Y Combinator Startup Podcast
00:02:54 · Aaron Epstein, Alex Danilowicz
[00:02:54] S0: How long did it take you to get to the idea that ultimately became Magic Patterns? [00:02:59] S1: It took us about nine months. We were always circling around it. So again, we were doing a component library editor. We were doing kinda Storybook on steroids. We'd had a Chrome extension that allowed you to bring local host and instantly publish it on the Internet as kind of like a feedback tool. That later became a feature of Magic Patterns. And throughout all of that, the main thing that I learned was that classic PG advice, find 10 users who really love you. None of those pivots we had... We didn't have any 10 users that really loved us. [00:03:32] S0: Mhmm. [00:03:33] S1: Where love is defined as they're paying you and they're using you. And then once we launched what became Magic Patterns, those 10 users came very quickly. [00:03:41] S0: How do you stay differentiated in a world where it feels like the design tools keep leveling up significantly every six months? And you guys were one of the the original prompt to design products that are out there. And so how do you find your audience in that and and keep staying ahead of the game, especially as the models continue to improve as well? [00:04:00] S1: I've said this before on video. Like, customers are our religion. [00:04:04] S0: Mhmm. [00:04:04] S1: Talking to them every single day. And then also adapting to new workflows. As an example, we released an MCP about a year ago as part of a hackathon project internally. [00:04:16] S0: Mhmm.
00:04:16 · Aaron Epstein, Alex Danilowicz
[00:04:16] S0: Mhmm. [00:04:17] S1: We didn't think it would go anywhere. And now MCP usage has completely exploded. It's one of the main ways that people interact with Magic Patterns. And so you always have to be almost rebirthing your company to adjust to new workflows, especially in the AI world. [00:04:31] S0: I'd love to see a demo. Can you show us a little bit about how it works? [00:04:34] S1: Yeah. Let's do it. I think one thing that would be good to start is I'll show you how we use it internally. [00:04:39] S0: And you're always dogfooding your product. [00:04:40] S1: Right? We are obsessed with dogfooding. But we never force the dogfooding because then it's... You're not getting actual... [00:04:46] S0: Right. It has to be good enough that you actually want that and you choose that to be your tool. Right?
00:04:46 · Aaron Epstein, Alex Danilowicz
[00:04:46] S0: Right. It has to be good enough that you actually want that and you choose that to be your tool. Right? [00:04:51] S1: Exactly. And then noting when you don't choose it. And so we've been dogfooding, creating our loading indicator for our own product. So, you know, we have WALL E, Eve from WALL E, or some of the... If you ever played portal, the video game, we were thinking through that kind of... What that might look like as a loading indicator. What's in here is everything here is a global chat. So we can make any updates and and make several updates at once. Right? Like, as an example, I could select the two of these. Say, give me a new style of loading indicator that merges the inspiration of the Claude Code icon and the Grok bot. And what's really neat too is, of course, you can use the MCP. So let's go ahead and do that just to kinda show it. I'm gonna go into cursor here. And through using our MCP, I can just go ahead and prompt. Right? Add an ASCII version of my agent. What's really neat is we're seeing lots of enterprises use this where they have so much context, like, in cursor or Claude code, whether it's PRDs or... And and meeting notes. So they can leverage all the skills that they already have, but then instantly kinda put it on this visual canvas to better communicate.
00:04:51 · Alex Danilowicz, Aaron Epstein
[00:04:51] S1: Exactly. And then noting when you don't choose it. And so we've been dogfooding, creating our loading indicator for our own product. So, you know, we have WALL E, Eve from WALL E, or some of the... If you ever played portal, the video game, we were thinking through that kind of... What that might look like as a loading indicator. What's in here is everything here is a global chat. So we can make any updates and and make several updates at once. Right? Like, as an example, I could select the two of these. Say, give me a new style of loading indicator that merges the inspiration of the Claude Code icon and the Grok bot. And what's really neat too is, of course, you can use the MCP. So let's go ahead and do that just to kinda show it. I'm gonna go into cursor here. And through using our MCP, I can just go ahead and prompt. Right? Add an ASCII version of my agent. What's really neat is we're seeing lots of enterprises use this where they have so much context, like, in cursor or Claude code, whether it's PRDs or... And and meeting notes. So they can leverage all the skills that they already have, but then instantly kinda put it on this visual canvas to better communicate. [00:06:10] S0: Mhmm. Yeah. It's interesting. So you've got this powerful canvas in in Magic Patterns, where when that's the best tool for the job, you can be working directly in there. And when you want to be working in code or in cursor or another app, you can just pull directly from that through the MCP.
00:06:10 · Aaron Epstein, Alex Danilowicz
[00:06:10] S0: Mhmm. Yeah. It's interesting. So you've got this powerful canvas in in Magic Patterns, where when that's the best tool for the job, you can be working directly in there. And when you want to be working in code or in cursor or another app, you can just pull directly from that through the MCP. [00:06:26] S1: Yeah. Exactly. And what's cool too is we have so many customers that come up to us and say, I'm using cursor and cloud code, but it gave me local host. I can't share Mhmm. I can't share my prototype with anybody. Yep. Say, oh, well, we have a solution for you. Right? Yeah. So what's cool here is actually we can see my colleague on here as well as the cursor agent from that cursor prompt that we fired off. Right? And so they're working simultaneously. And we can go ahead and just open this up here. We can see this is like that ASCII version of of Claude Code. Right? And kinda playing around, oh, what would it look like with different colors? Now, obviously, this is very Claude code esque. We're just kinda getting inspiration here, to make our own loading indicator. [00:07:06] S0: And it generated this entire page showing off the work that it had done. [00:07:11] S1: Yeah. Exactly. So like one thing that we encourage users to do, and we've seen users do ourselves, is explaining kind of the choices [00:07:19] S0: Mhmm.
00:07:19 · Aaron Epstein, Alex Danilowicz
[00:07:19] S0: Mhmm. [00:07:20] S1: And the different states. So as another example here, you kinda look at this one. We were thinking through, well, does it look like at different screen sizes? What does it, again, look like if it's Claude code? Kinda playing around with, should it look more like a helmet or like a pillow. Right? Again, just brainstorming and exploration. Where we see users get the most value in a tool like ours. [00:07:42] S0: Yeah. I mean, that's, I think, one of the most valuable things at the idea and inspiration stage is just being able to fire off a bunch of different variations. And a lot of times, it's hard to manage those, and they're all in different tabs and stuff. And it seems like Magic Patterns is able to just give you a bunch of nice tabs and options and kind of enumerates everything. It's like like, here's a bunch of color options. Here's body options. Here's different agent options. And it's really cool to do that in a very, centralized uniform way to actually make the tweaks and explore, find what you like, and then be able to move on faster to the next step in the flow.