Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Codex + Moonchild just turned a $10k design sprint into a 60-minute solo workflow This builder connected Codex to Moonchild and generated: - a complete design system - every core app screen - production-ready frontend code All in under an hour: Most startups still pay $3k-$10k for screens that... sit in Figma for weeks Then another sprint gets burned turning those screens into real components That workflow is getting replaced: - Moonchild builds the product's design system - Codex reads the system - The app gets built inside those constraints - No generic mockups - No messy handoff - No "looks different in production" tax The important part is not that AI can make pretty UI The important part is that Codex is no longer guessing taste from screenshots It has the rails: - tokens - components - states - layout rules - product patterns That's where design agencies get squeezed Not the top 1% with taste, brand strategy, and real product thinking The generic SaaS UI shops selling "premium screens" as a Figma file That offer is cooked The new agency is one operator with: - a strong design system - a coding agent - one afternoon And the gap between idea and production UI just got a lot smallershow more

ZEUS⚡️

30,967 subscribers

13,274 просмотров • 4 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 20

Фото профиля Hussain Hashim | Building SundayBack

Hussain Hashim | Building SundayBack4 месяцев назад

@zeuuss_01 whoa, that's crazy efficient. wish I could've saved that kind of time on my last project 😂

Фото профиля RH Fardin

RH Fardin1 месяц назад

A full design system, screens, and frontend in an hour is exactly where Codex shines. Strong workflow.

Фото профиля Max

Max4 месяцев назад

one afternoon agency? this is cooked for figma shops kaka 🫡

Фото профиля duhao

duhao4 месяцев назад

Figma tax cooked

Фото профиля Moath 🦇

Moath 🦇4 месяцев назад

figma shops are cooked lol

Фото профиля kiyosaki

kiyosaki4 месяцев назад

デザインと開発の間に新しい架け橋ができました。アイデアから実際のUIまでのギャップが大幅に縮まりました。

Фото профиля Jack

Jack4 месяцев назад

game changer! efficiency's never looked better

Фото профиля Daily Story

Daily Story4 месяцев назад

The shift from Figma to instant design systems is huge! Production-ready designs in under an hour is a game changer.

Фото профиля 叮叮当 | 买球上启胜

叮叮当 | 买球上启胜4 месяцев назад

这波操作属实猛啊🚀

Фото профиля Dwgs

Dwgs4 месяцев назад

figma shops just got put on borrowed time 😭

Фото профиля dllr

dllr4 месяцев назад

figma shops are cooked

Фото профиля Ethan Cole | Trading Mindset

Ethan Cole | Trading Mindset4 месяцев назад

this is the real unlock.

Фото профиля Jeak

Jeak4 месяцев назад

figma shops are officially on borrowed time 😭

Фото профиля 蜜桃团子🍑

蜜桃团子🍑4 месяцев назад

This workflow's actually insane

Фото профиля Chill with Mei 🌥️

Chill with Mei 🌥️4 месяцев назад

this shrinks the idea to live uo gap crazy fast

Фото профиля dopo.eth 💸

dopo.eth 💸4 месяцев назад

this unlocks solo founders for real

Фото профиля Cry✨Star

Cry✨Star4 месяцев назад

this kills the figma tax fast

Фото профиля Weq

Weq4 месяцев назад

agency guys on borrowed time 😭

Фото профиля Chexxe

Chexxe4 месяцев назад

figma shops are getting squeezed hard ngl

Фото профиля Junk 🛠️

Junk 🛠️4 месяцев назад

figma shops are officially sweating now 😭

Похожие видео

HE TURNED A $9,000 UI HANDOFF INTO A 3D SAAS INTERFACE IN 30 MINUTES this guy didn’t build another flat dashboard, he built a living 3d workspace with Claude Code reading the structure, logic and components instead of guessing from screenshots Moonchild makes the design system first: tokens, spacing, cards, charts, navigation, typography, then Claude turns it into a working React app through MCP 2 tools, 1 design system, 8+ screens and a second Claude checking drift while most founders still pay agencies to align buttons by hand save the full breakdown before your next SaaS looks like 6 templates fighting for custody of the same logo ↓

Gipp 🦅

11,041 просмотров • 3 месяцев назад

CLAUDE JUST COLLAPSED THE ENTIRE DESIGN STACK INTO A CHAT WINDOW. Canva. Figma. Slide decks. UI mockups. Infographics. All compressed into prompts. This video barely looks real. One prompt generates a full mobile app interface. Another turns random files into polished presentations and PDFs. Then the craziest part: you can export the entire design directly into Claude Code and continue building it instantly. The wall between design and development is disappearing in real time. The math nobody is doing. A startup that needed: • a UI designer • a presentation designer • a frontend mockup artist can now prototype everything in one workflow before hiring anyone. That changes who gets to build. A solo founder with taste and good prompts suddenly has capabilities that required entire creative teams in 2024. The bottleneck is no longer software. It’s judgment.

