# How to build something small
**作者**: Zara Zhang
**日期**: 2026-05-02T05:22:30.000Z
**来源**: [https://x.com/zarazhangrui/status/2050445806428438734](https://x.com/zarazhangrui/status/2050445806428438734)
---
Most people teach you how to build something big. But I think we should learn how to build something small.
Here are a few small things I've built. All of these were built as side projects for fun:
1. Frontend Slides (16k stars on GitHub): a skill that lets you create beautiful HTML slides with coding agents
2. Follow Builders (3.6k stars on GitHub): a skill that gives you a daily newsletter consisting of tweets and podcasts from a strictly curated list of AI builders
3. Tab Out (1.1k stars on GitHub): a Chrome extension that turns your New Tab page into a Mission Control where you can clearly see your open tabs and easily close them
# Why build something small?
## 1. Every big thing starts as a small thing
Positioning is everything. Most products fail not because they were too narrow, but because they targeted too wide.
If you're everything to everybody, you end up being nothing to nobody. You become a generic, bland thing that will be eaten by Claude.
## 2. Build for fun, build to learn
Don't take software too seriously.
Building software used to be a serious, utilitarian pursuit. People mostly did it to make money. This made sense when software was scarce and expensive.
But now that software is cheap and abundant, you can actually do it for fun. Vibe coding is basically my weekend hobby now, and some of my little skills feel more like art projects. We need to overcome the scarcity mindset for software. You're totally allowed to build something useless.
Building something is also the best way to learn. In the traditional education system, you learned to build. In the AI era, this is now reversed: you build to learn.
## 3. Build an opinionated product
Software is a form of self-expression. When you build a piece of software, you're embedding a little piece of your soul in it: your unique way of thinking and doing something.
Now that AI can build anything really quickly, what makes people want to use your software, not somebody else's?
Your product needs to have character. It needs to make people feel like "huh, I've never thought about it this way before, but it makes a lot of sense." People will use it because the opinion behind it resonates with them.
If your product is just some generic, bland productivity tool, people may as well just use Claude.
Case in point: there are so many AI news fetching skills out there; my Follow Builders skill resonated with people because they liked the underlying philosophy of "follow builders, not influencers."
## 4. You can afford to
Before AI, you couldn't afford to build something small. Because the cost of software development was so high, you had to hire a team, convince other people, justify it to a committee.
Now, it's literally just you and a coding agent. A coding agent doesn't need to be convinced. It will readily build whatever crazy and weird idea you have. So go build something that would get rejected in every big tech company's product review meeting.
# How to find product ideas
## 1. You're not that unique
A lot of people tell me "I have this pain point that I want to build a product for, but I'm worried it would be too niche."
I want to tell them: sorry that this sounds harsh, but you're not as unique as you think you are.
Whatever super niche pain point you have, there are at least 10k people in the world who share the same pain point. Maybe not 10 million, but definitely 10k.
In the old world, a product with a 10k total addressable market was not worth building. In the new world, a product with a 10k user base is a very successful side project.
What you think might be an extremely niche need might not be as niche as you think. You just need to find those 10k people who are as weird as you.
## 2. Start with the technology
For most of my projects, I actually didn't start with the pain point. I started with the technology. Every day I browse X and bookmark cool new technologies and APIs that come out. Then I have a regular "playtime" where I just feed my coding agent these new technologies and we brainstorm what we can build with them. It's a lot of fun.
Case in point: I built Tab Out because I first saw someone build something that reads their Chrome browsing history, and that's how I found out your browsing history is saved locally in a database. So I brainstormed with Claude what we could do with it, and after lots of discussion and iteration, we ended up with a browser extension that helps you close your tabs.
# How to talk to models
## 1. Use the best model
Counterintuitively, it will often end up being cheaper than if you use a dumber model. With a dumber model, you end up not being able to do things correctly, and you spend more tokens and time fixing it.
## 2. Treat it as your cofounder, not your employee
I seldom start by giving a detailed product spec and asking my agent to execute. I just describe my problem extensively, and ask for my agent's opinion. We bounce ideas off each other and come up with the solution together. It's a co-creation process.
