Y Combinator Startup Podcast
00:29:54 · Stephen Haney, Aaron Epstein
[00:29:54] S0: And I would love to see too, like, what is it actually doing? Because I can... I have AI enabled Kanban boards already. So why why does... What is making it special for construction? I would love to see that as as part of the value prop above. But to your point on on some of the fundamentals, like, very... You know, the bold is here. This looks like it may be an AI created some of it. Here's another great section. So here's one that would be cleaned up a lot by having fewer textiles. So you see, like, you know, one size, two sizes, three sizes, four sizes. That's probably another one too. If you take that down to three, it's gonna look so much better. So let's just try that real quick. And I can... I'll even ask the agent to do it for us. And again, use Paper Snapshot to grab it from the live site, paste it into Paper as editable layers. And then we'll just say... Let me just name this one. Here's another way you can do it. You can say... What was that? It's Cytex. This one we'll give to Cursor. We'll say, hey, Cursor, please clean up the Cytex frame using at most three font sizes and no bold, everything regular or below in weight. [00:30:59] S1: And so you named that frame SciText, and then you just gave it that context clue to the agent.
00:30:59 · Aaron Epstein, Stephen Haney
[00:30:59] S1: And so you named that frame SciText, and then you just gave it that context clue to the agent. [00:31:04] S0: Exactly. Just different ways to kind of tell it what you want it to work on. Yeah. My favorite is actually leaving comments. And I... The thing with I noticed earlier as I was jumping around, you tend to change your selection a lot, and I'll accidentally, like, deselect. So I I love leaving comments. I think it's just the best way to do things. But here we go. So it's starting to work on this one, and it's gonna align... Just, you know, bring bring back some of that vibe coded stuff. Now in Paper, we actually give instructions to the model not to do these these common mistakes. And sometimes people go, like, what's your secret sauce? Like, how... Why is it better? Why does it look better? It's just like, honestly, all we're doing is these basic rules of typography and contrast. Yep. And we we had the more senior designers on the team, like, distill their knowledge into the instructions [00:31:45] S1: That's great. For the model. Yeah. Even that is is very powerful, though. Just putting those guardrails up around what the models are doing can just save a lot of time and energy.
00:31:45 · Aaron Epstein, Stephen Haney
[00:31:45] S1: That's great. For the model. Yeah. Even that is is very powerful, though. Just putting those guardrails up around what the models are doing can just save a lot of time and energy. [00:31:54] S0: Yeah. Like, an expert, you know, kind of guiding the model Right. A little bit is is really helpful. In real life, I might have just done this by hand because it'd be faster. But if you had an entire site that you wanted to go through, for instance, using the agent is really useful. Or if you wanted to pull this back into your code base when you're done Mhmm. The agent can do that Yeah. For you. [00:32:09] S1: This already looks like a huge improvement. [00:32:12] S0: Yeah. I think very simple changes. Right? All we did was pull back the weight of the font, and we consolidated how many sizes there are. To me, it looks much more designed and more intentional. And so if we go pull the original again, here's kind of the... We'll pull up Paper and do a side by side. Now... And this is subjective. Right? And I know somebody probably spent some time on this design, and I think they nailed the content. But by pulling some of these AI out of it, to me, the side... The one on the right feels more trustworthy. It feels more intentional and more designed. [00:32:42] S1: It's interesting you talk about some of those AI tells. Yeah. What are some of the most common ones you've seen? What are the clues when you look at a page or you look at a design and you go, somebody just spit out whatever the model spit out and called it good and moved on?
00:32:42 · Aaron Epstein, Stephen Haney
[00:32:42] S1: It's interesting you talk about some of those AI tells. Yeah. What are some of the most common ones you've seen? What are the clues when you look at a page or you look at a design and you go, somebody just spit out whatever the model spit out and called it good and moved on? [00:32:55] S0: One, I don't think you should do And it's so tempting Yeah. As... Especially, I'm sure if you're, like, a YC founder and you have zero time and you're trying to sell your first... You know, make your first sales, it's probably very tempting to use whatever Claude Design spits out. I don't think you should do it because I I don't think it helps you stand out from the crowd. I think it makes you look like one of a million other projects, and it makes you look less intentional and less like you care. And so I think design is this great differentiator. And if you look at every great company of the last ten, twenty years, basically, all of them have exceptional design. Mhmm. You know? And I think that there's... I can't think of an example that doesn't. You know? And so I think if you wanna be one of those really great companies, you have to put the care in on design and and make sure that you stand out. So AI tells... You know, we talked about the font weight, the font sizes. Those are huge ones to me. [00:33:37] S1: YC's next batch is now taking applications. Got a startup in you? Apply at ycombinator.com/apply. It's never too early, and filling out the app will level up your idea. Okay. Back to the video.
00:33:37 · Aaron Epstein, Stephen Haney
[00:33:37] S1: YC's next batch is now taking applications. Got a startup in you? Apply at ycombinator.com/apply. It's never too early, and filling out the app will level up your idea. Okay. Back to the video. [00:33:51] S0: You've probably seen the the side... Little side swoop of color, like two pixels of color on every card. Yeah. Overusing cards in general. Just 20 cards all over the place. Now these are very easy things to correct too. Just ask the agent, ask Paper to create 20 variations of that layout, and then pick your favorite one, because it's gonna look a lot more thoughtful than just a bunch of cards Yep. All over the place. What what are some of your... Do do you have other examples of Purple. Oh, purple. [00:34:15] S1: Yeah. A lot of gradients, a lot of icons, and, all caps, like, tiny headers. [00:34:21] S0: Oh, the tiny headers. Yeah. It it... [00:34:23] S1: You know what? A lot of it turns out to be widgets for widget's sake. You know? It's it's not something that's actually trying to communicate something important or valuable to help a user understand what the design is trying to communicate. Totally. It's just there to fill up space is what a lot of it feels like. [00:34:39] S0: It's like a insecure designer. The agents are very insecure. They wanna, like, fill it out, and there's, like, lots of little ones and twos.
00:34:39 · Stephen Haney, Aaron Epstein
[00:34:39] S0: It's like a insecure designer. The agents are very insecure. They wanna, like, fill it out, and there's, like, lots of little ones and twos. [00:34:45] S1: Exactly. Like, why do you need that? Well, don't know. It looks like it anchors the corners on all those cards better or something. But, like, does it actually communicate anything? Yeah. Do those numbers mean something? No. They don't. Well, we should just get rid of them then. [00:34:56] S0: Totally. Totally. I think a lot of design is deleting. You know? [00:34:59] S1: It's like Yes. [00:34:59] S0: It's it's kinda nice to overbuild and then pull it back. But a lot of avoiding the agent look is pulling back. [00:35:04] S1: It's hard when, you know, the model spits something out, and then you've gotta go in and edit it. And you have to say, oh, that headline and describe it and all this stuff versus when you can just go in and select it, hit the delete button Yes. And everything snaps into place, it feels like you have so much more control. And the effort required to get it to a more thoughtful place is way, way, way, way less. And that, I think, is incredibly powerful that that doesn't force people to compromise on speed, but they can still get something that looks really, really great and stands out and doesn't feel like the models just spit it out. [00:35:38] S0: Well, sometimes we think about this as the best tool for the job. And sometimes it's prompting, and sometimes it's dragging. [00:35:43] S1: Yeah. You