CLAUDE JUST COLLAPSED THE ENTIRE DESIGN STACK INTO A CHAT WINDOW. Canva. Figma. Slide decks. UI mockups. Infographics. All compressed into prompts. This video barely looks real. One prompt generates a full mobile app interface. Another turns random files into polished presentations and PDFs. Then the craziest part: you can export the entire design directly into Claude Code and continue building it instantly. The wall between design and development is disappearing in real time. The math nobody is doing. A startup that needed: • a UI designer • a presentation designer • a frontend mockup artist can now prototype everything in one workflow before hiring anyone. That changes who gets to build. A solo founder with taste and good prompts suddenly has capabilities that required entire creative teams in 2024. The bottleneck is no longer software. It’s judgment.

Deydara

11,601 просмотров • 4 месяцев назад

Claude Code is CRACKED at design now and I don't think people understand how BIG this is. There is now one tool that takes you from a rough idea to fully designed, agency-tier, App Store-ready screens in minutes. One design system, every screen, real native code. Most builders hand design to Claude Code, get AI-default screens, and wonder why their app looks like every other vibe coded project. This is the 3-step workflow that fixes it: (full breakdown in the article)

Claude Code is CRACKED at design now and I don't think people understand how BIG this is. There is now one tool that takes you from a rough idea to fully designed, agency-tier, App Store-ready screens in minutes. One design system, every screen, real native code. Most builders hand design to Claude Code, get AI-default screens, and wonder why their app looks like every other vibe coded project. This is the 3-step workflow that fixes it: (full breakdown in the article)

Prajwal Tomar

106,397 просмотров • 2 месяцев назад

I still don't think people understand what just happened with Claude Code. There is now one tool that takes you from a rough idea to fully designed, agency-tier, App Store-ready screens in minutes. One design system, every screen, real native code. Most builders hand design to Claude Code, get AI-default screens, and wonder why their app looks like every other vibe coded project. This is the 3-step workflow that fixes it: (full breakdown in the article)

I still don't think people understand what just happened with Claude Code. There is now one tool that takes you from a rough idea to fully designed, agency-tier, App Store-ready screens in minutes. One design system, every screen, real native code. Most builders hand design to Claude Code, get AI-default screens, and wonder why their app looks like every other vibe coded project. This is the 3-step workflow that fixes it: (full breakdown in the article)

Prajwal Tomar

146,206 просмотров • 3 месяцев назад

Codex is not just a coding agent anymore. It is becoming a skill-based operating system. Most people still ask it to “build the app”. Better builders give it specialised skills: frontend design browser automation market research lead research Figma implementation copywriting customer research cold email content strategy That is the real shift. One agent with no skills guesses. One agent with the right skills follows a process. The next advantage is not who writes the longest prompt. It is who builds the best toolbelt around the agent. Stop starting every task from zero. Give Codex the skills for the job. Bookmark this before you ask a general agent to do specialist work again.

Codex is not just a coding agent anymore. It is becoming a skill-based operating system. Most people still ask it to “build the app”. Better builders give it specialised skills: frontend design browser automation market research lead research Figma implementation copywriting customer research cold email content strategy That is the real shift. One agent with no skills guesses. One agent with the right skills follows a process. The next advantage is not who writes the longest prompt. It is who builds the best toolbelt around the agent. Stop starting every task from zero. Give Codex the skills for the job. Bookmark this before you ask a general agent to do specialist work again.

Fluixo

26,556 просмотров • 3 месяцев назад

After testing every AI toolchain for a year, this is the only workflow I'm endorsing: Figma → Claude Code (Sonnet 4.5) Here's how I'm building Lorelight: 1. Design the happy path in Figma 2. Feed it to Claude Code via Figma MCP 3. Get a strong foundation in 15 minutes 4. Spend the next 50+ hours iterating (still design work) The design/dev loop that used to be isolated is finally closing. I even built a complete design system in within minutes. Custom components, living documentation, accessibility rules all from the Figma designs. If you're measuring the effectiveness of these tools by whether they can "one-shot" a design, you're consuming too many AI hype commercials. Log off. Then go actually build something with your hands. With AI. With your taste. Stop trying to "one-shot" good shit. And go make stuff with the new tools. For designers who want to ship real products, this is the stack that's getting it done.

