Paper：面向下一个时代的 AI 原生设计工具

智能体可以帮你提速，帮你省下大量工作，还能替你完成翻译、调整尺寸之类的任务。但我们坚信设计中人的因素至关重要。所以，我们想打造一个让人类能与智能体高效协作的工具。直接照搬 Cloud Design 生成的结果确实很诱人，但我觉得那并不能让你脱颖而出。我认为设计是巨大的差异化优势。看看过去一二十年的每一家伟大公司，基本上都拥有卓越的设计。所以，如果你想成为那样伟大的公司，就必须在设计上倾注心血，确保自己与众不同。

The agents can speed you up. They can save you a lot of work, and they can do tasks like translation or resizing for you. But we're big believers in the human element of design and how important that is. And so, we're trying to create a tool that lets humans work really fast with agents. It's probably very tempting to use whatever Cloud Design spits out. I don't think it helps you stand out from the crowd. And so, I think design is this great differentiator. And if you look at every great company of the last 10 or 20 years, basically all of them have exceptional design. And so, I think if you want to be one of those really great companies, you have to put the care in on design and make sure that you stand out.

今天，我很高兴邀请到 Paper 的创始人 Steven Haney。Paper 是一款 AI 原生的设计工具，正在设计界掀起风暴。我们在 YC 内部已经大量使用 Paper 来处理所有设计工作。我很期待他能向各位展示这款产品的运作方式。Steven，非常感谢你的到来。

Today, I'm excited to welcome Steven Haney, the founder of Paper, an AI-native design tool that's been taking the design world by storm. We're already using Paper a ton here at YC for all of the design work that we're doing internally, and I'm excited for him to show off how the product works to everybody out there. So, Steven, thank you so much for joining.

是的，我很荣幸能来到这里。我经常看这个节目，所以能上节目真的非常开心。感谢你的邀请。

Yeah, I'm honored to be here. I've watched the show a lot, and so, it's really, really nice to be on. Thank you for having me.

也许先开始，给大家介绍一下 Paper 是什么吧。

Maybe to start, tell people what is Paper.

是的，Paper 是一款设计工具，是一款智能体原生的设计工具。这意味着我们使用 HTML 和 CSS 作为实际的渲染引擎，这让智能体非常容易上手，因为它们对 HTML 和 CSS 理解得很好。而历史上很多设计工具都使用自定义渲染引擎，那些对智能体来说就难得多，你会看到更高的 token 消耗、更慢的速度、更低的准确性。所以，我们用 Paper 打造的是一个团队，现在大约 12 人，全是设计师和工程师。我们基本上是出于对设计的热爱而创办了这家公司，现在只是努力为这个新时代打造最好的设计工具。

Yeah, well, Paper is a design tool. It's an agent-native design tool. And what that means is we use HTML and CSS as the actual rendering engine, and that makes it very easy for agents to use because they understand HTML and CSS really well. And historically, a lot of design tools have custom rendering engines, and those are a lot harder for agents to use. And so, you'll see higher token spend, slower times, lower accuracy. So, what we're building with Paper is basically a group of people. It's about 12 of us now. All designers and engineers. We basically started this out of love for design, and now we're just trying to build the best design tool possible for this next era.

是啊，很难想象你们只有 12 个人，因为我经常从所有使用你们产品的人那里听到你们，尤其是很多创始人，他们正在挑选自己想要构建并一直使用的设计工具，而且他们自己从一开始就是 AI 原生的，他们正在寻找最适合自己的 AI 原生工具。

Yeah, it's crazy to think you're only 12 people because I hear about you all the time from everybody who's using you, and especially from so many founders that are just picking the design tool that they want to build and live in all of the time, and doing that from the ground floor being AI-native themselves. They're looking for the AI-native tool that is going to work best.

完全正确。

Absolutely.

那么，也许谈谈你构建 Paper 的灵感是什么，为什么现有的那些工具对你来说不够好？

So, maybe talk about what was your inspiration for building Paper, and why were some of the existing tools that are out there not good enough for you?

这确实源于对设计的热爱。正如我所说，我是以独立创始人的身份起步的，这其实是一个一直持续下去的副业项目。有几个月我都在想，会有人在意 Paper 吗？然后发现，哦，是的，人们确实在意，你知道，这太棒了，它真的起飞了。这是我无论如何都会去做的事情。这确实是我无论如何都会去做的事情，我坚信创业就应该这样。你应该去做你本来就会做的事情，你应该去做你拥有创始人市场契合度的事情。对我来说，这就是我创始人市场契合度最强的地方，因为我喜欢为创意专业人士构建工具。这是我每天醒来都会去做的事情，而且我构建创意工具时不会有糟糕的一天。所以，这优先于市场或竞争对手等一切。然后环顾四周，我想，天哪，你知道，我们是 Figma 的忠实粉丝，如今谈论设计几乎不可能不提 Figma。他们为设计行业做出了巨大贡献。他们现在是一家大公司，在企业客户方面做得很好。我们在想，也许现在是时候出现一款专注于设计师的新工具了，并且真正投入大量时间。AI 智能体带来了如此多的变化。我们能否构建一个智能体原生的、基于 HTML 和 CSS 的工具，打造出下一代工具呢？这就是我们的目标，到目前为止一切顺利。

It really was born from a love of design. As I said, I started as a solo founder, and it was really the side project that just kind of kept going. I had months where I was like, is anyone going to care about Paper? And then it was like, oh yeah, people do care, you know, this is great, it's really taking off. It was the thing I was going to do anyway. It was very much the thing I was going to do anyway, which I really believe starting a startup you should do that. You should do the thing you're going to do anyway, you should do the thing where you have founder market fit. And for me, this is where I had the strongest founder market fit, because I love building tools for creative professionals. It's something I'm going to wake up every day, and like I'm not going to have a bad day building creative tooling. So, that came first, even before the market or competitors or any of that kind of thing. And then looking around, it was like, well gosh, I mean, you know, we're big fans of Figma, you almost can't talk about design without saying, you know, Figma these days. They've done a lot for the design industry. They have a huge company now, and they're doing very well with enterprise companies. And we were thinking, well, maybe there's time for a new tool to focus on the designer, and just really spend a lot of time. There's so much change with AI agents. Can we build something that's agent native, building on HTML and CSS, and just build this, you know, next gen tool? And so, that's kind of what we're going after, and so far so good.

是的，那么作为一款 AI 原生、智能体原生的设计工具，这意味着什么？

Yeah, and what does that mean to be an AI-native, agent-native design tool?

这实际上关乎底层技术。所以，使用 HTML 和 CSS 作为渲染引擎，我们这样做是为了帮助设计师与开发者的交接。我们想，嘿，如果设计师能拥有一个无约束的系统，感觉像 Figma 或 Sketch，但顺便说一句，它是 HTML。他们不必知道这一点。那太好了，交接会更好。事实证明，如果你为人类构建了出色的交接，你也为智能体构建了出色的交接，因为智能体理解 HTML 和 CSS，这些都在它们的训练数据中。所以，当你让智能体处理 Paper 文件时，它实际上只是读取 CSS。智能体完全知道该怎么处理。你基本上是在尝试用可视化界面扩展智能体。有时候我理解 Paper 是一款设计工具，但它也是智能体的可视化界面。我们看到销售、工程师等各类人都在使用它，因为提示并不总是智能体的最佳输入机制。有时你想拖拽和绘制，直接操作会更快。

It's really about the fundamental technology. So, using HTML and CSS as the rendering engine, we actually did it to help with designer-developer handoff. We were like, hey, if the designer can have this constraint-free system where it feels like a Figma or a Sketch, but by the way, it's HTML. They don't have to know that. That's great, the handoff will be better. It turns out, if you build a great handoff for humans, you've also built a great handoff for agents, because agents understand HTML and CSS, and it's in their training data. And so, when you ask an agent to work with a Paper file, it's literally just reading the CSS out. And agents know exactly what to do with it. You try to basically extend the agent with a visual interface. It's sometimes that I get it paper is a design tool, but it's also this visual interface for agents. We see sales folks, engineers, all kinds of people are using it because prompting isn't always the best input mechanism for agents. Sometimes you want to drag and draw and it's just faster to be able to do direct manipulation.

是的，这很有趣，因为随着构建软件变得越来越容易，弄清楚要构建什么以及如何获得构建灵感似乎成了目前最棘手的问题之一，也是最大的瓶颈之一。你认为如何使用 Paper 来解决创意工作流程中的这一部分？

Yeah, it's interesting because as it becomes easier and easier to build software, the figuring out what to build and getting inspiration for how to build it seems to be one of the trickiest pieces right now and one of the biggest bottlenecks. How do you think about using Paper to be able to solve that piece of the creative workflow?

我们看到现在创建的软件比以往任何时候都多，工程团队现在进展神速。我不知道你怎么看，但我并没有觉得软件在变得更好。过去 6 个月里，我还没有遇到过让我惊艳的软件体验。所以这对我们来说很重要，我从小就是软件的粉丝。我喜欢构建优秀的软件。你能给我的最好赞美就是 Paper 是一款真正优秀的软件。所以我希望世界上有更多这样的软件，我希望帮助设计师和有品味的人跟上所有正在创建的软件的步伐。所以，给他们一个能够以提示和智能体的速度运行的工具，而不是仅仅被拖入 IDE 或原型制作中，但仍然能够以更快的速度进行传统设计工作。我认为这真的非常重要。

We see there's more software than ever being created and engineering teams are moving so fast now. And I don't know how you feel about this, but I haven't felt like the software is getting better necessarily. I haven't had a great software experience in the last 6 months that blew me away. And so it's important for us, like I grew up as a fan of software. I love building great software. The best compliment you can give me is that Paper is really great software. And so I want more of that for the world, and so I want to help designers and people with taste keep up, you know, with all of the software that's being created. And so giving them a tool that can move at the speed of prompting and of the agents, you know, rather than being just pulled into an IDE or just pulled into prototyping, but being able to still do the traditional design work at a faster pace. I think it's really, really important.

我很想看一个演示。你能给我们展示一下它是如何工作的吗？

I'd love to see a demo. Can you show us how it works?

好的，我们开始吧。如果你用过画布工具，这个界面会非常熟悉。有时候我喜欢从视觉元素开始。因为基本上我们是用浏览器来渲染，所以我们也能很容易地渲染着色器。

Yeah, let's jump in. So it's a very familiar interface if you've used canvas tools. Sometimes I like to start with the visual things. So because we are using basically the browser to render, we can also render shaders really easily.

着色器基本上就是我们构建的 WebGL 动画。这个叫 Paper Shaders，是我们整理的一个库。它完全开源，完全，你知道，随便你怎么用都行。而且着色器特别好玩，品牌设计师们很喜欢，因为你可以得到各种不同的视觉效果。这只是一个着色器配上不同的设置，所以你可以做各种花样。

And shaders are these basically WebGL animations that we build. This is called Paper Shaders. It's a library we put together. It's fully open source, fully, you know, feel free to use it for whatever you want to do. And the shaders are just so fun and brand designers love these because you can get all kinds of different looks. This is just one shader with different settings. And so you can do all kinds of stuff.

我知道在 YC，你们一直在用

I know at YC, you guys have been using

我们一直在用这些，我们很喜欢。

We've been using these all the time. We love it.

而且我觉得，你知道，对我们来说，而且我想很多人，这可能是他们第一次接触使用 Paper。这感觉非常现代、前沿，一年前还很难做到。然后你们把这个做得非常简单，而且原生集成到产品里，以至于现在到处都在用，因为太容易了，对吧？

And I think, you know, for us and and I imagine a lot of people out there, this is probably their first introduction to using Paper. This is something that feels very modern, cutting edge, that would have been really difficult to do a year ago. And then you guys have made this really simple and native to the product to the point where it's showing up everywhere because it's so easy to do it now, right?

