I made a tool that generates UIs with a design system that's copyable as prompts.
Everything is a prompt: font pairings, color system, spacing, icon sets, buttons and even webgl & threejs with full code samples.
This made explorations with Gemini 3.1 Pro so precise and fun.
Readout is a fully native macOS app I’ve been building for myself. It provides a real-time overview of your dev environment and Claude Code config. All local, no account required. It's still very much a beta, but now available to try: https://t.co/gpKj1KCpcM
I am happy to share that we (the @GoogleAIStudio team) are now a sponsor of the @tailwindcss project! Honored to support and find ways to do more together to help the ecosystem of builders.
In @GeminiApp this is what you're working with now:
Fast = 3 Flash
Thinking = 3 Flash (with thinking)
Pro = 3 Pro (with thinking)
Our best line-up yet!
In @GeminiApp this is what you're working with now:
Fast = 3 Flash
Thinking = 3 Flash (with thinking)
Pro = 3 Pro (with thinking)
Our best line-up yet!
Top feature request unlocked!
You can now attach a notebook made in @NotebookLM right inside @GeminiApp! Starting on the web, mobile next year. We just snuck this one in!
Introducing shadcn/create – Build your own shadcn/ui
Customize Everything. Pick your component library, icons, base color, theme, fonts and build something that doesn’t look like everything else.
Now available for Next.js, Vite, TanStack Start and v0.
工具型产品创业,有个共识是:上手要简单,要让用户尽快达到 aha moment 并付费。
这个共识没错,但对创业的用途不大。就像有人跟你讲:饮食要健康。
这共识还有个陷阱:容易把产品直接简单化。比如做成在特定场景下,非常简单好用的小工具。如果推广渠道合适,也有机会快速获取到第一波用户。
然后,用户会开始提各种需求,好用的小工具,会开始复杂。到一定阶段,甚至需要推翻重来。这过程中,奔着简单而来的原有用户,有可能会流失掉。或者为了兼顾简单和复杂,开始在产品上打各种补丁。
以上故事的背后,是通过简单,先吃到了第一口糖。最大的陷阱是,吃过第一口糖后,就会忍不住想吃第二口、第三口,鲜有愿意停下来,先饿上一段时间,重新思考并打磨产品,后续再继续吃糖的。
于是有了一个做工具型产品的非共识:不要一开始就追求简单易用,而是要想清楚究竟要满足什么用户需求,产品整体如何设计。
如同建房子。先有愿景,有蓝图。接着挖地基、搭结构。然后一层一层建。每建一层,可以邀请合适的用户进来住住。这时大概率是住着不舒服的。
先整体再部分,先复杂再简单,或许才是做工具型产品的正确方式。历史上可借鉴的案例故事是:Notion、Figma、Linear 等产品。
AI 时代的工具,更像一个个房子,用户入住后,需要和 AI 一起产生上下文,一起去做事。
AI 时代的好工具,不再会是各种各样的锤子。