Bring the problem, not the solution.
## 3. Try everything, waste tokens
Have an unreasonably high standard. Keep pushing the agent to its limits. Try crazy ideas and see what it does. You can't usually get away with this when working with humans, so make the most of it.
## 4. Cut features before shipping
LLMs are very good at adding things, but not very good at subtracting things. They often end up adding unnecessary features that look plausible at first but turn out to be useless in practice. As humans, your most important job is to subtract, simplify, and cut.
Build something small and elegant. Software is a medium for storytelling. Go tell a great story.
## 相关链接
- [Zara Zhang](https://x.com/zarazhangrui)
- [@zarazhangrui](https://x.com/zarazhangrui)
- [253](https://x.com/zarazhangrui/status/2050445806428438734/analytics)
- [Frontend Slides](https://github.com/zarazhangrui/frontend-slides)
- [Follow Builders](https://github.com/zarazhangrui/follow-builders)
- [Tab Out](https://github.com/zarazhangrui/tab-out)
- [Follow Builders](https://github.com/zarazhangrui/follow-builders)
- [Tab Out](https://github.com/zarazhangrui/tab-out)
- [1:22 PM · May 2, 2026](https://x.com/zarazhangrui/status/2050445806428438734)
- [253 Views](https://x.com/zarazhangrui/status/2050445806428438734/analytics)
---
*导出时间: 2026/5/2 13:34:32*
---
## 中文翻译
# 如何构建一个小而美的产品
**作者**: Zara Zhang
**日期**: 2026-05-02T05:22:30.000Z
**来源**: [https://x.com/zarazhangrui/status/2050445806428438734](https://x.com/zarazhangrui/status/2050445806428438734)
大多数人都教你怎么构建宏大的产品。但我认为，我们应该学习如何构建小而美的东西。
以下是我构建的几个小项目。所有这些都是为了好玩而做的副业项目：
1. Frontend Slides（GitHub 上有 16k 星标）：一个技能，让你可以通过编码代理创建精美的 HTML 幻灯片。
2. Follow Builders（GitHub 上有 3.6k 星标）：一个技能，每天给你发送一份通讯，其中包含经过严格筛选的 AI 创作者的推文和播客。
3. Tab Out（GitHub 上有 1.1k 星标）：一个 Chrome 扩展程序，将你的“新标签页”变成了一个“任务控制中心”，你可以清晰地看到打开的标签页并轻松关闭它们。
# 为什么要构建小而美的东西？
## 1. 每个大事物都始于小事物
定位就是一切。大多数产品失败不是因为它们太窄，而是因为它们的目标太宽。
如果你试图取悦所有人，最后谁也取悦不了。你会变成一个平庸、乏味的东西，最终被 Claude 吞噬。
## 2. 为了好玩而构建，为了学习而构建
不要把软件看得太严肃。
构建软件曾经是一项严肃的、功利性的追求。人们做软件主要是为了赚钱。在软件稀缺且昂贵的时代，这是合理的。
但现在软件既便宜又丰富，你完全可以为了好玩而做。“氛围编码”基本上已经成了我的周末爱好，我的一些小技能项目感觉更像是艺术品。我们需要克服对软件的稀缺心态。你完全被允许构建一些无用的东西。