那部分是我们的希望，就是能不能让设计师更容易上手？因为如果你是个设计师，整天泡在传统设计工具里，你想创建一个着色器效果，你想描述 AI 加载状态是怎么工作的。我一直听到的就是，我需要为 AI 做加载状态，我该怎么做？所以我们想，不如给大家这些可以定制的动画效果，你知道，不只是用现成的，你还可以进去调整，让它们变成你自己的。你可以做各种酷炫的东西。当然你可以用混合模式来创造组合。嗯，而且还有一些更微妙的特效也很受欢迎。这是半调网点。你可以把其他东西拉进效果里。所以这是把所谓的神经噪声拉进半调网点，你可以尝试不同的东西，得到不同的效果。嗯，我们花了大量时间。我们真的研究了真实的纸张，研究物理效果的随机性，然后尝试在代码里建模。所以我觉得我们的着色器库能脱颖而出，原因之一就是我们花了离谱的功夫让它尽可能好。品牌设计师真的很喜欢这个。比如，你知道，一个例子是 Quarter。不知道你们知不知道 Quarter 海报。嗯，那是这个团队做的非常酷的海报，他们做的是，我觉得是财报。他们现在把很多都改成用 Paper 做了，因为他们能快速得到那种复古的感觉。所以我喜欢这个。他们做的作品真的很酷，我很荣幸他们用 Paper 来实现这些海报。

That was part of our hope, was like can we make this more accessible to designers? Because if you're a designer and you're, you know, living in a traditional design tool all day, you want to create a shader effect. You want to describe how an AI loading state is working. And that's what I kept hearing, was I need to make loading states for AI and how do I do it? And so we just thought it'd be nice to give people these animated effects that they can customize and, you know, not just use the out of the box ones, but you can get in here and like tweak things and make them your own. And you can do all kinds of cool stuff. You can do blending modes, of course, to create combinations. Um, and you can also, these have been really popular, is some of these more subtle effects. This is a halftone dots. And you can pull other things into the effect. So this is pulling this, what we call neuro noise, into the halftone dots, and you can try different things and get different effects. Um, and we spent so much time. We actually studied literal paper to study the randomness of, you know, actual physical effects, and we try to model that in code. And so I think it's one of the reasons our shader library stands out, is we go to ridiculous degrees to make it as good as we possibly can. And so brand designers really love this. So like, you know, one example is Quarter. I don't know if you guys know the Quarter posters. Um, they are really, really cool posters that this team makes, that they do, I think it's like earning reports. And they've transitioned a lot of these to be built in Paper now, because they can get this cool retro, you know, vibe that, and really fast. So I love this. The work they're doing is really cool, and I'm like honored that they're using Paper to achieve some of these posters.

是的，真的很酷。我们在 Startup School 里用过，YC 的设计负责人 Ev 实际上做了定制的动画着色器，带有 YC 品牌标识和人名，做成门票，你知道，当人们被录取时，你可以玩一下、做动画，然后发给他们，对收到的人来说是很棒的体验。感觉非常贴心、用心、设计感十足，而且它也能创造出人们愿意分享的东西，这有助于传播，也都是因为设计和着色器。

Yeah, it's really cool. We've used it for, we have Startup School, and so Ev, who leads design here at YC, has actually created custom animated shaders with the YC branding with people's names on them, tickets that are, you know, you can play with and animate when people get accepted and send it to them, and it's a great experience for the person receiving it. It feels very thoughtful and intentional and highly designed, and it's also creates something that's very shareable that people want to share out, which helps to spread the word also, all because of the design and because of the shaders.

这是提升视觉效果、让它更特别一点的非常快的方法。

Really fast way to elevate the visuals and help it be a little more special.

所以，着色器在品牌设计师中非常受欢迎。我们还有，这个对 Paper 来说可能不太为人所知。我们实际上有一个很棒图像生成库，你可以同时使用各种模型。所以，我不知道，我们就做一个沉思的男人凝视月亮的插画。你可以想象用在品牌物料或者你正在做的任何东西上。所以，这会同时使用四个不同的模型，你可以快速探索你需要的任何插画的可能性空间。

So, shaders are very popular with the brand designers. We also do, this is kind of like a lesser known thing to Paper. We actually have a really great image generation library where you can use all kinds of models all at once. And so, I don't know, we'll just do a thoughtful man staring at the moon illustration. You can imagine for a brand piece or whatever you're working on. And so, this will use four different models at once, and you can quickly explore the possibility space of whatever kind of illustration you need to do.

那太酷了。是的，我看到你那里设置成了 variety pack。是那个让你一次得到四个的吗？

That's very cool. Yeah, so I see you have it set to variety pack there. Is that the thing that gives you the four at once?

如果你愿意，你可以选某个模型。它们各有不同的优缺点，或者你可以用 variety pack，我们会轮换里面的模型，因为新模型总是不断出现，它只是让你快速探索。你可以向它提供输入。你可以，比如，你知道，我会把这个着色器复制成一张图片，然后你可以把图片喂进去，说请让这个更鲜艳一点。所以，你可以组合这些做各种不同的工作流，你知道，非常非常快地创建很酷的图形。同样，你还可以矢量化。你可以做这个，提取颜色真的很，我们来做这个。所以，智能体做了一个非常多彩的东西，我可以提取颜色，它就会提取出来，所以我用这种方式快速探索想法。嗯，还能生成新纹理之类的。所以，这是 Paper 的品牌侧。这是图形。我们发现所有设计师都需要制作品牌资产。他们需要做，你知道，社交媒体帖子之类的。

You can pick a certain model if you want to. They all have different strengths and weaknesses, or you can do the variety pack and get, we kind of rotate which models are in there just as new models are always coming out, and it just lets you quickly explore. And you can provide inputs into it. You can, that's like, you know, I'll copy this shader as an image, and then you can feed the image into it and make this more colorful, please. So, you can do all kinds of different workflows combining these, you know, things to create really cool graphics really, really fast. Along the same lines, you can also vectorize. You can do this, extract colors is really, let's do this one. So, the agent made a really colorful thing, and I can extract the colors, and it just pulls out about, and so I explore ideas very rapidly this way. Um, and generate new textures, things like this. So, this is kind of the brand side of Paper. This is the graphics. And what we find is like all designers need to make brand assets. They need to make, you know, social media posts or whatever it is.

这也很有意思，因为，你知道，我觉得很多人把 Figma 当作产品设计工具来用和看待。

Which is interesting also because, you know, I think a lot of people use and think of Figma as product design.

嗯。

Mhm.

而且嗯，它当然能做很多品牌设计元素，但一开始并不是那样。看起来你可以做产品设计，而且这里还有很多很酷的工具来做品牌设计工作。

And um it certainly can do a lot of brand design element, but didn't start as much that way. And it seems like you can do product design and there's all these really cool tools to do a lot of brand design work, too.

是的。

Yes.

还有平面设计，你知道，传统上我觉得用很多这些工具更难。

And graphic design, which, you know, traditionally I think has been more difficult with a lot of these tools.

是的，这是我们价值观的一部分。我们两者都喜欢，你知道吗？所以，我觉得产品设计很有趣，但我们也会一直做品牌设计和图形。说实话，我们对着色器的想法是，嗯，我们花的是我们的营销预算。我们不把这当作产品开发。我们想的是，与其买广告，不如为世界做一个有用的库，嗯，把精力和钱花在构建着色器库上。它得到了很多关注，效果很好。同样，我们开发了一款字体 Paper Mono，作为我们即将推出的新字体。我真的很自豪。它真的非常好。嗯，我们发现没有一款等宽字体是那种全能型的，既能用于营销，又能用于代码。大多数都是为终端设计的。所以我们想要一款能作为品牌一部分的字体。所以我们做了 Paper Mono。它几周后发布。这对我们来说就是营销。你知道，与其买广告，不如造一款字体。

Yeah, it's part of our values. We love both, you know? And so, I think the product design is very interesting, but we'll always have the brand design and the graphics, too. To be honest, the way we think about the shaders is um we spend our, this is our marketing budget. We don't think of this as product development. We think of it, instead of buying ads, let's make this useful library for the world um and spend that effort and that money on building the shader library. It gets a lot of attention. It works really well. Similarly, like we develop a font, Paper Mono, as a new font that we're launching. I'm really proud of it. It's really, really good. Um, and we found there's no mono font that is just kind of an all-rounder that you can use in marketing, that you can use in code. Most of them are built for the terminal. And so, we wanted one that you can use as part of your brand. So, we made Paper Mono. It's launching in a couple weeks. That's marketing for us. That, you know, instead of buying an ad, let's build a font.

对世界更好，对吧？所以，YC 的 Eva 前几天晚上在纽约市的一个晚宴上，遇到一个穿着 Paper Mono 衬衫的人，我觉得那太酷了。

Better for the world, right? So, Eva at YC was at a dinner in New York City the other night, and she ran into someone wearing a Paper Mono shirt, which I thought was so cool.

因为这种衬衫全世界大概只有一百件吧。

Because there are only, I don't know, a hundred of these in the world.

是啊，怎么才能弄到一件？

Yeah, how do you get one of these?

嗯，我们可以给你弄一件。我们会给你寄一件过去。我们想开一个周边商店，你知道，Paper 周边商店。但这是 Paper Mono。我们很快会推出一个很棒的小型网站。我们在数字的可读性上花了很多时间，因为这是很多等宽字体真正挣扎的领域。我们只是觉得这是一个非常、非常易读、非常实用的等宽字体。所以，我们对此真的很兴奋，对吧？这太有趣了。基本上，我们做这些事情只是作为我们营销的一部分。

Yeah, well, we can get you one. We'll send you one over. We want to set up a merch shop, you know, Paper merch shop. But this is Paper Mono. And we have a great mini site launching soon. We spent a lot of time on the legibility of numbers, because that's an area that a lot of mono fonts really struggle with. We just think this is a very, very legible, very usable mono font. So, we're really excited about this, right? It's so fun. We get to do these things as just part of our marketing, basically.

你提到这个产品最初是为了帮助解决设计到开发的交接问题。是的。给我们展示一下你是如何在产品中做到这一点的。

You mentioned that the product started to help solve the design-to-dev handoff. Yeah. Show us how you're able to do that in the product.

嗯，是的。所以，它最初是，“嘿，这是代码。这字面上就是一个 React 组件。我们为什么不让你把它复制为 React 组件呢？”所以，我们现在看到的这个着色器，你可以右键点击并复制为 React。当你粘贴时，你得到的就是我们看到的字面代码。所以，这只是一种非常快速的方式，比如，“嘿，设计师做了这个很酷的动画。他们把它调得完美无缺。他们是设计师，对吧？”然后让他们把它复制出来并发布。所以，我们看到这些在互联网上到处流行。人们发布这些 React 组件。但它更进一步。所以，你在 Paper 中看到的任何东西都是代码。你知道，这个里面有盒子的框架就是代码。它基本上已经是一个网站了。所以，你可以把它复制为 Tailwind，或者复制为 React，然后直接取出代码。那是我们的起点。那已经相当不错了。我们已经看到一些人在使用它。

Well, yeah. So, it started as, "Hey, this is code. This is literally a React component. Why don't we let you copy it as a React component?" And so, this shader that we're looking at right now, you can right-click and copy as React. And when you paste it, you get the literal code that we're looking at. And so, this was just a really fast way of like, "Hey, the designers made this really cool animation. They've dialed it in perfectly. They're the designer, right?" And let's let them copy that out and ship it. And so, we've seen these take off all over the internet. People shipping these React components. But it goes further. So, anything that you're looking at in Paper is code. You know, this frame with this box inside of it is code. And it's basically a website already. And so, you can copy it as Tailwind, or you can copy it as React and just grab out the code. That's where we started. And that was pretty good. We already saw some people using it.

然后在，是什么时候？去年 2025 年 12 月，Claude Code 爆发了。

And then in, what was it? Last December 2025, the Claude Code explosion happened.

而我没想到设计师会进入终端。我从没想过我们会看到这种情况。

And I didn't think designers were going to be in terminals. I never thought that would be a thing we'd see.

但我们确实看到了。所以，那是一个时刻，我们想，“天哪，我们得进入桌面端。”那时，我们还没有桌面应用。所以，就像，“天哪，我们得进入桌面端。那是现在事情发生的地方。本地仓库，设计师有仓库，他们在学习 GitHub。让我们成为这场爆发的一部分。”我们看待它的方式有点像新的智能体栈。我的意思是，你会看到，你知道，我有 Cursor，我有 Claude Code，你有多个智能体。你有 Paper 作为与智能体通信的视觉方式。然后，也许你有 GitHub 或者你知道，代码审查。那就是我们现在看到构建者在使用的东西。

But we clearly did. And so, that was the moment where we were like, "Gosh, we got to get onto the desktop." At that point, we didn't have a desktop app. So, it was like, "Gosh, we got to get onto the desktop. That's where things are happening now. Local repos, designers have repos, they're learning GitHub. Let's be part of this explosion." The way we see it is kind of the new agent stack. And what I mean by that is you'll see, you know, I have Cursor, I have Claude Code, you have multiple agents. You have Paper as a visual way to communicate with the agents. And then, maybe you have a GitHub or you know, the code review. That's what we see builders using now.

我的意思是，你看到的也是这样吗？比如，最新的 YC 批次？

I mean, is that what you see, too? Like, the newest YC batches?

是的，我们看到的很多都是这样。我们甚至看到很多这样的功能被整合到单一应用中。我们在 Conductor 的朋友，你可以直接推送代码、合并代码，做你需要的一切。

Yeah, that's a lot of what we see. And we even see a lot of that getting rolled into single apps. Our friends at Conductor, you can push code and merge code and do everything that you need directly.

是的，就是这样。是的，我也开着 Conductor。是的。

Yeah, there we go. Yeah, I have Conductor up, too. Yeah.

直接从应用里。所以，越来越多地，它被整合到应用中，而不是让多个离散的应用作为栈的一部分。

Directly from the app. And so, more and more, it's kind of being consolidated into apps rather than having multiple discrete apps as part of the stack, too.

