Загрузка видео...

Не удалось загрузить видео

На главную

Today, we’re open-sourcing the draft specification for DESIGN.md, so it can be used across any tool or platform. We’re also adding new capabilities. DESIGN.md lets you easily export and import your design rules from project to project. Instead of guessing intent, agents know exactly what a color is for...

6,858,116 просмотров • 5 месяцев назад •via X (Twitter)

Комментарии: 36

Фото профиля Stitch by Google
Stitch by Google5 месяцев назад

We’ve also given DESIGN.md some new exciting capabilities: ✨ Tokens Section: A new area that keeps your design tokens and natural language descriptions living together in the exact same file. 🧩 Components Section (WIP): We are experimenting with a new section to define components, and we want your feedback! 🛠️ CLI Validator: The repo includes a CLI tool to validate your design.md file against the spec—incredibly useful when building with your own agents.

Фото профиля Stitch by Google
Stitch by Google5 месяцев назад

Let’s build a shared and open visual language for AI design. 🤝 Check out the open-source spec, try out the CLI, and let us know your thoughts on the new Components workflow! 🐙 GitHub Repo: 📰 Read more on The Keyword:

Фото профиля RO
RO5 месяцев назад

Releasing hundreds of design.md files using the specification

Фото профиля web3nomad.eth | atypica.ai
web3nomad.eth | atypica.ai5 месяцев назад

CLAUDE.md for behavior, DESIGN.md for visual intent, Karpathy's wiki .md for accumulated knowledge. we're converging on a spec-file layer that agents read before doing anything. the interesting question is what happens when these files contradict each other.

Фото профиля Ozmen
Ozmen5 месяцев назад

We had also developed our own specs on top of Stitch’s initial release and got good results. This week, we’ll revise them according to the new spec and update the previews.

Фото профиля Bill Zahalan
Bill Zahalan5 месяцев назад

most design systems exist in someone's head and a slack thread. the AI wrapper is just finally forcing teams to write it down

Фото профиля Chen Avnery
Chen Avnery5 месяцев назад

Plain text spec files are becoming the universal agent config layer. CLAUDE.md for behavior, DESIGN.md for visuals, AGENTS.md for coordination. We run 12 agents off structured .md files. Consistency at scale starts with agents reading markdown, not dashboards.

Фото профиля Philipp Tsipman
Philipp Tsipman5 месяцев назад

This is an amazing effort! Love seeing a standard like this. Excited to see where it goes. Tried this on our @tailwindcss-based app. Here’s where it doesn’t quite fit for us yet: * Our theme is dual-mode (light + dark); frontmatter seems like a single flat palette * Our colors live as OKLCH— hex would be lossy * Shadows, easing, and animation tokens don’t seem to have a home in the spec yet * Tailwind v4’s @theme inline already makes our CSS the config, so a separate tailwind.theme.json would drift Definitely watching — excited to see how this grows! Kudos to all involved! 👏👏☺️🙏

Фото профиля Jack Wotherspoon
Jack Wotherspoon5 месяцев назад

Give the man, the myth, the legend @_davideast the tag!

Фото профиля Luong NGUYEN
Luong NGUYEN5 месяцев назад

hmm, same idea, different approach with sleek-ui. and I have built a skill to do exactly that 2 weeks ago

Фото профиля VC Intern
VC Intern5 месяцев назад

This is lowkey huge. If agents can read structured design tokens + rules, you go from "generate UI" -> "generate consistent product systems" That’s the missing layer most AI design tools didn’t have.

Фото профиля Paul Gosnell
Paul Gosnell5 месяцев назад

you can upload your DESIGN.md into Chilled Sites to create an on brand site!

Фото профиля Dave-Thinking
Dave-Thinking5 месяцев назад

Weird that llms let us work with unstructured data, so people structure data for the llms? Were there really no structured data for designs before?

Фото профиля klöss
klöss5 месяцев назад

Google I love you today

Фото профиля Bradley Beach
Bradley Beach5 месяцев назад

love the effort. I've been using DESIGN.md in conjunction with a ds file for quite some time. But standardizing a spec like this will no doubt only improve my own work. Appreciate it.

Фото профиля Sahil Panhotra | Indie Builder
Sahil Panhotra | Indie Builder5 месяцев назад

wow this will really help with designs thank you for opensourcing this 🥰

Фото профиля Bill Zahalan
Bill Zahalan5 месяцев назад

agents coding UI with zero design memory has been silently wrecking shipped products. this is the right fix.