After testing every AI toolchain for a year, this is the only workflow I'm endorsing: Figma → Claude Code (Sonnet 4.5) Here's how I'm building Lorelight: 1. Design the happy path in Figma 2. Feed it to Claude Code via Figma MCP 3. Get a strong foundation in 15 minutes 4. Spend the next 50+ hours iterating (still design work) The design/dev loop that used to be isolated is finally closing. I even built a complete design system in within minutes. Custom components, living documentation, accessibility rules all from the Figma designs. If you're measuring the effectiveness of these tools by whether they can "one-shot" a design, you're consuming too many AI hype commercials. Log off. Then go actually build something with your hands. With AI. With your taste. Stop trying to "one-shot" good shit. And go make stuff with the new tools. For designers who want to ship real products, this is the stack that's getting it done.

Tommy Geoco

22,905 просмотров • 11 месяцев назад

Turn any website into an AI-readable design system. Here's how: Google recently introduced the DESIGN.md specification: a file that helps AI agents understand a product’s design system. So we built a free tool for designers. Paste any website URL and Masumi’s DESIGN.md Generator extracts the brand’s colors, typography, components, spacing, and visual rules into an editable DESIGN.md file. Your designer can review it, tweak it, and hand it to Claude Code, Cursor, Codex, or any AI coding agent so the generated UI stays on-brand. Links below

albina

26,087 просмотров • 4 месяцев назад

Every frontend developer just stopped opening DevTools. Your AI coding agent can now reverse-engineer the entire design system of any website directly from the terminal. Just type: /design And it instantly extracts: • Brand colors • Fonts & typography • Spacing system • Buttons & UI components • Layout patterns • Design tokens Then saves everything into a structured DESIGN.md file your AI agent can understand and reuse. Powered by Hyperbrowser + Claude Code MCP. The crazy part? You can now study, replicate, and rebuild world-class UI systems in minutes instead of wasting hours manually inspecting websites. This changes how vibe coding works forever. Repo👇

divyansh tiwari

78,201 просмотров • 4 месяцев назад

I gave Codex one idea: A screen-time app for kids that doesn’t feel like a punishment. Then it helped turn that idea into Peekaboo, a gentle mobile app built around a tiny purple character with a sprout on its head. 🌱 The workflow was wild: 🎨 GPT Image 2.0 shaped the cozy visual world, mascot poses, sticker rewards, and app-store-style mockups 🧠 GPT-5.5 helped design the product logic: timers, breaks, rewards, parent moments, and kid-friendly microcopy 📱 Codex pulled it together into an interactive mobile app prototype with real screens, transitions, animations, and state Prompt below 👇

I gave Codex one idea: A screen-time app for kids that doesn’t feel like a punishment. Then it helped turn that idea into Peekaboo, a gentle mobile app built around a tiny purple character with a sprout on its head. 🌱 The workflow was wild: 🎨 GPT Image 2.0 shaped the cozy visual world, mascot poses, sticker rewards, and app-store-style mockups 🧠 GPT-5.5 helped design the product logic: timers, breaks, rewards, parent moments, and kid-friendly microcopy 📱 Codex pulled it together into an interactive mobile app prototype with real screens, transitions, animations, and state Prompt below 👇

Bas Fijneman

74,717 просмотров • 5 месяцев назад

CLAUDE DESIGN SKILLS CAN TURN A $20 PLAN INTO A JUNIOR DESIGN SYSTEM ASSISTANT A blank prompt makes Claude judge design like a generalist, one screen at a time, with too much room for random taste and vague feedback Design Skills give it a repeatable way to look at interface work: spacing, hierarchy, contrast, component consistency, states, layout rhythm, and the small visual rules that make a product feel finished That is where it becomes useful for a designer, it can review a rough screen, catch what feels off, suggest a cleaner structure, keep repeated components aligned, and explain the changes in a way that feels closer to a design lead than a prompt response The value is not that Claude becomes "creative" and the value is that its judgment becomes repeatable, so the same design standards can be applied across every screen instead of being rebuilt from scratch in every chat Check the full article about cowork and skills below