我们也看到了这一点。Conductor 和 Paper 现在是社区中很多人一起使用的配对。我觉得这太酷了。我喜欢 Conductor。这是一个很棒的产品。

That's what we see, too. And Conductor and Paper are this pairing right now that a lot of people in the community are using both together. I think it's so cool. I love Conductor. It's a great product.

但我们看到了 Claude Code 的发生，比如，让我们进入桌面端。我们在桌面应用中内置了一个 MTP 服务器，我会给你演示一些它能做的事情。我们用 Conductor 来做这个。为什么不呢？我就说，“嘿，Conductor，在 Paper 中，请做一个小的测试框架，向 YC 问好。”我会展示它在做什么。我们会进入更复杂的案例，但只是为了展示基本技术是如何工作的。当智能体使用 Paper 的 MTP（我们会把它放在屏幕的右半部分），我们给它工具调用，比如，“嘿，哪些字体可用？这个页面的基本设置是什么？”然后它字面上运行工具，比如，写 HTML。这字面上是，你知道，它是 JSON 格式，但那里它字面上是在给我们发送 HTML。

But we saw this Claude Code happening, like, let's get on the desktop. We built an MTP server into our desktop app, and I'll give you a demo of some of the stuff it can do. Let's use Conductor for this. Why not? I'll just say, "Hey, Conductor, in Paper, please make a small test frame saying hello to YC." And I'll show you what it's doing. We'll get into more complex cases, but just to show you how the basic technology works. As the agent uses the MTP of Paper, which we'll put on the right half of the screen, we give it tool calls, like, "Hey, which fonts are available? What's the basic setup of this page?" And then it literally runs tools, like, write HTML. This is literally, you know, it's in JSON format, but there it's literally sending us HTML.

嗯。

Mhm.

而 Paper 引擎能够直接接受 HTML。它知道如何处理它。那里没有翻译。智能体写 HTML，Paper 能渲染 HTML，你不必在格式之间来回切换。这样做能节省你的 token。它让运行更快，而且你得到的奇怪幻觉更少。这就是我们真正起飞的地方，因为人们在做设计到代码，他们在做代码到设计。

And the Paper engine is just able to take HTML. It knows what to do with it. There's no translation there. The agent writes HTML, Paper can render HTML, and you don't have to switch back and forth between formats. What that does is it saves you tokens. It makes it run faster, and you just get less weird hallucinations. And this is really where the moment we took off, because people are doing design to code, they're doing code to design.

我再给你一个 Cursor 中的例子。这是我们实际的 Paper 代码库，我就说，“嘿，你能把那个 colors.css 放到 Paper 画布上作为样式指南吗？”所以，这是我们来自 Paper 的实际 CSS 文件，代码库 Paper，不是产品。Cursor 会获取它，然后把它渲染到画布上。所以，我们看到很多人在做，你知道，审计他们的代码库，看看有什么。你可以做组件架构，要求图表。它真的把设计工具带入了栈的其余部分。我们太习惯于设计工具在别的地方了，对吧？

I'll give you another example in Cursor. This is our actual Paper code base, and I'll just say, "Hey, can you put that colors.css onto the Paper canvas as a style guide?" So, this is our actual CSS file from Paper, the code base Paper, not the product. And Cursor is going to take that and then render it onto the canvas. And so, we see a lot of people doing, you know, auditing of their code base, what exists. You can do component architectures, ask for diagrams. And it really just brings the design tool into the rest of the stack. We're so used to the design tool being over somewhere else, right?

而且它们之间有一堵墙。这就像设计工具现在成了整个栈的一部分。

And having this wall between it. And this is like the design tool is now part of the entire stack.

是的。这差不多就是这里的目标。

Yeah. It's kind of the goal here.

是的，我的意思是，像你所说的那种交接中一直存在的问题是，设计师会设计一个东西，然后把它交给开发人员，然后也许它实际上不会按照设计师最初在画布上工作时的意图来构建和发布。

Yeah, I mean, one of the things that's always been broken with that handoff like you're talking about is designers would design a thing and then they give it to the developers and then maybe it wouldn't actually be built and shipped in the way, you know, the designer originally intended when they were working in the canvas.

是的。

Yep.

或者即使是这样，事情也会失去同步，代码会演变，永远不会被包装回设计中。所以，什么是真相之源？而这里真正好的是代码是真相之源，两个系统都知道如何在同一个代码库上工作。

Or even if it was, things would just get out of sync and the code would evolve and it would never get wrapped back into the design. Which and so it's what is the source of truth? And what's really nice about this is the code is the source of truth and both systems know how to work on that same code base.

完全正确。是的，我们看到很多团队维护他们设计系统的两个副本。

Exactly. Yeah, we see so many teams maintain two copies of their design system.

是的。

Yeah.

而让它们保持同步不是一个可处理的问题。这真的不可能。所以，你有很多维护成本来保持两者更新，而且你会有准确性问题。所以，我们从新公司，更多的智能体式构建者那里看到的是，他们把代码库视为真相之源。

And it's not a tractable problem to keep them in sync. It's impossible, really. And so you have a lot of maintenance cost with keeping both of them updated and you just have accuracy problems. So what we see from the newer companies, the more agentic builders, is they are treating the code base as the source of truth.

嗯。

Mhm.

而且，你知道，我们还没有在 Paper 中提供组件。这是一个常见的抱怨，比如人们非常想要组件，我们正在努力解决这个问题。

And, you know, we don't have components in Paper yet. It's a common complaint, like people want components really a lot, and we're working on that.

但你不需要它们，因为你的代码库是事实来源，你可以按需调用东西。我们还更进一步，构建了一个 Chrome 扩展，你可以抓取你的实时网站，将其复制到 Paper 画布中，这是一个很好的方式，从用户看到的内容开始，并在此基础上进行迭代。

But you don't need them because your code base is the source of truth and you can kind of summon things in as you need them. And we took that a step further too, we built a Chrome extension where you can grab your live site and copy that into the Paper canvas, which is a really nice way to start from what your users are seeing and build on top of it and iterate.

也许这是一个很好的过渡。我们应该审查一些用户提交的网站，然后我想用那个功能把其中一些拉进 Paper，做一些调整，看看我们能实时编辑什么，来尝试改进一些网站。

Maybe that's a good segue. Should we review some user-submitted sites and then I would love to use that feature to be able to pull some of them into Paper and make some tweaks on it and just see what we can live edit to try to improve some of the sites.

我很乐意。这总是节目中我最喜欢的部分。

I would love to. It's always my favorite section of the show.

好的。

Okay.

太棒了，我们开始吧。

Awesome, let's do it.

我们这里第一个是 Legion Health，精神科服务低至 0 美元（含保险），在线药物管理，针对多动症、抑郁症、焦虑症、双相情感障碍等。嗯，我不知道。当我第一次看到这个，我看到顶部那个小药丸，这让我觉得这就像是一个 vibe-coded 的东西，因为它太符合我们看到的智能体生成的那种风格了。

So the first one we got here is Legion Health, psychiatry as low as $0 with insurance, online medication management for ADHD, depression, anxiety, bipolar disorder and more. Um I don't know. When I first look at this, I see the little pill up there at the top, and this kind of it makes me think this was just like a vibe-coded thing cuz it matches so much of the style that we see um that the agents are just spitting out.

这里肯定有打磨和完成度的问题。我觉得像这些部分留一点空隙这样的小细节。药丸非常普通。不过总的来说，我能理解价值主张。

There's definitely like a fit and finish thing here. I think little things like how these sections kind of leave a little gap. The pill is very generic. I think overall though, the I can understand the value prop.

嗯。

Mhm.

它看起来非常清晰，我认为这很棒。

It looks very clearly, which I think is great.

设计的很大一部分也是，你能理解发生了什么吗？

A big part of design too like can you comprehend what's going on?

它在右边展示了好处，比如

It shows the benefit over on the right of like being

在田野里非常开心之类的，我猜。

Being very happy in a field or something, I guess.

是的，你过着美好的生活。

Yeah, you're having a great life.

是的。

Yeah.

嗯，所以，我认为这些部分是有效的。我认为更多的是要收紧，你知道，收紧一些设计会让品牌感觉更严肃、更高端、更值得信赖，我认为。

Uh so, I think like those parts are working. I think it's more about just tightening up um here again, you know, it tightening up some of the design would really help the brand feel more serious, more elevated, a little more trustworthy, I think.

是的。

Yeah.

嗯，这感觉，你知道，我现在不确定我是否信任这个品牌。嗯，这是一个你必须拥有信任的领域，对吧？

Um this feels, you know, I don't know if I trust this brand right now. Uh and this is a area where you have to have trust, right?

是的，那么你看这个的时候，是什么让你不信任它？

Yeah, so what is the thing when you look at this that makes you not trust it?

一些设计元素，比如对齐、对比度选择。它们感觉可能是 vibe-coded 的，或者像有人没有花太多注意力在这上面，然后你的思绪会想到他们还有什么没注意到的。另一件事是，这一定是一家 YC 公司，但我在这里没有看到，我会说这是一个很好的点，值得提出来

Some of the design elements is like the the alignment of things, the contrast choices. They feel maybe vibe-coded or like somebody didn't spend a lot of attention to this, and then your mind goes to what else don't they spend attention on. The one other thing is like this must be a YC company, but I don't see that here, and I would say that'd be a great thing to call out

作为一点社会证明

as a little bit of social proof

是的。

Yeah.

或证据。但这很好。我的意思是，这里有很多值得喜欢的地方。我只是会稍微打磨一下完成度。

or evidence. But like this is nice. I mean, there's a lot to like here. I would just I would work on the fit and finish a little bit.

我给你看 Paper Snapshot。Paper Snapshot 是一种从你的实时网站抓取内容的方法。它取代了截图。所以，我们抓取这个部分，因为我认为这是一个很酷的部分，可以处理。然后我们把它粘贴到 Paper 中。嗯，这些都是实时部分，对吧？所以，这不是截图。这是实际的东西，你可以进来编辑，你可以像 alt-drag 一样得到它的另一个副本，所有这些。嗯，所以，让我们让智能体来处理这个。我喜欢做的一件事是，实际上只是让它生成一堆变体。

I'll show you Paper Snapshot. Paper Snapshot is a way to grab content from your live site. This replaces taking screenshots of things. So, we'll just grab this section cuz I think this is a cool one to work on. And we'll paste it into Paper. And um these are all live sections, right? So, this is not a screenshot. This is actual stuff that you can come in here and edit, and you can like alt-drag and get another copy of it, all these things. Um so, let's ask the agent to work on this a little bit. And one of the things I like to do is actually just ask it for a bunch of variations.

嗯。

Mhm.

所以，我们用，嗯，Conductor。嘿，Conductor。嗯，这是用 GPT 5.5。你能为我在 Paper 中的选择制作三个新的变体，专注于工艺、对齐和对比度选择，以提升视觉效果吗？

So, we'll use let's uh Conductor. Hey Conductor. Uh this is using GPT 5.5. Can you make three new variations of my selection in Paper focusing on the craft and alignment uh and contrast choices to elevate the visuals.

你可以做很多提示，但我经常发现简单的提示就很好，说实话。

You can do a lot of prompting, but I often find like simple prompting is is fine, honestly.

这有什么真正强大的地方？有几件事。嗯，第一，我喜欢这种一次性生成一堆不同变体的概念。这是获得灵感的最佳方式。有时候，你知道，你有一种你想要的感觉，但你并不真正知道。这是一个很好的方式，看一堆东西，然后说，我喜欢这个里面的那个。我喜欢这个里面的这个。然后组合起来，取得更多进展，更快，而不是陷入创意低谷。然后另一件很酷的事情是，你能够直接说，“嘿，画布上我的选择”

What's really powerful about this? A couple things. Um one, I love this concept of just spitting out a bunch of different variations. It's the best way to get inspiration. And sometimes, you know, you have a sense of what you want, but you don't really know. And this is a great way to look at a bunch of things and go, I like that from this one. I like this from this one. And combine it and and make so much more progress so much faster rather than being stuck in that creative rut. And then the other thing that's really cool is you're able to just say, "Hey, the thing that is my selection on the canvas

是的。

Yeah.

Paper。

paper.

它知道那是什么。现在它能够处理那个，这真的很强大。

And it knows what that is. And now it's able to go to work on that, which is which is really powerful.

我想我选错了。抓取那个，嗯，YC 卡片。

I think I had the wrong selection there. Grab the uh the YC card.