Фото профиля Luis
Luis5 месяцев назад

Ok this is exactly how MAADb @maadb_ai is built for data tracking: YAML frontmatter + typed schema + markdown body, schema-validated and git-committed on every write. DESIGN.md slots right in cleanly. Building a MAADb workbench to help track and index your DESIGN.md files.

Фото профиля Sebastian Buzdugan
Sebastian Buzdugan5 месяцев назад

cool, now give us design.md linters and ci checks or it wont stick

Фото профиля klöss
klöss5 месяцев назад

@juristr very very cool

Фото профиля Hiten Shah
Hiten Shah5 месяцев назад

Yay!!!

Фото профиля Rimas
Rimas5 месяцев назад

very logical to open-source the standard though i would have released a bit more resources for easy integration like agent skills

Фото профиля Brennan McEachran 👨‍🚀
Brennan McEachran 👨‍🚀5 месяцев назад

Love the idea, but curious how it’ll work in practice. The design tokens tend to sit in code (tailwind configs eg) maybe it’s worth the drift risk? Similarly components live in code.

Фото профиля Farid
Farid5 месяцев назад

That's awesome! I especially love the bottom-up approach. Starting with the most basic elements, then moving up to components, blocks, and finally concepts - it feels really logical and scalable.

Фото профиля Chen Avnery
Chen Avnery5 месяцев назад

Plain text spec files are becoming the universal agent config layer. CLAUDE.md for behavior, DESIGN.md for visuals, AGENTS.md for coordination. We run 12 agents off structured .md files. Consistency at scale starts with agents reading markdown, not dashboards.Plain text spec files are becoming the universal agent config layer. CLAUDE.md for behavior, DESIGN.md for visuals, AGENTS.md for coordination. We run 12 agents off structured .md files. Consistency at scale starts with agents reading markdown, not dashboards.

Фото профиля Abdulmuiz Adeyemo
Abdulmuiz Adeyemo5 месяцев назад

You guys need to create Stitch CLI I want that to be able to use the CLI to create a beautiful design with code instead of doing it in the site

Фото профиля fforres
fforres5 месяцев назад

Neat! Also, that @_davideast guy is kinda cool.

Фото профиля Tomas Lau
Tomas Lau5 месяцев назад

@edgarasben you were right, every system, even design system, is just an md file.

Фото профиля Impulse
Impulse5 месяцев назад

@theootu on regarde on apprends

Фото профиля Jean-Patrick Smith
Jean-Patrick Smith5 месяцев назад

@nummanali Its very odd to me this is .md and not… structured data

Фото профиля Mariusz
Mariusz5 месяцев назад

We need to be able to split this into multiple files, having components and tokens in the same file might be cool for demos but in real DS this file will be a million lines long

Фото профиля Leander
Leander5 месяцев назад

you put a fucking css file inside a markdown file

Фото профиля Parth Agarwal
Parth Agarwal5 месяцев назад

This tool is great and honestly awesome for creatives with zero code knowledge like me as well. Would it be possible to export as PNG or PDF or a mode that lets you design for social media or graphic designing?

Фото профиля George
George5 месяцев назад

Standardized design rules that agents can understand and reuse across projects are going to save everyone so much pain. Great move.

Фото профиля Torian
Torian5 месяцев назад

I image this, or some form of it, will have amazing applications for animations and cinema form.. especially if it maintained in a LLM Wiki. Imagine if, when you wrote a script, the LLM understood the colors, animations, tones, etc. of words and phrases and settings, even in relationship to the overall trajectory of the plot and where we currently are in it. I imagine something similar will be coming out for music as well at some point. Sidenote: I never played Portal, but have recently been amazed at the complexity of the dialogue and how it's embedded throughout the gameplay. This was accomplished before AI using if-then triggers. I imagine a simplistic form of this can actually be accomplished through markdown files.

Фото профиля 0xVox
0xVox5 месяцев назад

A state of the art check point being made by Stitch… DESIGN.md is genuinely the greatest layer for design development harness system.