CLAUDE DESIGN SKILLS CAN TURN A $20 PLAN INTO A JUNIOR DESIGN SYSTEM ASSISTANT A blank prompt makes Claude judge design like a generalist, one screen at a time, with too much room for random taste and vague feedback Design Skills give it a repeatable way to look at interface work: spacing, hierarchy, contrast, component consistency, states, layout rhythm, and the small visual rules that make a product feel finished That is where it becomes useful for a designer, it can review a rough screen, catch what feels off, suggest a cleaner structure, keep repeated components aligned, and explain the changes in a way that feels closer to a design lead than a prompt response The value is not that Claude becomes "creative" and the value is that its judgment becomes repeatable, so the same design standards can be applied across every screen instead of being rebuilt from scratch in every chat Check the full article about cowork and skills below

Penguin

10,349 просмотров • 3 месяцев назад

Anthropic released Claude Design TODAY and it's now accessible at I spent the last hour giving it a first look, and shared my thoughts and results in the video below. This is a BIG drop. This is a new design surface from Anthropic, and it changes what "AI design" means. Short version: Claude can now design. Not "describe a design." Not "generate an image of a design." Actual production work — prototypes, wireframes, high-fidelity mocks, slide decks, landing pages — editable, on-brand, and ready to hand off. Here's what stood out on first look: → Real design surfaces Prototypes, wireframes, hi-fi, and slide decks — each with templates and proper structure, not just pretty screenshots. → Comment-based edits Leave a comment on any element and Claude revises it. This is the Figma-style review loop, with the designer replaced by a model that works at 3am. → Brand design systems You can feed it your system — colors, type, components — and it actually respects it. On-brand output, not generic AI slop. → Export anywhere PDF, PowerPoint, Canva, standalone HTML. Plus a built-in handoff straight to Claude Code for engineers to implement. → Import from real tools Figma, GitHub, and captured web elements come in as inputs. Your existing work is the starting line, not the discard pile. → Collaboration Share links for view / comment / edit — the exact tier system teams already expect. What I tested on Opus 4.7: • A 5-slide deck generated from a single screenshot. Claude asked clarifying questions BEFORE generating and shipped speaker notes by default. • A landing page build. Solid first pass, real components, real layout logic. • Multiple chats running concurrently. You can parallelize design work across threads like a small team. Why this matters: PMs, founders, marketers, and non-engineers can now create designs that engineers can actually ship with production-ready output and a claude code handoff built in. The gap between "I have an idea" and "here's a working prototype with my brand applied" just collapsed to minutes. Full walkthrough, live demos, exports, and honest takes on where it breaks below. P.S. • This is an Anthropic Labs product — NOT GA yet. • Claude Design is currently webapp only (no API), and does not yet support the Analytics API, Compliance API, or cost/usage reporting. • Availability: – Default ON for Pro / Max / Team – Default OFF for Enterprise Enterprise admins can toggle it on via RBAC in console (comes with a ~$20/user initial credit).

JJ Englert

32,445 просмотров • 5 месяцев назад

DOWNLOAD MASTERCARD DESIGN MD AND BUILD CLEAR WITH CLAUDE CODE people onboard Claude with text designers actually getting results onboard it with a file most never think to write step everyone skips: A design md - plain text rulebook for colors, fonts, spacing, component patterns, tone You don’t write it from scratch - pull a public one from an open design system repo, or literally download a real brand’s guidelines and tell Claude “design like this” Upload it once to a Claude Design system, pick the strongest model, set effort to Max, wait 10-20 minutes for real mockups to review Every project after that pulls your actual brand automatically - zero re explaining your look every single prompt mistake that burns the most hours: designing and coding in the same conversation Claude Design is for visual exploration Claude Code is for production “Mixing them is where beginners lose entire afternoons re litigating decisions that were already made” real workflow, start to finish: design system once - structured brief - first draft - refine with chat, inline comments, sliders - export handoff bundle - Claude Code converts it to a real Next.js app - push, deploy, done 10 dashboards in 10 minutes isn’t the headline Never re explaining your brand again is full below

YARD

31,614 просмотров • 1 месяц назад

🎨 Introducing Genspark Design The next-gen AI for design and creation, powered by Claude Opus 4.7. From rough idea to professional design, no design background needed. - One tool for everything you design. UI prototypes, videos, HTML animations, posters — all in one place and production-ready. - Stay on-brand with your own design system. Upload your Figma files or save your designs, reuse them across every project, and share them with your team. - Ship it, don't just mock it. Turn any app or website design into working code with one click, built on Genspark Code. Start building at our launch price 👉

Genspark

179,614 просмотров • 3 месяцев назад

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.