让我在那里重新启动它。再用我的选择一次。哦，我看到发生了什么。它用 HD 内容改变了它。嗯，哦，实际上，你知道吗？这是一个很好的方式展示我们能做的另一件事。所以，我们可以在这个帧上留下评论，说，嗯“请为这个内容制作三个新的变体。探索布局以获得视觉冲击力。”相反，我要做的是，我留下了一个

Let me let me restart it there. One more time using my selection. Oh, I see what happens. It's it changed it um with the HD content. Um oh, actually, you know what? This is a good way to show another thing we can do. So, we can leave a comment on this frame and say, um "Please make three new variations of this content. Explore the layout for visual impact." And instead, what I'll do is I left a

在 Paper 中的评论

comment in Paper

嗯哼。

Uh-huh.

然后我现在切换到智能体，说，嗯“请处理我在 Paper 中的评论。”只有一个。这将是另一种你可以定位的方式。你可以想象有一个大的设计，留下你所有的反馈，然后让你的智能体处理它。

and I'll switch over to the agent now and say, um "Please address my comments in Paper." There's only one. And this will be another way that you can kind of like target. It's you can imagine having a big design and leaving all of your feedback and then just setting your agent on it.

是的。让它运转，你知道。

Yeah. Letting it spin, you know.

但我们看到很多人让这些通宵运行。

But we see a lot of folks are leaving these running like overnight.

他们在设置循环

They're setting up loops

嗯。

Mhm.

一个智能体生成数百个变体。实际上，对我们来说，像智能体规模那样扩展我们的服务器等等是一个挑战。他们做的工作比我预想的多得多。嗯，这太酷了。然后他们现在进来，他们策展，你知道，他们进来，哦，那是个好主意。那是个好主意。让我把这些东西组合在一起。这有点像这种新的策展设计过程，我认为非常有趣。

of of an agent just generating hundreds of variations. And it's actually a challenge for us to be like agent scale with our servers and everything. Like they're doing a lot more work than I thought they were going to be doing. Um and it's so cool. And they they now they come in and they curate, you know, they come in oh, that's a good idea. That's a good idea. Let me combine these things together. And it's kind of this new curation design process I think is really interesting.

想到这样一个世界，你只是进去，在作品上留下一堆评论，你去睡觉，早上醒来，它们要么都被处理了，要么有很多迭代供你选择，就坐在那里等着你，这太酷了。

It's so cool to think about this world where you just go in, you leave a bunch of comments on the work, you go to bed, you wake up in the morning, and they're all either addressed or lots of iterations for you to choose from are just sitting there waiting for you.

完全正确。我认为这真的很酷。

Exactly. I think it's really cool.

这是一个新世界。

It's a new world.

我发现它会做我知道但不会想到的事情，因为我太忙了。所以它有点像让我扩展自己一点，让我一天有更多时间，因为我可以把它放在这些可能更模板化的任务上，或者我只是没有时间同时做四件事。所以让我设置智能体来处理它。

I find that it'll do things that I know, but I wouldn't have thought of cuz I was too busy. And so it kind of like it lets me scale myself a little bit and have more time in my day because I can just set it on these tasks that are maybe more boilerplate or I just don't have time to do four things at once. And so let me set the agents on it to to go address it.

所以这是，嗯，5.5。它现在正在处理想法，你会看到它迭代。它可以截图。所以它会注意到像对齐没有，它正在相互碰撞。它会在进行过程中自我修复。

So it's uh this is 5.5. It is working through ideas now and you'll see it iterate. It can take screenshots. So it'll notice things like that alignment isn't it's running right into each other. It'll fix itself as it goes through.

嗯，而且

Um, and

是啊，这很酷。

Yeah, that's cool.

好的，所以它实际上在这里吐出了一个变体，但那里的对齐有点乱，而且它还在工作。所以一旦它给你东西，事情并没有结束。这是一个迭代的过程，对吧？

Okay, so it's actually spit back a variation here, but the alignment's a little screwed up there and it's still working. So it's not done once it gives you something. It's an iterative thing that's happening here, right?

它的工作。是的，而且智能体也在不断进步。比如，我可以看到第一次它把文字跑到了卡片上。它通常会捕捉到并纠正，或者如果没有，你可以直接告诉它，嘿，纠正文字溢出。

Its work. Yeah, and it can do agents are getting better at this too all the time. For instance, I can see like the first shot it ran the text over the cards. It'll usually catch that and correct it or if it doesn't, you can just, you know, tell it hey, correct the the text overflow.

嗯。

Mhm.

嗯，让我这样做。我们设置为适应。然后我们回到指挥家。请处理任何文字溢出问题。我注意到的另一件事是，模型总是在变得更好，而且它们有不同的优势和劣势。

Um let me do this. Let's set to fit. And we'll pop back in conductor. Please address any text overflow issues. The other thing I noticed too is is the models are always getting better and they have different strengths and weaknesses.

嗯。

Mhm.

所以我经常用快速模型来做这样的演示，它们往往犯更多错误。所以，你知道，如果你真的在做这件事，你可能会用一些处于前沿的东西，那些会带来更好的性能。

And so I I often use fast models for demos like this and they tend to make more mistakes. And so, you know, if you're doing this for real, you're probably using something that's right at the cutting edge and those will deliver, you know, better performance.

是啊，你最近常用的模型是什么？

Yeah, what are your go-to models these days?

所以 Fable 是一个很棒的，你知道，我认为那可能是目前最好的视觉品味。

So Fable is a wonderful, you know, I think that's probably the best visual taste right now.

是啊。

Yeah.

呃，它非常慢。这就是为什么我不用它做演示。我实际上经常用 Cursor 的 Composer 2.5。就速度而言，它是一个非常好的模型。质量非常好，非常精确。5.5 通常也是一个很好的平衡。所以，我会换着用。我认为如果我需要纯粹的品味，那就是 Fable 和 Anthropic 的模型。如果我要追求精确，或者我有像“嘿，我有 100 个画板，我需要一个任务来遍历整个列表”这样的需求，我可能会用 Composer。呃，它只是做得非常精确。我发现 Cursor 是一个非常好的工具。它不太懒。它经常启动子智能体来完成任务。所以，我会换着用。所以，这里它给了我三个不同的想法，你知道吗？我认为从这里开始，我通常会花更多时间在确切想要什么上，然后给它更多方向。但是，我可能会开始分支。我可能会想，“哦，我喜欢这个。我喜欢，你知道，我有点喜欢这个列表。这实际上很容易阅读。”我有点喜欢这个卡片布局，实际上喜欢突出显示一张卡片，旁边有其他卡片，这很好。我可能会开始分支。我认为它的力量在于，你可以让五个智能体去生成五个更多的变体，然后找到一个真正符合你目标的。

Uh it's very slow. That's why I don't use it for demos. I use Cursor's Composer 2.5 actually a lot. It's a very good model for the speed. Quality is very good, very precise. 5.5 is still usually pretty good balance. So, I jump around. I think if I need pure taste, it's it's the the Fable and and the Anthropic models in general. If I'm going for precision or I have like, "Hey, I have 100 artboards and I need a task to like go down the entire list." I might reach for the Composer. Uh it it just does a really precise job. I find Cursor's a really good harness. It's not too lazy. It'll often spin up sub-agents to get jobs done. So, I jump around a bit. So, here it gave me kind of like three different ideas, you know? And I think from here what I would usually do spend a little more time on exactly what I actually want out of out of it and then give it more direction. But, I might start branching. I might be like, "Ooh, I like this. I like, you know, I kind of like the list of this. That's actually very easy to read." I have kind of like the card layout of this actually like featuring one card and having some other cards to the side is nice. I might just start branching. I think the power of this is you can ask five agents to go generate five more of each, you know, and and kind of find one that really fits what you're going for.

我认为有趣的一点是，它给了你很多灵感和想法，然后你可以开始分支并沿着一条路走下去。但是，仍然是模型在做设计，它仍然有一些你经常看到模型做的东西的标志，无论好坏。那么，当你设计时，你有了这个灵感，你会想，“好吧，这个列表很有趣。我没想到会那样做。也许我想用那个。”然后你如何让它更属于你自己，并摆脱很多模型会吐出的那种标准垃圾？

I think one of the things that's interesting is it gives you a lot of inspiration and ideas and then you can start branching and going down a path. But, it's still the models that's doing the design and it still has some of the hallmarks of the things that you see models do frequently, for better or for worse. And so, how do you when you're designing and you've got this inspiration you're like, "Okay, this list is interesting. I hadn't really thought of doing that. Maybe I want to go with that." How do you then make it more your own and get out of kind of the the standard slop that a lot of them will spit out?

是的。嗯，我有一些非常具体的规则可以和你分享。一个是模型喜欢粗体。它们喜欢粗体风格，并且真的试图把你的字重拉回来，你知道，加粗东西太诱人了。试着把它们拉回尽可能轻，它就会神奇地看起来设计得更好。另一件事是，呃，太多太多字号了。呃，模型喜欢有五、六、七、八个不同的字号。试着只用三个。如果你降到三个，所以让我们在这个上面快速试一下。如果我们把它降到，呃，让我们看看，比如 500。即使那也可能比需要的重。嗯，这里也一样，比如这些实际上不需要加粗。这是一个明显的标志，比如这个上面，护理组织。黑色太重了。让我们把它拉回来，突然它看起来已经更有设计感了。

Yeah. Well, I have some like very specific rules I can share with you. One is that models love bold. They love bold styles and and really like try to pull your font weights back, you know, it's so tempting to bold things. Just try to pull them back as light as you can get, and it'll just uh magically look better designed. Another thing is um too many too many sizes. Uh models love having five, six, seven, eight different font sizes. Try to work with three. If you get down to three, so let's let's just try it real quick on this one. If we if we bring this down to um uh let's see, like a like a 500. Even that's maybe heavier than it needs to be. Um same here, like these don't actually need to be bold. This is such a tell of a of a this one up here, the care organized. Black is so heavy. Let's just pull that back, and suddenly it looks more designed already.

对。看起来更干净了。

Right. Looks cleaner.

它看起来更干净、更易接近。这里也是黑色。让我们把它拉回来。嗯，这些是非常简单的调整，你可以做。这里的对比度相当不错。很多时候模型会把对比度搞砸。嗯，所以我会说这是另一个步骤。你可以确保，文字可读吗？

It looks cleaner and more approachable. Black here, too. Let's just pull that back. Um these are really simple tweaks that like you can make. The contrast here is pretty good. A lot of times models screw up contrast. Um so I would that's another step. You can just make sure it's like, is the text readable?

对。

Right.

嗯，这些小的二、三、四。这些对我来说有点太对比了。我可能会把它们拉回来。它们应该是辅助元素。

Um these these little two, three, four. These are a little too contrasty for my taste. I would probably pull these back. They're supposed to be a supporting element.

我就删掉它们？我的意思是，那些是模型喜欢添加数字或小图标之类的东西。是的，很酷的是你可以直接删除它，然后它会把其他东西都吸上来，而不是留下空白。

I just delete them? I mean, those are the kind of things where the models like to add numbers or little icons or things like that there. And yeah, it's really cool that you can just go through and delete it, and it just snaps everything else up rather than leaving a blank space there.

完全同意。完全同意。嗯，这是这个工具整体上的一个优势，Paper 首先是一个设计工具。它首先是一个人类设计工具，恰好与智能体配合得非常好。所以这意味着你可以自定义你需要做的任何事情。你不会被困在你所在的轨道上。你不需要重新提示。你可以开始深入并改变东西。嗯，所以是的，100% 同意。也许也去掉那个。我做的第一件事是尝试降到大约三个字号，然后把所有粗体都拉回来。你会立刻得到一些感觉更有设计感和有意为之的东西。

Totally. Totally. Well, that's one of the powers of of of this tool in general, is Paper is a design tool first. It's a human design tool first that happens to be really really good with agents. And so that means you can customize whatever you need to do. It's you're not stuck with like the track you're on. You don't you don't prompt again. You can start reaching in and and changing things. Um so yeah, 100% agree. Maybe get rid of that one, too. The first thing I do is is try to get down to like three font sizes, and just pull all that bold way back. And you'll immediately get something that feels more designed and intentional.

是啊。

Yeah.

然后你从这里做什么？太好了，你有了新的部分。你对它感到兴奋。你如何把它包装回去？

And then what do you do from here? Great, you've got the new section. You're excited about it. How do you then wrap it back in?

嗯，有几种方法。你可以右键点击，嗯，让我实际抓取这里。呃，你可以把它复制为 React。

Well, so there's a couple ways. You can you can right click, and um let me actually grab here. Uh you can copy it as React.

嗯。

Mhm.

嗯，不过这是比较长的路。所以我可以把它作为代码拿出来，粘贴到我的 IDE 中。你也可以直接让智能体把它拉回来。所以，你知道，我打开了 Paper 的代码库，但你可以直接说，嗯，你知道，请把我在 Paper 中的选择构建成代码库中的一个新组件，我们实际上不会在 Paper 中发布它。它可以读取我们刚刚做的所有事情。

Um so that's kind of the long way, though. So I can get this out as code and paste it into my IDE. You can also just ask the agent um to pull this back. So, you know, I have the paper code base open, but you can just say um you know, please build my selection in paper into a new component in the code base, which we will not actually ship in paper. It can read everything that we just did.