构建东西也是最好的学习方式。在传统的教育体系中，你是先学会了再去构建。而在 AI 时代，这个顺序颠倒了：你要通过构建来学习。
## 3. 构建有观点的产品
软件是一种自我表达的形式。当你构建一个软件时，你实际上是在其中嵌入了一小部分你的灵魂：你独特的思考和行事方式。
既然 AI 可以非常快速地构建任何东西，是什么让人们想要使用你的软件，而不是别人的？
你的产品需要有个性。它需要让人们感觉：“咦，我从来没从这个角度想过，但这很有道理。”人们会使用它，是因为其背后的观点与他们产生了共鸣。
如果你的产品只是一个平庸、乏味的生产力工具，人们不如直接去用 Claude。
举个恰当的例子：市面上有很多 AI 新闻获取技能；我的 Follow Builders 技能之所以能引起共鸣，是因为人们喜欢其背后的哲学：“关注创作者，而不是网红。”
## 4. 你承担得起
在 AI 出现之前，你承担不起构建小东西的代价。因为软件开发成本太高，你必须组建团队，说服别人，向委员会证明其合理性。
现在，实际上只有你和编码代理。编码代理不需要被说服。无论你有什么疯狂、古怪的想法，它都乐意去构建。所以，去构建那些会在任何大厂产品评审会议上被毙掉的想法吧。
# 如何寻找产品点子
## 1. 你并不独特
很多人告诉我：“我有这个痛点，想为它做个产品，但我担心它太小众了。”
我想告诉他们：抱歉这话听起来很刺耳，但你并不像你想象的那么独特。
无论你的痛点多么小众，世界上至少有 1 万人和你有同样的痛点。也许不是 1000 万，但绝对是 1 万。
在旧世界，一个总潜在市场（TAM）只有 1 万人的产品是不值得构建的。在新世界，一个拥有 1 万用户基数的产品是一个非常成功的副业项目。
你认为可能极其小众的需求，实际上可能没那么小众。你只需要找到那些和你一样古怪的 1 万人。
## 2. 从技术出发
对于我的大多数项目，实际上我并不是从痛点出发的。我是从技术出发的。每天我都会浏览 X（推特），并收藏出现的新技术和 API。然后我会定期进行“游戏时间”，把这些新技术投给我的编码代理，我们头脑风暴看看能用它们做什么。这非常有趣。
举个恰当的例子：我构建 Tab Out 是因为我最初看到有人构建了一个读取 Chrome 浏览历史的东西，这让我发现你的浏览历史是保存在本地数据库中的。所以我与 Claude 头脑风暴我们可以用它做什么，经过大量的讨论和迭代，我们最终做出了一个帮助你关闭标签页的浏览器扩展。
# 如何与模型对话
## 1. 使用最好的模型
反直觉的是，这通常最终比使用更笨的模型更便宜。使用更笨的模型，你往往无法正确完成任务，反而要花费更多的 token 和时间去修复。
## 2. 把它视为联合创始人，而不是员工
我很少在开始时就给出详细的产品规格说明并要求我的代理去执行。我只是广泛地描述我的问题，并征求代理的意见。我们互相交换想法，共同得出解决方案。这是一个共同创造的过程。
带来问题，而不是解决方案。
## 3. 尝试一切，挥霍 Token
设定一个不切实际的高标准。不断 pushing 代理的极限。尝试疯狂的想法，看看它能做什么。你在与人工作时通常不能这样肆无忌惮，所以要充分利用这一点。
## 4. 发布前削减功能
LLM 非常擅长增加功能，但不擅长削减功能。它们最终往往会添加一些乍一看很合理但实际上毫无用处的不必要功能。作为人类，你最重要的工作是做减法、简化和删减。
构建一些小而优雅的东西。软件是讲述故事的媒介。去讲一个好故事吧。
## 相关链接
- [Zara Zhang](https://x.com/zarazhangrui)
- [@zarazhangrui](https://x.com/zarazhangrui)
- [253](https://x.com/zarazhangrui/status/2050445806428438734/analytics)
- [Frontend Slides](https://github.com/zarazhangrui/frontend-slides)
- [Follow Builders](https://github.com/zarazhangrui/follow-builders)
- [Tab Out](https://github.com/zarazhangrui/tab-out)
- [Follow Builders](https://github.com/zarazhangrui/follow-builders)
- [Tab Out](https://github.com/zarazhangrui/tab-out)
- [1:22 PM · May 2, 2026](https://x.com/zarazhangrui/status/2050445806428438734)
- [253 Views](https://x.com/zarazhangrui/status/2050445806428438734/analytics)
---
*导出时间: 2026/5/2 13:34:32*