It's like literally copying it. But I think this is actually really cool. Like I would use this product. I would totally use this product. All right. Let's go back to Polymet, see what we've got. Okay, so Polymet is ready for us.

So I don't know, you know, not super glassy, by the way. I don't know if it's me, but it doesn't feel very glossy. Okay, let's see 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. Wow, the cumulative engagement chart, I think, is really good. Statistical confidence is really interesting. Wow, recent optimizations, AI suggestions. I mean, pretty cool. Pretty cool. Title optimizer, performance comparison.

Wow, showing you all these different things. Like, this is really helpful. It might even be a bit more in-depth than, oh, yeah, than V-0. But pretty cool. what I like about V0 is 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 let's see what it says you're right the current design has some glass like elements but doesn't fully embrace true glassmorphism 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. There's feedback that you get back from V0 versus like you're kind of like, you're shouting into a dark hole with polymint. You just kind of have to hope that it's going to create the thing you want. And I do like that with V0,

you're hearing firsthand, like how it's thinking about things. So let's go see what happens from a visual perspective. From, I don't 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 polymet uglier, like, visually than V-0? I think probably a little bit. Is it slower?

I mean, probably a little bit. But did it end up coming out with a nice product? 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 V0. Would that have gotten us a nicer product? Side by side. Are we comparing apples and oranges here?

I don't know. It's possible. It's possible. But I got to say, based on based on Oh, let's actually, let's see what this. Okay, so it's a little more glassy. Yeah, it's a little more glassy for sure.

Yeah, like this is a beautiful, like this is nice. So what this is missing here on the V0 version is you can hover over and seeing what number you're at. But that was really nice that Polymet did that. That was really cool. So, yeah, like it literally built out the coat. And I think that's helpful.

I really do. I think that's helpful. And that's definitely a pro in the camp of Polymet. So, yeah, but I don't know, man. This looks really, really nice. Like the V0 is a little bit nicer, I think, from a visual perspective. That's the episode. That's the episode today.

I think I wanted you to see me use this product, Polymet, for the first time. I've used V0 before. I've done episodes on V0 before. I'm impressed with V0. It continues to get better. But I'm always on the lookout for, you know, I see AI product designer and that's something I want. So, you know, what's my recommendation?

My recommendation, you know, is it V0? Is it Polymet? Well, the reality is it seems like V0 is a little bit better, but today. But Polymet might be better tomorrow. You know, who knows? So I think it's playing with. these tools. Right now, I'm feeling like V0. I enjoy, I enjoy getting that feedback back. I think the visual design is a little bit nicer. But I think you can use both, right? You can now copy that V0,

put it into Polymet and see what happens. Like, can you make this better? Can you make this pop more? I think that's how you get to. That's how you get the most, like how you get an actual AI product designer is by doing that. It's using a couple tools just like how a lot of you probably use chat GPT, you use Clode,

using GROC now, GROC 3, Gemini, you're going to have three or four tools that you're going to use for AI product design. You're going to have three or four tools you're going to use for AI marketing. You're going to have three or four tools that you're going to use for a lot of these different

categories. So how do you get the most out of them is just you use all of them you realize what's best for each individual product right like clode for me writing is just it's just a better at writing researching you know chat gbt so there's these nuances that make these these products better it's about finding them writing them down and that's that's what i want this podcast you know to be is not just about, you know, giving you startup ideas like, hey, go steal this startup idea for that you can build a SaaS product around YouTube analytics and predictions. Like, I hope someone takes that idea. That's going to work. But it's also about figuring out,

you know, what are the nuances sharing in the comment section, learning together. And, you know, thanks for listening. If you enjoy this, please let me know. I read every single comment on YouTube and let me know 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. And I hope this provided an ounce of creative juices and happy building.