嗯。

Mhm.

而且它非常了解我的代码库，因为它是我使用的智能体。所以，它实际上可以引入这个设计。它会匹配我们拥有的编码风格和约定，嗯，并把它构建到代码库中。如果它已经存在，通常你已经有了这个组件。它只会更新它，你知道，而且非常非常快。所以，我们看到很多人现在就像，这就是整个循环。就像，甚至没有交接了。就像一个人做这些改变、迭代和发布，这真的很酷。

And it knows my code base really well because it's the agent that I use. And so, it can actually pull in this design. It'll match the the coding styles that we have and the conventions that we have um and build it into the into the code base. And if it already existed, usually you'd already have this as a component. It would just update it, you know, and it's really really fast. So, we see a lot of people are just kind of like, this is the whole loop now. Like, there isn't even a handoff anymore. It's just like one person making these changes and iterating and and shipping, which is really cool.

是啊。那真的很酷。

Yeah. That's really cool.

是的，这就是它的强大之处。设计师比以往任何时候都更容易按照自己的想法去构建和发布产品，完成最后一公里，让产品上线，然后迭代改进。像这样的工具正在赋予人们超能力。这是一个全新的世界，一个人就能完成整个团队的工作。

Yeah, that's what's so powerful. It's easier than ever for designers to actually build and ship things in the way that they see it, and to get that last mile, get something live, iterate on it, and make it better. Tools like this are giving people superpowers. It's a whole new world where one person can do the work of an entire team.

哦，绝对如此。是的，绝对如此。而且我认为即使在团队中，我们也看到了很多这样的情况。团队正在利用这一点加速，但我认为核心是智能体式工作流。如果你使用智能体来完成工作，你需要能够与智能体良好沟通的工具。所以这就是我们关注的焦点。

Oh, absolutely. Yeah, absolutely. And I think even in teams we're seeing a lot of this too. Teams are speeding up using this, but I think the core of it is agentic workflows. If you're using agents to accomplish your work, you need tools that speak to the agents really well. And so that's what we're focusing on.

YC 下一期创业营现在开始接受申请。你有创业想法吗？前往 ycombinator.com/apply 申请。永远不嫌早，填写申请表会让你的想法更上一层楼。好了，回到视频。

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.

好的，再来一个？

Sure, do one more?

来吧，这里还有一个。

Let's do it. Here's another one.

好的，我们来看 SciTechs。加速现场基础设施运营。规划流程，现场执行，将每一个行动转化为一个活的知识库，你可以监控、自动化并直接提问。好吧，我的意思是，第一眼我就注意到同样超粗的标题。

All right, we got SciTechs. Accelerate field infrastructure operations. Plan the process, execute in the field, and turn every action into one living knowledge base that you can monitor, automate, and just ask. Okay, I mean, right away, the first thing I notice is same super bold headline.

就像你刚才说的，我们看到了一些发光效果，颜色感觉像是 vibe coded 的，又是很多紫色。这往往是另一个特征。这里的动画看起来不错，有点像在展示产品的工作原理。

Just like you were talking about, we've got some of those glows, the colors feel vibe coded, a lot of purple again. That tends to be another tell. The animation here looks cool. It's kind of like showing how the product works.

是的，这引起了我的注意。

Yeah, that gets my attention.

是的。而且，直到我们看到动画，我才知道它是做什么的。

Yeah. Also, I had no idea what it was until we got to the animation.

是的，我还是不太确定，但看起来像是看板之类的东西。

Yeah, I still am not quite sure, but yeah, it's something that looks like a Kanban board, I guess.

是的，我感觉到我可以以一种更容易监控的方式来组织我的信息。然后我想说的是，我在这里对设计的反馈是，要更清楚地说明作为用户我能从中得到什么。

Yeah, and I'm getting the sense that I can have my information in such a way that I can monitor it more easily. And then I think I would say that my feedback here for design is actually make it more clear what I'm getting out of it as a user.

嗯，有趣的是，他们下面有这张图片，这个正在播放的视频。它展示了建筑卡车和一个戴着安全帽的人在用手机工作。你回头再看，上面写着现场运营，是的，现场基础设施运营。然后你就会想，哦，这是涉及建筑或重型机械之类的运营管理。但在首屏上方并不明显，因为最大的线索就在首屏下方。

Well, it's interesting because then they've got this image down here, this video that's playing. It's showing construction trucks and somebody with a hard hat on working on their phone. And you go back up and it's like the field operations, yeah, field infrastructure operations. And then it's like, okay, this is something with managing operations for involving construction or heavy machinery or something like that. But it's not obvious above the fold here because that biggest clue right there is right below the fold.

我还想看看它到底在做什么，因为我已经有支持 AI 的看板了。那么它对建筑行业有什么特别之处？我希望在首屏的价值主张中看到这一点。但你说到一些基础问题，比如这里非常粗的字体。这看起来像是 AI 生成的。这里还有一个很好的部分。这个部分如果减少文字样式会整洁很多。你看，一种字号、两种、三种、四种。这可能是另一个问题。如果减少到三种，看起来会好很多。我们快速试一下。我甚至可以让智能体帮我们做。再次强调，我用 paper snapshot 从实时网站抓取，粘贴到 paper 中作为可编辑图层。然后我们就说给这个命名。这是另一种做法。你可以说这是什么，是 Scitex。这个我们交给 cursor。我们会说：“嘿，cursor，请清理 Sitex 框架，最多使用三种字号，不要加粗。所有字重保持常规或更细。”

And I would love to see too like what is it actually doing, because I can have AI enabled Kanban boards already. So what is making it special for construction? I would love to see that as part of the value prop above. But to your point on some of the fundamentals like very bold is here. This looks like maybe 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 text styles. So you see like one size, two sizes, three sizes, four sizes. That's probably another one too. If you take that down to three, it's going to look so much better. So let's just try that real quick. I'll even ask the agent to do it for us. And again, I use paper snapshot to grab it from the live site, paste it into paper as editable layers. And then we'll just say name this one. Here's another way you can do it. You can say what is that is Scitex. This one we'll give to you, cursor. We'll say, 'Hey, cursor, please clean up the Sitex frame using at most three font sizes and no bold. Everything regular or below in weight.'

所以你给那个框架命名为 Sitex，然后你就给了智能体那个上下文线索。

And so you named that frame Sitex and then you just gave it that context clue to the agent.

没错。这只是告诉它你想让它处理什么的不同方式。我最喜欢的是留下评论。关于选择，我注意到之前我在跳转时，你倾向于频繁改变选择，我会不小心取消选择。所以我喜欢留下评论。我认为这是最好的方式。但开始了。它开始处理这个了，它会做很多事情，你知道，带回一些 vibe coded 的东西。在 paper 中，我们实际上给模型提供了指令，避免这些常见错误。有时人们会问：“你的秘诀是什么？为什么更好？为什么看起来更好？”其实，老实说，我们所做的只是这些基本的排版和对比度规则。

Exactly. It's just different ways to kind of tell it what you want it to work on. My favorite is actually leaving comments. The thing with the selection, I noticed earlier as I was jumping around, you tend to change your selection a lot and I'll accidentally deselect. So 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 going to do a lot, you know, bring back some of that vibe coded stuff. Now, in paper we actually give instructions to the model not to do these common mistakes. And sometimes people go, 'What's your secret sauce? Why is it better? Why does it look better?' And it's just like, honestly, all we're doing is these basic rules of typography and contrast.

是的。

Yeah.

我们让团队中更资深的设计师将他们的知识提炼到指令中。

And we had the more senior designers on the team distill their knowledge into the instructions.

这对模型来说很棒。

That's great for the model.

是的，即使这样也非常强大。仅仅为模型的行为设置这些护栏就能节省大量时间和精力。

Yeah, even that is very powerful though. Just putting those guardrails up around what the models are doing can save a lot of time and energy.

是的，就像专家稍微引导一下模型真的很有帮助。在现实生活中，我可能会手动完成，因为那样更快，但如果你有一个完整的网站要处理，使用智能体就非常有用了。或者如果你完成后想把它拉回代码库，智能体可以帮你做。

Yeah, like an expert guiding the model a little bit 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 in your code base when you're done, the agent can do that for you.

这看起来已经是一个巨大的改进了。

This already looks like a huge improvement.

是的，我认为这是非常简单的改变，对吧？我们只是降低了字体的字重，并合并了字号数量。对我来说，它看起来更有设计感，更有意图。所以如果我们再拉出原始版本，比如，这是……我们会打开 paper 并排对比。现在这是主观的，对吧？我知道可能有人在这个设计上花了不少时间，我认为他们内容做得很好，但通过去除这些 AI 特征，对我来说，右边的那个感觉更值得信赖，更有意图，更有设计感。

Yeah, I think it's 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, like, here's kind of the... We'll pull up paper and do a side by side. Now 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 tells out of it, to me the one on the right feels more trustworthy, it feels more intentional and more designed.

你谈到这些 AI 特征很有趣。

It's interesting you talk about some of those AI tells.

是的。

Yeah.

你见过的最常见的特征有哪些？当你看到一个页面或设计时，你会说“有人只是把模型输出的东西直接拿来用，说不错就继续了”，这些线索是什么？

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.

第一，我认为你不应该那样做。这很诱人，尤其是如果你是一个 YC 创始人，时间紧迫，试图完成第一笔销售，很可能很想直接使用云设计输出的任何东西。我认为你不应该这样做，因为我认为它不会帮助你脱颖而出。它让你看起来像是百万个项目中的一个，让你看起来缺乏意图，看起来不够用心。所以我认为设计是一个很好的差异化因素。

One, I don't think you should do that. And it's so tempting, especially I'm sure if you're like a YC founder and you have zero time and you're trying to make your first sales, it's probably very tempting to use whatever cloud design spits out. I don't think you should do it because 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.

如果你看看过去 10 到 20 年的每一家伟大公司，基本上它们都有卓越的设计。我想不出有哪个例外。所以我认为如果你想成为那些真正伟大的公司之一，你就必须在设计上投入心血，确保自己脱颖而出。所以 AI 的迹象——我们谈过字体、字号——对我来说这些都是很大的迹象。

And if you look at every great company of the last 10, 20 years, basically all of them have exceptional design. I can't think of an example that doesn't. So I think if you want to be one of those really great companies, you have to put the care into design and make sure that you stand out. So AI tells—we talked about the font, the font sizes—those are huge ones to me.

YC 下一期现在开始接受申请。你心里有创业想法吗？在 ycombinator.com/apply 申请吧。永远不嫌早，填写申请表会让你的想法更上一层楼。好了，回到视频。

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.

你可能见过那种侧边的小色带，每张卡片上都有两像素的颜色。总体上过度使用卡片，到处都是 20 张卡片。这些其实也很容易修正。只要让智能体、让 Paper 生成那个布局的 20 个变体，然后挑你最喜欢的那个，因为它看起来会比一堆卡片散落各处要用心得多。你还有哪些其他的例子——

You've probably seen the little side swoop of color, like two pixels of color on every card. 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 going to look a lot more thoughtful than just a bunch of cards all over the place. What are some of your—do you have other examples of—

紫色。

Purple.

哦，紫色。对。

Oh, purple. Yeah.

渐变、大量图标，还有全大写的小标题。

Of gradients, a lot of icons, and all-caps headings, like tiny headers.

小标题。

Tiny headers.

对。你知道很多这些其实是什么吗？为了小部件而小部件。它们并不是真的在传达什么重要或有价值的东西，来帮助用户理解设计想表达什么。很多感觉就是用来填充空间的。

Yeah. You know what a lot of it turns out to be? Widgets for widgets' sake. 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. It's just there to fill up space, is what a lot of it feels like.

就像一个没有安全感的设计师。智能体非常没有安全感，它们想填满它，到处都是些零零碎碎的小东西。

It's like an insecure designer. The agents are very insecure and they want to fill it out, and there's like lots of little ones and twos.

对，完全正确。比如，你为什么要那个？嗯，我不知道。它看起来像是把那些卡片的角落固定得更好之类的，但它真的传达了什么东西吗？那些数字有意义吗？不，没有。那我们干脆删掉它们好了。

Yes, exactly. Like, why do you need that? Well, I don't know. It looks like it anchors the corners on all those cards better or something, but does it actually communicate anything? Do those numbers mean something? No, they don't. Well, we should just get rid of them then.

完全同意，完全同意。我觉得很多设计就是做减法。

Totally, totally. I think a lot of design is deleting.

对。

Yes.

先过度构建再往回拉，这挺好的。但避免智能体风格很大程度上就是往回拉。

It's kind of nice to overbuild and then pull it back. But a lot of avoiding the agent look is pulling back.