Mnimiy

114,141 просмотров • 3 месяцев назад

I see a lot of negative feedback about Apple’s new UI updates. But you are missing the point. It’s not about glass effects or making every UI element transparent / shiny. It’s about liquidity, depth, and movement. UI that feels alive. We are entering a new era of interface design. What was once static, flat, and fixed is becoming dynamic, adaptive, dimensional. Flat design is over. And flat screens will be too. Sooner than you think. I think Apple’s new UI system is less about a visual update. It’s the first real step toward multimodal interfaces. Where components aren’t bound to a rigid screen but float, shift, and respond. They appear where you need them, and disappear where you don’t. It’s about removing unnecessary clutter and making human-computer interaction feel… well, more human. Just because we’ve spent the last decade staring at opaque UI components doesn’t mean it’s the optimal way to interact with computers. Sure, it’s not perfect, but it’s the first real step into a new era of UI. The future is screenless. And dynamic components are the new screens.

I see a lot of negative feedback about Apple’s new UI updates. But you are missing the point. It’s not about glass effects or making every UI element transparent / shiny. It’s about liquidity, depth, and movement. UI that feels alive. We are entering a new era of interface design. What was once static, flat, and fixed is becoming dynamic, adaptive, dimensional. Flat design is over. And flat screens will be too. Sooner than you think. I think Apple’s new UI system is less about a visual update. It’s the first real step toward multimodal interfaces. Where components aren’t bound to a rigid screen but float, shift, and respond. They appear where you need them, and disappear where you don’t. It’s about removing unnecessary clutter and making human-computer interaction feel… well, more human. Just because we’ve spent the last decade staring at opaque UI components doesn’t mean it’s the optimal way to interact with computers. Sure, it’s not perfect, but it’s the first real step into a new era of UI. The future is screenless. And dynamic components are the new screens.

Felix Haas

653,995 просмотров • 1 год назад

AI instead of UI The last few years radically changed how we think about digital products & product design process in general. What we are witnessing right now is a transition where AI is no longer just a feature; it is becoming the infrastructure of interaction. For decades, UI design was rooted in the concept of “Happy Path,” a series of static, linear screens (routes from A to B) designed to funnel users toward a goal. This “one-size-fits-all” approach assumes that all users have the same mental model, which is far from the truth. The rise of AI tools like ChatGPT and Gemini is showing that we are moving into an era of Generative Interfaces. Instead of a designer pre-determining every button and menu, the interface is synthesized in real-time based on user actions. Back in 2019, Gleb Kuznetsov and I were working on the concept of morphing Interface, the idea of a UI that adapts its structure based on user intent. The great thing about this UI is that it was highly dynamic: different users saw different content/contextual actions based on their behavior. This concept was crazy in 2019, but it is highly relevant to the modern state of the product design process. And I strongly believe that it represents the future of UI design. We will move beyond the “AI chatbox" crutch Yes, many products today treat AI as a sidecar (think of Copilots or chatbots pinned to the side of a traditional dashboard), but this is a transitional phase. Why? Because adding a chat window to a 20-year-old software layout is like putting a jet engine on a horse-drawn carriage. That's why the future isn't "AI as an add-on"; it is AI as the Operating System. AI will power generative interfaces that are rooted in anticipatory design: UI won’t wait for a command; it will surface tools based on the user's current environmental context and historical behavior. This evolution changes the very nature of product design, and we will move away from designing pages/screens and toward designing systems of logic.