Похожие видео

how to use Google's NEW open source Design.md + AI Skills to make your startup look like a $100 million company in 1 hour: 1. Design.md is an open source file from Google that captures the soul of a design. Typography, colors, spacing, all in one markdown file. You attach it to your prompt and your agent builds beautiful things every time. 2. Think of it this way. The HTML is the finished dish. The design.md is the recipe. The skills are the ingredients. Put them together and everything you build looks consistent and professional. 3. Don't create a design system from scratch. Find a brand you love. Linear, Stripe, Vercel, whatever resonates. Study it. Use ChatGPT or Claude to help you extract the design language into your own design.md file. 4. Build skills on top of your design.md. A landing page skill. A mobile app skill. A motion design skill. A slide deck skill. Each one references the same design.md so everything looks like it came from the same designer. 5. The biggest mistake people make: they nail one screen and then everything else looks generic. Design.md solves this. One file keeps every page, every format, every medium consistent. 6. Use it across everything. Your landing page. Your app. Your pitch deck. Your promo videos. Same DNA. Same taste. Same system. That's what separates a startup that looks real from one that looks vibe-coded. 7. Build a second brain for design inspiration. When you see something beautiful in the real world or online, capture it. Save it. When you're building something new, reference it. Taste is developed, not downloaded. 8. It's obvious but the difference between a product people trust and a product people bounce from is how it looks and feels. Design.md gives you that edge. you can watch below shoutout to Meng To for coming on The Startup Ideas Podcast (SIP) 🧃 and walking through his full workflow. if you want to use AI to actually build gorgeous designs, you'll want to use see this. watch

GREG ISENBERG

512,753 просмотров • 4 месяцев назад

Today, Box is announcing major new AI agent capabilities to let customers tap into the full value of their unstructured data. First, we’re announcing all new updates to the Box AI Studio to make it even easier to build AI agents that tap into your enterprise content for any job function, business process, or industry specific use case. We are also expanding our set of foundational agents that customers will be able to use to work with their enterprise content, including new features like search and research on unstructured data. Next, we’re announcing Box Extract to enable customers to use AI agents seamlessly for complex data extraction from any type of document or content. This makes it easier than ever to pull out data from contracts, invoices, research data, marketing assets, medical charts, and more. Finally, we’re introducing Box Automate, a new workflow automation solution within Box that lets you deploy AI agents across enterprise content-centric workflows. With Box Automate, you can design your business process in a simple drag and drop builder and then drop in AI agents at any step in the process. This ensures agents execute tasks at the right steps in a workflow every time. Best of all, our AI agents and workflow tools are designed to work across any system our customers work within, whether it’s leveraging pre-built integrations, Box APIs, or the new Box MCP Server. Ultimately, all of these capabilities come together to transform how companies can work with their enterprise content. Software has historically only been good at automating work that deals with structured data, which is why ERP, CRM, and HR systems have been mainstays of enterprise software for so long. The data in these systems fits neatly into a database, and the workflows are very ripe for automation. But it turns out most of the work in the world deals with unstructured data. It’s ideating through research documents, working with a client on contracts, reviewing details for a new product launch, looking at a patient’s healthcare record to make a diagnosis, working through due diligence documents for an M&A deal, and so on. For the first time ever, we can begin to bring all new insights and automation to this work with AI agents. At Box, we’re incredibly excited to be on this journey to help customers transform how they work with their most important data.

Aaron Levie

91,863 просмотров • 1 год назад

New Tools for a New Era. Coding agents like Claude and Cursor have dramatically reduced the time it takes to go from idea to functional software. But the experience of designing and refining with them sucks. One reason for this is that while the terminal is an incredible tool for communicating direction with language, it is a terrible tool for defining and exploring visual and interactive objects. Here is one idea for how we might fix a small part of that. In the old world, when you wanted to create a transition or animation in your app, you would type some code, refresh your local server, and click to run your animation. It probably wasn't right, because after all no one can know what 'cubic-bezier(0.3, 0.05, 0.45, 1)' really feels like when you read it. You need to see it. Feel it. Interact with it in a real world context. So you'd edit some values, save, refresh, and keep guessing and checking until it felt right. Today, you can write a quick, single-use tool that's a visual studio for designing animations. You can then configure some components and containers common in all apps, and explore different animations in real time, adjusting key properties, and getting it just right. Then, you can copy a highly detailed prompt (or export a skill containing all your animations) that captures your intent and direction with perfect clarity. Paste this into your terminal and your agent instantly implements it everywhere. To me, this is an improvement over the old world, and a better way to work in today's. I'm extremely excited to see the ways in which our ability to rapidly create software will shape how we design software tomorrow. Feedback, ideas, and critiques welcome!

joshpuckett

82,659 просмотров • 8 месяцев назад