当模型吐出一些东西，然后你得进去编辑，你得说“哦，那个标题”，然后描述它等等，这很难；相比之下，你可以直接进去选中它，按下删除键，一切就各就各位了。感觉你有了多得多的控制权，而且把它带到更用心的地方所需的努力要少得多得多。我认为这非常强大——它不强迫人们在速度上妥协，但他们仍然能得到看起来非常棒、脱颖而出、不像是模型随便吐出来的东西。

It's hard when the model spits something out and then you've got to 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, 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 it 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 model has just spit it out.

有时候我们把这看作是为工作选择最佳工具，有时候是提示，有时候是拖拽。你不想用错工具。那不好，对吧？

Sometimes we think about this as the best tool for the job, and sometimes it's prompting and sometimes it's dragging. And you don't want to use the wrong one. That's no good, right?

每个用 vibe coding 做的应用都有浅色模式和深色模式。

Every vibe-coded app has light mode and dark mode.

而且这是那种——所有 MVP、所有第一版——没有人会把它作为想发布的第一个功能来构建。

And it's the kind of thing—all MVPs, all first—nobody would ever build that as the first feature they want to launch.

对。

Right.

只是因为你免费得到它，而且模型喜欢做，所以每个人都有。但它很少是值得花时间或包含在你设计里的东西。所以这也是一个大迹象。

It's just that you get it for free and the models love to do it, so that's why everybody has that. But rarely is it the thing that is worth spending time on or including in your design. So that's one of the big tells as well.

而且它真的好吗？我觉得糟糕的深色模式是另一个大迹象，对吧？比如它真的用纯黑，而不是，你知道，或者只是反转颜色之类的。对。所以 Wes 最近发了一条很棒的推文，展示了天启四骑士，就是——对，我们谈过这个。

And is it actually good? I think a bad dark mode is another big one, right? Where it's literally using black instead of, you know, or just reversing the colors or things like this. Yeah. So Wes had a great tweet recently showing the four horsemen of the apocalypse, which is—yeah, I mean, we talked about this.

对。

Yeah.

那个可能直接删掉就好，如果你有的话。你把它去掉，你不需要它。这个，全大写的小眉题，可能也不需要。

That's probably just delete that if you have that. You get rid of that, you don't need it. This one, the all-uppercase little kickers, probably don't need that.

还有中间额外的字距。

With the extra letter spacing in between.

完全同意。

Totally.

对。

Yep.

对。这就像我 14 岁学设计的时候。我当时想：“对，把东西拉开间距。看起来很棒。”对，这个很好，带额外小图标的徽章。

Yeah. This was like me when I was learning design when I was 14 years old. I was like, "Yeah, space the stuff out. It looks great." Yeah, this is a good one, the badges with the extra little icons.

对。

Yeah.

很多胶囊按钮，很多图标。

A lot of pills, a lot of icons.

对。当然，还有紫色渐变。对。你知道，Linear 把这种风格做得很好，然后我觉得它被编码进了模型里，供接下来——

Yeah. And, of course, the purple gradient. Yeah. You know, Linear made this style great, and then I think it got encoded into the models for the next—

对，我的意思是，这是有趣的一点：单独来看，这些东西并不坏。只是当它们被过度使用，你总是看到它们时，就像你说的，它就不脱颖而出了。

Yeah, I mean, that's one of the things that's interesting: in isolation, these things are not bad. It's just when they're overused and you see it all the time, to your point, it doesn't stand out.

对。

Yeah.

而且它看起来很草率。设计总是在演进，标准总是在演进，基线总是在演进，你必须始终领先于它。否则，你看起来就像个平庸的东西，而平庸的东西并不卓越，那不是人们乐于使用的东西。

And it looks sloppy. Design is always evolving, the standards are always evolving, the baseline is always evolving, and you always have to stay ahead of that. Otherwise, you just look like an average thing, and the average thing is not exceptional, and that's not something people are excited to use.

而且我认为，如果你向世界展示平庸的形象，就很难建立一家伟大的公司。

And I think it's hard to build a great company if you have a mediocre presentation to the world.

它甚至影响你招聘到谁，谁被你的公司吸引，以及你能吸引到的人才。所以值得用心去做。

It even impacts who you hire and who's attracted to your company for recruiting and the talent you can attract. So it's worth being intentional.

好了，我们来看看 Maridata。 “像当地人一样通过二维码支付。一个全球钱包，解锁亚洲和拉丁美洲的本地二维码支付。” 好的，所以我们看到一堆旗帜，我认为这表示很多国家。这是个支付产品。我有点紧张——一个看起来像 vibe coding 出来的支付产品。

All right, let's take a look at Maridata here. "Pay like a local via QR codes. A global wallet that unlocks local QR payments across Asia and Latin America." Okay, so we've got a bunch of flags, which I think indicates lots of countries. It's a payments thing. And I get a little nervous—a payments thing that looks vibe-coded.

对，再说一次，你品牌的可信度非常重要，尤其是处理金融业务时。这里另一个例子是，把内容拉上来——把好的内容放在首屏之上。我有点喜欢这个网站的能量，尽管有些地方有点太狂野了。有点太杂乱。很草率。但我能看出它有这种——它试图暗示这种全球感，我觉得这真的很酷。在我们——哦，我喜欢这个。“运作方式”。

Yeah, again, the credibility of your brand is really important, especially if you're dealing with finances. Here's another example of like pull up the content—get your good content above the fold. I kind of like the energy of this site, even though some of it is a little too wild. It's a little too all over the place. It's sloppy. But I can tell it has this—it's trying to suggest this global feeling, which I think is really cool. Before we—oh, I love this. "How it works."

对，这很酷。

Yeah, this is cool.

把这个也拉上来。你知道，我滚了很久才到那里。

Get that up, too. You know, I had to scroll pretty far to get there.

对。而且这看起来干净多了，也更专业。

Yeah. And this just looks a lot cleaner, more professional, also.

确实。

It does.

这让我更信任它。

Which makes me trust it more.

绝对。所以，在我们开始之前，我快速用 Paper 跑了一下这个，只是为了——我其实只是让它往回拉，为这个网站创建一个更专业、更值得信赖的基础。

Absolutely. So, before I—I ran this one through Paper real quick before we came on, just to—all I asked it was actually to pull back and just create a foundation for this site that is a little more professional and a little more trustworthy.

我们用 5.5 做了这个，它给出的结果就是这样。我实际上觉得在这种情况下，它失去了一点原始设计的兴奋感。

And we used 5.5 on this, and this is kind of what it came up with. And I actually think in this case, it lost a little of the excitement of the original design.

嗯。

Mhm.

但这就是你身处设计工具中的意义，现在你可以自己进来把它找回来。

But that's where you're in a design tool, and now you can come in and bring that back yourself.

对。

Yeah.

但我确实认为这给了你更多一点的基础。再说一次，文字太多了。

But I do think this gives you a little bit more of a foundation. Again, way too much text.

是的。

Yes.

文字太多。

Too much text.

把这些东西收一收。

Pull back on some of these things.

嗯，但我认为它给了你更多一点的基础……而且再说一次，你可以进来删除一些 vibe 编码的东西。少即是多。这就是我想对这个网站做的：保持兴奋感，保持这种国际化的感觉……就像那样。它很独特。但你不能走得太远，你知道，也许这个文字渐变有点太狂野了，感觉不太可信。但我确实喜欢这个价值主张，而且我大部分情况下很快就能理解它是做什么的，我喜欢这一点。

Um but I think it gives you a little bit more of a foundation that... And again, you can come in and delete some of the vibe-coded stuff. Less is more. That's what I would try to do with this site is keep the excitement, keep this kind of like international... like that. It's unique. But you can't go so far, you know, maybe this text gradient is a little too wild and doesn't feel super trustworthy. But I do like the value prop, and I understand what it is for the most part pretty quickly, which I like.

我喜欢他们右下角有个二维码。

I like that they've got a QR code in the bottom right.

这是产品的一部分，对吧？就像……

Which is part of the product, right? It's like...

对。

Yeah.

这很酷。这是我以前不太常见到的东西。

Which is cool. That's something that I haven't seen very much before.

它让我想和它互动。它很有吸引力。

It makes me want to interact with it. It's inviting.

是的。

Yep.

是的。整体感觉，那种氛围是……如果我们能让它更可信一点，但我喜欢这种兴奋感，我喜欢这种能量，我喜欢它给我的邀请感。

Yep. The overall feeling, the vibe is... If we can make it a little more trustworthy, but I like the excitement, I like the energy, I like the invitation that I have.

对，不过它也几乎太容易让人忽略在角落里了，因为你知道，你太习惯看到右下角的聊天框了，你会假设有一堆东西应该忽略。

Yeah, it's almost too easy to miss it down in that corner, though, too, cuz, you know, you're so used to seeing the chat with us box down, and you just assume there's a bunch of things that you should ignore.

那些东西除非你有问题，否则你不会看。我不知道，也许他们应该把二维码放到主区域，说“现在试试”。

That are unless you have a problem, like that's where you look. And I don't know, maybe they should bring that QR code up to the main area and say, "Try it now."

放在主视觉里。

Spit in the hero.

对，对。

Yeah. Yeah.

我确实觉得这个主视觉可以更努力地发挥作用。因为当我往下看的时候，我会想：“对，这不错。这很扎实。”越往下越显得可信。

I do feel like this hero could be working a lot harder for that. Cuz when I start getting down here, I'm like, "Yeah, this is good. This is solid." It seems to get more trustworthy the further you go.

嗯。对，你说的这点很有意思，你知道，归根结底，当你用模型生成设计时，是模型在生成设计。你有点受制于它们被训练了什么、它们喜欢怎么设计。

Mhm. Yeah, it is interesting your point that, you know, at the end of the day the models are the ones that are generating the design when you use them to generate the design. And you're kind of at the mercy for how like what they've been trained on and how they like to design.

是的，对。

Yes, yeah.

所以重要的是使用正确的模型，而这些模型会随着时间推移不可避免地变得更好。然后你需要的下一件事就是更快地获得更多控制权。

And so what's important is using the right models and those models getting better at design, which will inevitably happen over time. And then the next thing that you need is just more control over it quickly.

对。

Yeah.

所以拥有这种控制权，能够编辑它并让它更符合你自己的愿景，实际上是这里真正缺失的强大部分，我认为这正是 Paper 在这里提供的很多东西。

And so to have that control, to be able to edit it and make it more in your own vision, is actually the really powerful missing piece here that I think is a lot of what Paper is providing right here.

智能体可以加速你的工作。它们可以帮你省很多事，还能帮你做翻译或调整尺寸之类的任务。但我们坚信设计中人的因素及其重要性。所以我们试图创造一个工具，让人类能和智能体一起非常快速地工作。

The agents can speed you up. They can save you a lot of work, and they can do tasks like translation or resizing for you. But we're big believers in the human element of design and how important that is. And so we're trying to create a tool that lets humans work really fast with agents.

你觉得智能体能不能像人类一样学会品味？

Do you think the agents can learn taste the same way humans can?

它们会在字距之类的事情上变得更好，那些小的战术性事情会随着时间推移变得更好。而且我觉得让我受到鼓舞的是，像 Fable 这样的模型似乎更有思想。感觉它实际上比以前的模型在决策中投入了更多选择和思考。所以我认为这就是设计的一部分，就是那种深思熟虑。

They'll get better at things like letter spacing, the little tactical things will get better over time. And I think what I'm encouraged by is a model like Fable seems much more thoughtful. It feels like it actually put some choice, some thought into its decisions compared to previous models. And so I think that is a piece of design, is that thoughtfulness.

对。

Yeah.

那么，我是否认为它会取代人类做这些设计决策？不，绝不可能。因为很多设计实际上是组织中非常人性化的决策任务。它向人们展示方案，然后人们可能会说：“哦，不是那样。我不喜欢那样。”设计的角色是……你最后看到的是像素，但设计在组织中的角色是决策、利益相关者、引入需求和问题空间，这些都不是智能体真正擅长的。你知道，谁知道随着时间的推移会怎样。它们会变得越来越聪明，但我就是认为人类是构建脱颖而出之物的关键部分。

Now, do I ever think it's going to replace a human making these design decisions? No, no way. Because a lot of design is actually a very human task of like decision-making in an organization. It's showing people comps and being... and people can be like, "Oh, not like that. I don't like that." The role of design is... you see the pixels at the end, but the role of design in an org is like decisions and stakeholders and bringing in requirements and problem space, and those are not things that agents have any skill at really. You know, who knows over time. They're going to get smarter and smarter and smarter, but I just think humans are such an essential piece of building stuff that stands out from the crowd.

对，这很有意思。我和一位在数十亿美元、以设计为先的公司领导设计的人有过非常相似的对话，关于人类脑海中有一个思考过程，他们在对某件事做出反应，并有一个评估标准，这对我们人类来说目前是非常隐性的。问题是，你能把这些东西说出来吗？

Yeah, it's interesting. I was having a very similar conversation with someone who leads design at a multi-billion dollar design-forward company about there's a thought process that goes through a human's head where they're reacting to something and a criteria they're evaluating and it's very implicit for us as humans right now. And the question is can you verbalize what those things are?

