用AI Agent做世界级设计的三步法与提示技巧
How to turn your AI into a world-class designer
👋 Hey there, I’m Lenny. Each week, I share deeply researched product, growth, and career advice. For more: Lenny’s Jobs | Lenny’s Podcast | Lennybot | How I AI | Become an AI-Native Builder and my other favorite AI/PM courses
👋 大家好，我是 Lenny。每周我都会分享经过深入调研的产品、增长和职业建议。更多内容请访问：Lenny’s Jobs | Lenny’s Podcast | Lennybot | How I AI | 成为 AI-Native Builder 以及我其他最喜欢的 AI/PM 课程
Subscribe now
立即订阅
P.S. Get a full free year of Cursor, Notion, Replit, Lovable, Wispr Flow, Linear, ElevenLabs, Factory, PostHog, Granola, Brain.fm, Waking Up, and more, by becoming an Insider subscriber (while supplies last). Learn more.
附言：通过成为 Insider 订阅会员（数量有限，送完即止），您可以免费获得 Cursor、Notion、Replit、Lovable、Wispr Flow、Linear、ElevenLabs、Factory、PostHog、Granola、Brain.fm、Waking Up 等一年的完整使用权。了解更多。
I’d always thought AI was bad at design. But after reading this mind-blowing post by Anshu Chimala, I realize I was just doing it wrong. Anshu led software engineering and design teams at Apple for 12 years, focusing on research and prototyping for future AI products. He regularly shares design tutorials and demos on X (he’s one of my favorite follows). For deeper dives into crafting distinctive experiences with AI, check out his Substack and connect with him on LinkedIn.
我一直认为 AI 在设计方面表现不佳。但在阅读了 Anshu Chimala 这篇令人惊叹的文章后，我意识到我只是方法不对。Anshu 在苹果公司领导软件和工程设计团队长达 12 年，专注于未来 AI 产品的研究和原型开发。他经常在 X 上分享设计教程和演示（他是我最喜欢的关注对象之一）。想要更深入地了解如何用 AI 打造独特的体验，请查看他的 Substack 并在 LinkedIn 上与他联系。
Let’s get into it.
让我们开始吧。
A conversational calorie tracker, built in three prompts with Claude Fable 5:
一个对话式卡路里追踪器，使用 Claude Fable 5 通过三个提示词构建：
A space exploration game, built in two prompts with Claude Opus 5:
一个太空探索游戏，使用 Claude Opus 5 通过两个提示词构建：
A dynamic landing page, built in three prompts with Claude Opus 5 + GPT-5.6 Sol:
一个动态落地页，使用 Claude Opus 5 + GPT-5.6 Sol 通过三个提示词构建：
I often post AI design demos like these on X. Every time I do, someone inevitably asks, “Why does the model create all this incredible stuff for you, but when I try, I only get generic slop? It’s like you’re using a completely different model.”
我经常在 X 上发布这类 AI 设计演示。每次我发布时，总有人不可避免地问道：“为什么模型能为你创造所有这些令人难以置信的东西，但当我尝试时，我只能得到千篇一律的垃圾内容？这就像你在使用完全不同的模型一样。”
I’m not using a different model, but I am getting more out of the models I work with. Most people only see 1% of AI’s creative potential. I want to show you how to tap into the other 99%.
我并没有使用不同的模型，但我确实从所使用的模型中获得了更多收益。大多数人只看到了 AI 创意潜力的 1%。我想向你展示如何挖掘剩下的 99%。
AI models are capable of amazing creativity, but that creativity gets stifled by how they’re trained. Large language models are next-token predictors: at each step, they look at a sequence of text and predict what comes next based on millions of examples. The results may be rated by humans, and those ratings fed back into the model. This teaches the model to make consistent, safe choices that fit everyone’s preferences.
AI 模型具备惊人的创造力，但这种创造力因其训练方式而受到抑制。大型语言模型是下一个词预测器：在每一步中，它们查看一段文本序列，并基于数百万个示例预测接下来的内容。结果可能会由人类进行评级，并将这些评级反馈回模型。这教会模型做出一致、安全且符合所有人偏好的选择。
This makes typical LLMs great at most tasks but poor designers. To create a design, an LLM has to build it out token by token. Whenever it needs to make a design decision—what colors to use, or how to arrange elements—the model fills in the tokens it thinks are most likely to please everyone. As a result, the design usually ends up being repetitive and bland. It’s like the ultimate case of design-by-committee.