嗯。

Mhm.

比如你决定某件事好不好、看起来好不好、是否达到标准的这个过程是什么。你能真正地逐一量化所有这些，并教给模型，让它拥有像人类一样的品味吗？然后问题就变成了，如果所有模型都能做到这一点，是不是一切又会看起来一样了？

Like what is the process of you deciding whether something is good or not or looks good or not or hits the bar or not. Can you literally go through and quantify all of that and teach that to a model to the point where it has taste like a human would? And then the question becomes well if all the models were able to do that, does everything just look the same again?

然后你总是需要人类去推动寻找下一个真正新颖、脱颖而出、更能突破极限的东西。

And then you always need the humans to be driving to finding the next thing that's actually going to be new and stands out and pushes the limits more.

我们看到即使在人类的前模型时代，趋势也会接管。你知道，每个人都看起来像线性风格几年，然后别人发现了新东西，对吧？我确实认为模型会在战术上变得擅长。它们会更好地避免把所有东西都加粗。你知道，我认为那很棒，那会非常好。但仅仅是想法、产品，设计中有太多东西，就像它是否展示了价值主张？那些东西更重要。比如这个网站，我觉得有点太狂野了，也许对他们来说，真正有趣和令人兴奋非常重要。也许这就是他们的市场需要的。

We see that even within human pre-pre-models as trends take over. You know, everyone kind of looks like linear for a couple years and then somebody else figures out something, right? I do think the models will get good at tactics. They'll get better at not making everything bold. You know, and I think that that's great and that'll be really nice. But the just the thought, the product, there's so much of design again, it's like was this showing value prop or not? That stuff's more important. This site for instance that I think is a little too wild, maybe it's really important for them to be really fun and exciting. Maybe that's what their market needs.

嗯。

Mhm.

你知道，所以也许对他们来说，保持非常兴奋和某种模型决策是更高层次的事情……你知道，也许有足够的信息你就能开始接近，但我认为我们离那还很远。对，也许 10 年左右。也许我不知道，也许我太悲观了。也许它会来得更早。但我仍然认为人类是拼图中不可或缺的一部分。

You know, and so maybe it's a higher order thing for them to be very exciting and kind of model decision can... you know, maybe with enough information you could start to get there, but I think we're pretty far away from that. Yeah, maybe 10 years something like that. Maybe I don't know, maybe I'm too pessimistic. Maybe it'll come sooner. But I still see humans as just this essential piece of the puzzle.

对，我们当然希望如此。

Yeah, we certainly hope so.

对，希望如此。

Yeah, let's hope so.

我很好奇你们在 Paper 内部是怎么使用智能体的？

I'm curious how are you guys using agents internally at Paper?

在某些方面我们用得很多，但在其他方面我们用得……我们在某些方面有点像恐龙。

In some ways we use them a lot and then in other ways we use them... we're kind of like dinosaurs in some ways.

比如，我们的 Slack 里没有智能体，我们也不会……我们在编码时确实大量使用智能体，但我们仍然会阅读代码。我们阅读所有代码，每一行。

Like, we don't have agents in our Slack, and we don't... we use agents for coding quite a bit, but we still read our code. We read all of our code, every single line.

每一行。

Every line.

通常会有多个人类阅读每一行。

Usually multiple humans read every single line.

为什么？

Why is that?

嗯，一是设计工具真的很难构建。你知道，今天你无法写出 Figma 级别的代码设计工具。也许最终可以。所以这需要大量非常精确、非常细致的工作。从系统角度来看，它是非常多维的。所以我们必须要非常小心。我们希望确保我们的体验，你知道，设计师需要 120 FPS。它必须快。它必须每次都正常工作。而智能体还达不到。

Well, one is design tools are really hard to build. You know, you can't write a code design tool at the level of a Figma today. Maybe you can eventually. And so it takes a lot of really precise, really careful work. It's very multi-dimensional in terms of the systems. And so we just have to be really careful. And we want to make sure our experience, you know, designers need 120 FPS. It needs to be fast. It needs to work every single time. And the agents just aren't there.

还没有。

Not yet.

另一件事是精英小团队，对吧？所以 12 个人保持极高的人才标准。我认为如今在创办公司时，你应该尝试这样做。并用智能体来加速人员。但如果人更少，沟通负担更少，其他成本也更少。

The other thing is a small elite team, right? So 12 people keep the talent bar extremely high. I think when you're building companies, that's how you should try to do it these days. And use the agents to accelerate the people. But if you have less people, you have less communication burden, you have less of these other costs to go through.

不过，我们使用智能体的一个例子是我们的品牌设计师 Agu。他是一位出色的品牌设计师，擅长视觉。他会一点编码，但我觉得他不会称自己为程序员。他在上次发布前大约一周内完成了我们整个网站。

One example of how we use agents though is Agu, our brand designer. He's a brilliant brand designer, great at visuals. He codes a little bit, but I don't think he'd call himself a programmer. And he made our entire website in about a week before this last launch.

哇。

Wow.

包括发布，包括所有动画。他在 Paper 中设计了所有内容。而这种设计你不想用提示词来做，对吧？你需要这个……他在背景中有着色器，微妙地贯穿这些主题。他在 Paper 中做了所有事情，然后他只是提示。而这是，你知道，6 个月前了，所以是不同的模型。他只是在 Paper 文件之上提示动画。他说，你知道，把我的 Paper 设计变成一个代码库。这是一个 Next.js 网站，帮我整合起来。没有其他人看过这个。所以 Agu 在一周内端到端完成了。因为他是个设计师，他加入了这些彩蛋。有一些有趣的小额外内容。

Including shipping it, including all of the animations. And he designed everything in Paper. And this is the kind of design you wouldn't want to do this with prompting, right? You need this... he has shaders in the background subtly coming through these motifs. He did everything in Paper, and then he just prompted. And this was, you know, 6 months ago now, so different models. He just prompted the animations on top of his Paper file. He was like, you know, take my Paper designs, turn it into a code base. This is a Next.js site, and put it together for me. No one else looked at this. So Agu did this end-to-end in a week. Because he's a designer, he puts in these Easter eggs. There's little like fun extras.

而且它完全是交互式的。

And it's all just interactive.

它是交互式的。而这是他本来不会做的事情。他不会有时间。我相信他本可以，你知道，从技能上讲他本可以达到，但他不会有时间做这个。所以我认为这真的非常酷。所以我认为很多时候它更多出现在我们的核心产品之外，在核心产品中我们实际上仍然非常依赖人工，出于精确性的原因。但在所有其他方面，所有我们需要制作的视频，所有营销网站，所有那些我们可以让智能体帮助人们更快完成的事情。

It's interactive. And this is something he would not have done. He wouldn't have had the time. I'm sure he could have, you know, skill-wise he could have got there, but like he wouldn't have the time to do this. So I think that's really, really cool. And so I think a lot of times it shows up more not in our core product, where we're actually pretty human-based still for precision reasons. But in all the other stuff, all the videos we need to make, all the marketing site, all of that other stuff where we can, you know, have agents help us help people go faster.

是的。所以我们确实，嗯，做了不少，然后当然还有编码智能体，你知道，我们广泛使用 Cursor，我们广泛使用 Claude Code，我们使用 Bug Bot 进行 PR 审查，这非常有帮助。它有时有点过于迂腐，但它仍然能捕获错误，这很好。

Yep. So we do, yeah, quite a bit of that and then of course the coding agents, you know, we do use Cursor extensively, we use Claude Code extensively, we use Bug Bot for our PR reviews, which has been really helpful. It's a little too pedantic sometimes, but it still catches bugs, which is good.

现在对智能体有一点 FOMO。所以就像，哦，每家公司都在不查看代码的情况下发布。你是不是太慢了，你知道？我们有点采取质量软件需要时间的做法。

There's a little bit of a FOMO right now with agents. So it's like, oh every company is shipping without looking at their code. Are you going too slow, you know? We are kind of taking the approach that quality software takes time.

嗯。

Mhm.

而且我们有竞争对手拥有每一个功能。但他们没有关注度，或者人们不在乎。不管出于什么原因，就像人们希望 Paper 更好。他们不希望拥有每一个功能的竞争对手更好。我认为那是因为我们在乎，我们投入了那种精确性和关怀。所以即使我们移动得慢一点，人们仍然更在乎它，所以我认为质量很重要。所以谢天谢地。

And we have competitors that have every single feature. But they don't have the attention or people don't care. And for whatever reason, whatever that is, it's like people want Paper to be better. They don't want the competitors that have every single feature to be better. And I think that's because we care and we're putting in that precision and that care about these things. So even if we're moving a little slower, people still care more about it and so I think that quality matters. So thankfully.

我与很多设计师交谈后感觉，你们几乎在建立一种草根运动。就像一种小众运动，人们现在使用 Paper 作为新的酷东西，很多设计师都在使用，这是新的现代工作方式。这是有意的吗？你们在做什么来获得更多用户、增长、获得一些心智份额？比如你们似乎是唯一一家……Figma 显然已经建立了这个巨大的庞然大物并上市了，你知道，财富 500 强都用它，所有这些，但感觉你们已经开始撬动一些了。当然在某些用户类型中。你们是怎么做到的？对你们来说什么最成功？

My sense from talking to a lot of designers is that you guys are almost building kind of a groundswell movement. Like a cult movement of people that are now using Paper as the new cool thing that a lot of designers are using and it's the new modern way to work. Was that intentional and what are the things that you're doing to try to get more users, to grow, to get some mind share? Like you seem to be one of the only companies... Figma obviously has built this huge behemoth and gone public and you know, all the Fortune 500 uses them and all this stuff, but it feels like you've started to crack some of that. Certainly within certain user types. And how have you gone about doing that and what's been most successful for you there?

是的，很大一部分是与市场价值观高度一致。第一年我们没有产品，但仅通过谈论我们的价值观就获得了大约 25,000 名 Twitter 粉丝。你知道，只是上播客说我真的喜欢设计。你喜欢设计吗？然后我们进入话题，谈论排版或其他什么。与市场价值观一致，他们会原谅你产品缺失很多东西。他们会等待它们出现。如果他们能看出你是真诚的，他们会为你加油。你知道，如果你在构建设计软件，这真的很重要。真的很重要。也许不是对所有软件，但对于设计软件，通常最好的产品、最真诚的产品会赢。所以我认为对我们来说，你知道，再次，12 人的设计师和工程师公司，只是践行我们的价值观，人们真的能产生共鸣。顺便说一句，产品也非常好。我认为那部分很重要。你必须达到。但是，你知道，我认为这是其中的一部分。然后是市场时机。每家公司……希望我们有一天也有这个问题。每家公司最终都会向上市场移动，当你这样做时，你就不再那么酷了，你知道？你向企业销售。你不再在地下酷活动中了，你知道。所以，我真的很荣幸能成为社区的一部分。至于你的观点，比如我想你看到了，你知道，Ramp 一直在发布他们信用卡上实际 Ramp 订阅的数据。是的。如果他们发布了一个你可以与之聊天的关于 Ramp 数据的 AI。如果你问它关于设计工具的问题，它，你知道，显然是 Figma。Sketch 也在那里。然后 Paper 就在 Sketch 旁边。所以我们是自 Figma 出现以来第一家在那个市场有所作为的公司，你知道？而且它增长非常快。这真的很鼓舞人心。真的很令人兴奋，因为当你创办一家公司时，你不知道它会如何发展。你完全不知道。就像我说的，有几个月我都在想没人会在乎这个。

Yeah, a huge part of that is being very values aligned with the market. We didn't have a product for the first year and we still got to about 25,000 Twitter followers just by talking about our values. You know, just go on podcast be like I really like design. Do you like design? We then get into the topic and talk about typography or whatever. Being values aligned with your market, they will forgive so much about your product missing things. They'll wait for them to come out. They'll root for you if they can tell you're authentic. You know, and if you're building design software, it really matters. It really matters. Maybe not for all software, but for design software, usually best product, most authentic product wins. And so I think for us it was just, you know, again, company of 12 designers and engineers and just live our values and people really resonate with that. And by the way, the product is really good, too. I think that that part's important. You got to get there. But, you know, I think that's part of it. And then there's market clock. Every company... Hopefully we have this problem someday. Every company eventually goes up market and you just stop being as cool when you do that, you know? You're selling to enterprises. You're not underground at the cool events, you know, anymore. So, I'm really honored that we are part of the community. And to your point, like I think you saw, you know, Ramp has been releasing the data of actual Ramp subscriptions on their credit cards. Yeah. And if they released an AI you can chat with about the Ramp data. And if you ask it about design tools, it's, you know, Figma obviously. Sketch is there. And then Paper is right there with Sketch. And so we're the first company since Figma's come out to like make a dent in that market at all, you know? And it's growing very quickly. Which is really encouraging. It's really exciting cuz you don't know when you start a company like how it's going to go. You have no idea. Like I said, there were months where I was like nobody's going to care about this.

而现在有这么多酷的人，嗯，比我酷得多的人，非常关心 Paper，并且穿着我们的周边商品等等，看到这些真是太有趣了。

And to now have like so many cool people, um people are way cooler than me, that care a lot about Paper and are like wearing our merch and stuff is like so much fun to see.

老实说，这是最棒的部分。

And honestly, it's the best part.

这太酷了。而且这不是你的第一家公司，这是你的第二家公司，对吧？看起来甚至在你有产品之前，你就已经把自己、你的愿景和价值观展现出来了，你成为了代言人，这就是人们在你有产品之前，以及产品早期所认同的东西，而成功的正是你本人，以及你把这些传播出去。那么，这和你之前创办的另一家公司有什么不同？对比一下这两者？

That's really cool. And this is not your first company. This is your second company, right? And it seems like even before you had a product, you have gotten yourself out there and your vision and your values and you become the ambassador and that's what people were buying into before you had a product and certainly in the early days of having a product and that's what's been successful is you. And getting that out there. And how is that different from you, you know, you built another company before this and like contrast the two?

嗯，我的第一家公司 Modules 做的是设计和开发交接。

Well, so my first company Modules was working on design and developer handoff.

嗯。

Mhm.

我们在这个过程中还做了 Radix UI。它就像是我们一个一直持续下去的副项目。然后，你知道，Radix 成了默认的 React 组件库。

And we built Radix UI along the way. It was like one of our side projects that just kept going. And, you know, Radix became this default React component library.

嗯。

Mhm.

第一，这是 AI 之前的事。所以，你知道，一切都更难。设计和开发交接更难。第二，我们真的同时听取双方的意见，结果我们很困惑。因为设计师希望工程师改变，工程师希望设计师改变，而且他们会告诉你对方团队会使用你的软件。你不能那样构建软件。所以我们学到了一些关于做出人们真正想要的东西的惨痛教训。然后我想我已经能够把这些应用到 Paper 上。但是，我们确实做出了，我的意思是 Radix 有惊人的产品市场契合度。我们只是没看到围绕它建立风险投资规模业务的方法。所以我们想，那就让它免费，把它送出去，然后，你知道，下次再带着新东西回来。所以这很酷。我的意思是那结果非常好。我们把这公司卖给了 WorkOS，一家很棒的认证和身份公司。我们在 Paper 上使用 WorkOS。然后几年后，我又想重新开始做创意工具。

One was this was pre-AI. So, you know, everything was harder. Designer-developer handoff was harder. Two was we really listened to both sides at once and we got very confused. Because designers want engineers to change and engineers want designers to change and like they will tell you the other team will use your software. Like you can't build software that way. And so we learned some hard lessons about making something people actually want. And then I think I've been able to apply that at Paper. But, we did make, I mean the Radix has amazing product market fit. We just didn't see a way to build like a venture scale business around it. And so we thought let's just make it free and give it away and then, you know, come back with something next time. And so that's been cool. I mean that worked out really well. We sold this company to WorkOS, which is an amazing auth and identity company. We use WorkOS for Paper. And then a couple years after that I just wanted to start back into creative tooling again.

那你从那次经历中学到了什么教训，这次在应用吗？

And are there any lessons that you took from that experience that you're applying this time?

你可能会把产品构建过度复杂化。你知道，“做出人们想要的东西”是个好说法。很多时候，当你面对产品时，你会想：我的公司下一步需要什么？现在可能发生在我公司身上的最好的事情是什么？对我们来说，一开始就是成为对话的一部分，拥有 Twitter 粉丝。好吧，那就去做能涨粉的事情。去上播客。去和用户交谈，然后向外传达他们的价值观。所以，你知道，很多时候其实很简单。我认为我们把它搞得太复杂了，我们试图为公司制定那些绝妙的战略，但其实就是要弄清楚下一步需要什么，然后尽可能用最直接的方式去实现。而且，不要害怕做那些听起来很难的事情，显然你必须去做。所以，这就是我们采取的理念，瓶颈优先，我非常相信这个理念。比如我们现在，瓶颈是早期采用者在使用 Paper。那些可能不是早期采用者类型的人，非常习惯他们现在的工作方式。他们缺少评论和组件等功能。所以现在我们的瓶颈又变成了功能。所以现在，那就是我们下一步要做的。把那个瓶颈释放给业务。另一个战术上的事情就是每天和用户交谈。非常重要。我在公司第一年有个规矩，我必须每天和一个设计师交谈，我坚持了一整年。那非常有用，因为我了解到，当你开始创建公司和产品时，你会有不同的视角。你忍不住，你有个人知识。所以保持扎根于用户对话非常重要。

You can way overcomplicate product building. You know, the make something people want is a great phrase. And you really a lot of times when you with your product it's like what does my company need next? What would be like the best thing that possibly could happen to my company right now? At the beginning for us that was like being part of the conversation, having Twitter followers. Well, let's go do things that get Twitter followers. Let's go on a podcast. Let's talk to users and then represent their values outwardly. So, you know, a lot of times it's actually very simple. And I think we make it too complicated and we're trying to have these brilliant strategies for our companies and it's like what do you need next and just do the most straightforward thing you can possibly do to get there. And you know, and don't be scared to do things that sound hard, you know, obviously you got to do them. So, that's the philosophy we've taken a bottleneck first huge huge philosophy I really believe in. Like for us right now the bottleneck is early adopters are using Paper. The people that are more, you know, maybe not an early adopter type are very used to what they're doing now. And they're missing features like comments and components. And so now our bottleneck is actually features again. And so now it's like well that's what we got to go do next. And release that bottleneck to the business. Another just like a tactical thing is just like talking to users every day. So so important. I had a rule the first year of the company I had to talk to a designer every single day and I did it all the way through the year. And that was so useful cuz I learned just how like when you start making the company and the product you just have a different perspective. You can't help it. You have personal knowledge. And so just staying rooted in user conversations is really important.

是的，随着公司成长和扩张，这变得越来越难，因为有很多其他事情在争夺你的时间，把你拉向不同的方向，那些事情看起来很重要，或者当下很紧急。是的。但真正核心的是那些基本的东西：构建产品、和用户交谈，还有，你知道，锻炼或者任何你需要做的事情，这样你就不会因为做前两件事而发疯。但这就是公司的核心，对吧？就是这样。所以很高兴听到你从第一天就这么做了，我相信这已经在你的团队文化中根深蒂固了，现在每个人都在和用户交谈。

Yeah, it gets harder and harder to do that as the company grows and scales also because there's so many other things that are vying for your time and pulling you in different directions and that seem important or here on fire in the moment. Yeah. But really it's those core fundamental things of build your product, talk to users, and you know, exercise or whatever you need to do so you don't go crazy doing the first two things. But that's the core of it for the life of the company, right? And that's it. And so it's cool to hear that you've done that from the very first day and I'm sure it is something that has been instilled culturally in your team now and that everybody is talking to users at this point.

是的。

Yeah.

而且现在每个人都在和用户交谈。

and that everybody is talking to users at this point.

哦，是的。是的，当人们入职时，就像，你必须进入 Discord 和人们交谈，或者在 Slack 里。这真的非常重要。而且不是每个人都舒服。也许他们来自大公司，被告知不能和用户交谈，你知道，但事实是，不，进去吧。你不会搞砸的。你只是学到很多。我认为它指导你的决策。决策在公司里非常重要。你可以看看成功的公司，你可以追溯他们的决策，比如，哦，那是一个转折点。那个决策非常好。所以我认为拥有一个信息灵通的员工基础。比如我不能做公司里的每一个决策。即使只有 12 个人，我也不可能做到。所以如果你能让你的员工真正了解用户以及他们真正想要什么，你就会在各地做出好的决策，你知道，到处都是。而且，是的，这非常重要。

Oh yeah. Yeah, that's when people onboard it's like you yeah, you have to be in the Discord talking to people or in the Slack. It's really really important. And not everyone's comfortable. Maybe they've come from a bigger company where they were told they can't talk to users and you know, it's like no, get in there. You can't screw it up. And you just learn so much. And I think it guides your decision-making. Your decisions are really important in a company. You can kind of look at like successful companies of like you can trace their decisions backwards in time of like oh, that was an inflection point. That decision was really good. And so I think having an informed employee base. Like I can't make every decision in the company. Even at 12 people there's no way I could do that. And so if you can have your employees be really informed about users and what they actually want, you'll have good decisions being made all over, you know, all over the place. And I yeah, it's really important.

你认为设计的下一步是什么？

What do you think is next for design?

嗯，我认为很多设计并没有改变。再说一次，在组织中，设计的功能仍然非常重要，作为探索问题空间、竞争分析、高管利益相关者等等的方式。我们完全没有看到那方面的改变。所以，你知道，我认为设计的功能会保留。如果有的话，我认为我们会看到更多，因为有更多的公司，有更多的软件要制作。所以，我们看到世界上对设计的需求越来越多。我确实认为工具会加速发展，因为我认为我们需要能够以跟上工程和产品团队的速度保持质量水平。软件会发布，不管设计师有没有机会让它变得更好。这有点像竞争格局的现实。那么，我们如何帮助确保设计师能成为对话的一部分，并在发布过程中跟上节奏呢？

Well, I think a lot of design isn't changing. Again, in orgs it's like the function of design is still really important as a way to explore problem space, competitive analysis, executive stakeholders, things like this. We're not seeing that change at all. And so, you know, that function of design I think is sticking around. If anything, I think we're going to see more because there are more companies and there's more software to be made. So, we're seeing just more and more design need in the world. I do think the tooling is going to accelerate because I think we just need to be able to keep the quality bar up at a pace that is, you know, keeping up with the engineering, with the product teams. The software will ship whether the designer gets a chance to make it better or not. It's just kind of like a reality of the competitive landscape. So, how do we help make sure that the designer can be part of the conversation and keep up in that shipping process.

但你知道，我觉得总的来说，有时候我认为变化并没有人们想象的那么大，因为我觉得很多设计是一个非常人性化的问题，最终的像素只是过程的输出，你懂的。

But, you know, I think in general, sometimes I think there's less change coming than people think, actually, because I think that a lot of design is a very human problem, and the pixels at the end are like the output of the process, you know.

说到底，它只是媒介，对吧？

It's the medium at the end of the day, right?

没错。是的。是的。

Exactly. Yeah. Yeah.

那 Paper 接下来有什么计划？

And what's next for Paper?

嗯，我们正在，就像我说的，我们在构建一些基础组件、评论、瓶颈消除器。我真的很兴奋。从与用户的交流中我学到的是，人们到处都在构建各种原型，它们最终放在 Vercel 上或作为 HTML 文件，而人们不知道如何在这些原型上留下反馈，甚至不知道如何找到别人在谈论的那个原型。所以，我们要做的是，基本上你可以把东西 iframe 到 Paper 画布上，作为一个整理原型的地方，然后人们可以像他们习惯的那样在原型上留下评论。所以，当人们问我们是否在做原型设计时，就像，嗯，算是吧。我们将帮助你组织你的原型，并建立反馈循环。我认为这对那些为设计师构建“氛围编码”游乐场的公司来说是一个巨大的解锁，但结果往往很混乱，他们需要一些工具来帮助组织。所以，这是我们在接下来的 6 个月左右要重点做的事情，因为我们正在构建人们期望的基础功能。

Well, so we are, like I said, we're building out some table stakes components, comments, bottleneck reducers. I'm really excited. Something I've learned from talking to users is people are building all these prototypes all over the place, and they're ending up on Vercel or their HTML files, and people don't know how to leave feedback on them, or how to even find which one someone's talking about. So, what we're going to do is we're going to put basically you can iframe things onto the Paper canvas as a place to keep your prototypes kind of organized, and then people can leave comments as they're used to doing on the prototypes. So, when people ask us if we're doing prototyping, it's like, well, kind of. We're going to help you organize your prototypes and have feedback cycles. And I think this is going to be a really big unlock for companies that are, you know, building playgrounds for the designers to vibe code in, but then it's kind of like this messy result and they need some tool to help them organize that. So, that's a big thing we're going to be working on the next, you know, 6 months or so as we're building out the table stakes that people expect.

太棒了。Steven，非常感谢你来做客，和我们分享 Paper，以及你所有的设计见解，我知道这些年来你在你建立的公司和你工作过的那些不可思议的地方，这些见解来之不易。所以，谢谢你。

Amazing. Steven, thank you so much for coming on and sharing Paper with us and all of your design insight that I know has been hard-earned over the years and the companies that you've built and the incredible places you've worked. So, thank you.

是的，非常感谢你的邀请。

Yeah, thank you so much for having me.

本期《设计评论》就到这里，我们下期再见。

That does it for this episode of Design Review, and we'll see you on the next one.