这使得典型的 LLM 擅长大多数任务，却不擅长设计。要创建设计，LLM 必须逐个 token 地构建它。每当它需要做出设计决策——比如使用什么颜色，或如何排列元素——模型就会填入它认为最可能取悦所有人的 token。结果是，设计通常最终变得重复且乏味。这就像是“委员会式设计”的终极案例。
Great design, on the other hand, starts with feeling and aims to create an emotional response. It bends the rules and delights users with memorable, unexpected choices. Great design is exactly the opposite of what an LLM does naturally, which is to make the most predictable choice at every step.
另一方面，优秀的设计始于情感体验，旨在引发情感共鸣。它打破常规，通过令人难忘且出人意料的抉择让用户感到愉悦。优秀的设计恰恰与 LLM（大语言模型）的自然行为相反，后者在每个步骤中都倾向于做出最可预测的选择。
However, if we can get the model to reach beyond the most predictable choices, we can access a vast landscape of creative ideas that most people miss out on.
然而，如果我们能让模型超越那些最可预测的选择，我们就能触及一个广阔的创意领域，而大多数人往往错失这些机会。
This is a lesson I learned from managing human designers, before I was managing AI ones. For most of my career at Apple, I led an R&D team designing exploratory future AI products. Early on, our preconceived notions about how user interfaces should work limited our creativity and kept us returning to the same old ideas. Through rigor and new processes, we learned to stop re-creating what’s comfortable and instead look to the fringes of what’s possible, to generate something new. We became experts at polishing the little details to an Apple level of quality.
这是我在学习管理人类设计师时学到的教训，当时我尚未开始管理 AI 设计师。在 Apple 的大部分职业生涯中，我领导着一个 R&D 团队，负责设计探索性的未来 AI 产品。起初，我们对用户界面运作方式的先入之见限制了我们的创造力，使我们不断回到那些老套的想法上。通过严谨的态度和新的流程，我们学会了停止重复舒适区内的内容，转而关注可能性的边缘，以生成全新的事物。我们成为了将细微细节打磨至 Apple 级别品质的专家。
Since my time at Apple, I’ve been working on applying that same process to my work with AI. In the past couple years, AI agents have become extremely capable. They can do in hours what used to take my team weeks. And with the right guidance, they can create designs that look completely unlike anything else.
自从我离开 Apple 以来，我一直在致力于将同样的流程应用到我的 AI 工作中。在过去几年里，AI 智能体已经变得极其强大。它们能在几小时内完成过去需要我的团队花费数周才能完成的工作。而在正确的引导下，它们能够创造出完全不同于其他任何事物的设计。
Loosely inspired by the Double Diamond design process, I’ve reimagined the design process for a team of AI agents instead of human designers:
loosely 受双钻设计流程的启发，我重新构想了一个面向 AI 智能体团队而非人类设计师的设计流程：
- Discover new ideas beyond the average slop by exploring a variety of directions and creating bold, ambitious design briefs.
- Define an individual design identity by pushing AI beyond its familiar patterns and chaining models together to fully realize the design’s potential.
- Deliver a stunning final result by polishing away the sloppy rough edges and focusing on the key elements.
- 通过探索多种方向并制定大胆、雄心勃勃的设计简报，发现超越平庸垃圾信息的创新想法。
- 通过将 AI 推离其熟悉的模式并将多个模型串联起来以充分实现设计的潜力，定义独特的设计身份。
- 通过打磨掉粗糙的边缘并聚焦于关键元素，交付惊艳的最终成果。
By following these stages and applying the techniques within each one, you can create an incredible design remarkably quickly—and make people ask, “Why does AI create magic for you (and not me)?”
通过遵循这些阶段并应用其中的技巧，你可以非常快速地创造出令人惊叹的设计——并让人们不禁问道：“为什么 AI 能为你创造魔法（而不是为我）？”
Discover: Explore the space of possibilities
探索：发掘可能性的空间
The hardest part of the design process is looking at a blank screen with infinite possibilities. The best way to tackle that moment is to start by going broad before going deep. AI is an excellent tool to explore a wide variety of potential directions.
设计过程中最难的部分是面对拥有无限可能的空白屏幕。应对这一时刻的最佳方式是先广泛探索，再深入挖掘。AI 是一个探索各种潜在方向的绝佳工具。
As we know, though, models tend to overrely on familiar patterns and make conservative choices. To explore the full potential design space, we want to coax a model to do the opposite: be bold, be varied, and take risks. Below are two ways to push it out of its comfort zone.
然而，正如我们所知，模型往往过度依赖熟悉的模式并做出保守的选择。为了探索完整的设计空间潜力，我们希望引导模型采取相反的做法：大胆、多样且敢于冒险。以下是两种将其推出舒适区的方法。
Technique 1: Use seed strings to inject variety
技巧 1：使用种子字符串注入多样性
The idea here is to get the model to find a new source of inspiration for designs, rather than relying on the defaults it learned from training. If you’ve tried to prompt a model to design a website or app, you’ve probably already seen what that default looks like.
这里的想法是让模型找到设计的新灵感来源，而不是依赖从训练中学到的默认设置。如果你曾尝试提示模型设计网站或应用，你可能已经见过那种默认效果是什么样的。
As a simple example, I gave four instances of Claude Code the same prompt:
作为一个简单的例子，我给四个 Claude Code 实例发送了相同的提示：
Prompt:
提示：
Build me a landing page for my productivity app.
为我构建一个生产力应用的落地页。
Claude Opus 5:
Claude Opus 5：
Almost every time, we get a purplish gradient, text on the left, graphic on the right, and the exact same structure. It looks like every AI-designed website ever.
几乎每次，我们都会得到紫红色渐变、左侧文字、右侧图形，以及完全相同的结构。它看起来就像有史以来所有由 AI 设计的网站。
We didn’t ask the model to do anything unique or varied, so it makes sense that it keeps falling back on the same patterns it knows well. But just asking for variety doesn’t work:
我们并没有要求模型做任何独特或多样的事情，所以它不断回归到熟悉的模式是有道理的。但仅仅要求多样性是行不通的：
Prompt:
提示：
Build me a landing page for my productivity app. Give me something totally unique. Make every design decision completely at random.
为我构建一个生产力应用的落地页。给我一些完全独特的东西。让每一个设计决策都完全随机。
Claude Opus 5:
Claude Opus 5：
The results are different from before, but they’re still not varied. The model always uses the same color scheme, structure, and even the same awkward pottery metaphors. It’s predicting tokens that sound random but aren’t actually random.
结果与之前不同，但仍然缺乏多样性。模型总是使用相同的配色方案、结构，甚至是同样的尴尬陶器比喻。它预测的是听起来随机但实际上并不随机的 token。
The problem is that the model can’t inherently act randomly. It can only predict the most likely token. If we want variety, we have to bring it from outside the model. One technique for this is String Seed of Thought, published by Sakana AI. We make the AI generate a random string and use it as design inspiration. That way, the model is truly making different decisions each time.
问题在于模型无法本质上随机行动。它只能预测最可能的 token。如果我们想要多样性，就必须从模型外部引入。一种为此采用的技术是 Sakana AI 发表的“思维字符串种子”（String Seed of Thought）。我们让 AI 生成一个随机字符串并将其作为设计灵感。这样，模型每次才能真正做出不同的决策。
Prompt:
提示：
I want you to build me a landing page for my productivity app.
我想让你为我构建一个生产力应用的落地页。
Follow this procedure:
遵循以下流程：
- Generate a long, random alphanumeric string using a shell script.
- Define the creative direction (color scheme, layout, typography, etc.) based on the string. Look beyond the surface for subpatterns, special numbers, anything that inspires you.
- Use your judgment to bring this direction to life and make it look great.
- 使用 shell 脚本生成长度较长的随机字母数字字符串。
- 根据该字符串定义创意方向（配色方案、布局、排版等）。超越表面寻找子模式、特殊数字或任何能激发你灵感的事物。
- 运用你的判断力将这个方向变为现实，使其看起来很棒。
Don’t reveal the string in the design. It’s only for your inspiration.
不要在设计中透露该字符串。它仅用于你的灵感。
Claude Opus 5:
Claude Opus 5：
Suddenly the outputs are much more varied! Now we’re seeing different color schemes, fonts, and new ideas. The previous designs were ones that any Claude user could get. These designs are one-of-a-kind; no two runs ever produce the same result.
突然，输出结果变得丰富多样！现在我们看到了不同的配色方案、字体和新创意。之前的设计是任何 Claude 用户都能得到的。这些设计是独一无二的；没有两次运行会产生相同的结果。
Technique 2: Be much more ambitious with your prompts
技巧二：在提示词中更加大胆
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力