AI instead of UI The last few years radically changed how we think about digital products & product design process in general. What we are witnessing right now is a transition where AI is no longer just a feature; it is becoming the infrastructure of interaction. For decades, UI design was rooted in the concept of “Happy Path,” a series of static, linear screens (routes from A to B) designed to funnel users toward a goal. This “one-size-fits-all” approach assumes that all users have the same mental model, which is far from the truth. The rise of AI tools like ChatGPT and Gemini is showing that we are moving into an era of Generative Interfaces. Instead of a designer pre-determining every button and menu, the interface is synthesized in real-time based on user actions. Back in 2019, Gleb Kuznetsov and I were working on the concept of morphing Interface, the idea of a UI that adapts its structure based on user intent. The great thing about this UI is that it was highly dynamic: different users saw different content/contextual actions based on their behavior. This concept was crazy in 2019, but it is highly relevant to the modern state of the product design process. And I strongly believe that it represents the future of UI design. We will move beyond the “AI chatbox" crutch Yes, many products today treat AI as a sidecar (think of Copilots or chatbots pinned to the side of a traditional dashboard), but this is a transitional phase. Why? Because adding a chat window to a 20-year-old software layout is like putting a jet engine on a horse-drawn carriage. That's why the future isn't "AI as an add-on"; it is AI as the Operating System. AI will power generative interfaces that are rooted in anticipatory design: UI won’t wait for a command; it will surface tools based on the user's current environmental context and historical behavior. This evolution changes the very nature of product design, and we will move away from designing pages/screens and toward designing systems of logic.

Nick Babich

54,034 просмотров • 8 месяцев назад

Spent the day testing Claude Opus 4.7. Last month I built a design director agent for OpenClaw and now it cooks. 15 minutes in, Paper Design MCP + Claude Code had made me a rough draft. In under an hour, a Framer worthy site. My workflow: 1. Feed my agent references so it can extract design systems and lock in on my taste 2. Claude Code calls Paper Design MCP to generate the visual system (just keep the Paper app open) 3. Paper exports the assets and Claude Code then preps the build docs 4. Agent loops back, critiques, iterates Got no clue why anyone is paying $10K for a website anymore. It’s easy now.

Spent the day testing Claude Opus 4.7. Last month I built a design director agent for OpenClaw and now it cooks. 15 minutes in, Paper Design MCP + Claude Code had made me a rough draft. In under an hour, a Framer worthy site. My workflow: 1. Feed my agent references so it can extract design systems and lock in on my taste 2. Claude Code calls Paper Design MCP to generate the visual system (just keep the Paper app open) 3. Paper exports the assets and Claude Code then preps the build docs 4. Agent loops back, critiques, iterates Got no clue why anyone is paying $10K for a website anymore. It’s easy now.

klöss

14,629 просмотров • 5 месяцев назад

Been quietly building Aaru's new design system and porting it into code over the past week. Components built on Base UI, one at a time, all living in our own custom "storybook". Started with the Figma tokens, ended up fine-tuning everything in code, as colours and type just render differently in the browser. Now testing patterns and moving into layouts. Honestly the biggest unlock for design handover I've had in years. Next up: documenting each component's usage for agent use. Recommendations welcome.

Been quietly building Aaru's new design system and porting it into code over the past week. Components built on Base UI, one at a time, all living in our own custom "storybook". Started with the Figma tokens, ended up fine-tuning everything in code, as colours and type just render differently in the browser. Now testing patterns and moving into layouts. Honestly the biggest unlock for design handover I've had in years. Next up: documenting each component's usage for agent use. Recommendations welcome.

Muharrem Şenyıl

45,491 просмотров • 2 месяцев назад

Finally, we have published Horizon OS UI Set for ISDK-Unity and Figma with the Interaction SDK v69 release on 10/9! This is our first public release of official UI components and design resources based on the Quest Design System. UI Set for Meta XR Interaction SDK: Figma Design file: By using UI Set, you can achieve consistent input modality support, visual feedback, and interaction behaviors. In addition to UI components and common UI pattern examples, theming capability can help you bring your own brand identity into your UI. We hope these UI Set Unity components + Figma design assets + Guideline docs - can help you designers, developers, and creators design, experiment, and build great spatial app experiences for Horizon OS platform. Including a personal blog post - How to build a simple spatial panel app with Meta Horizon OS UI Set, an image viewer with NASA Mars Rover API: #MetaQuest #MixedReality #MetaHorizonOS #InteractionSDK #MetaXRSDK #SpatialComputing

Yoon Park (박동윤)

59,277 просмотров • 2 лет назад

This Chinese developer launched 6 agents under 1 orchestrator, and they run his UI design agency at $32,000 a month on their own. He built a system of 6 agents on Claude Sonnet 4.6 that single-handedly runs his agency for UI auditing and redesign for SaaS startups and e-commerce. No contractors, no project manager, and no team. Just him, a MacBook, and 1 API key. Traditional design agencies out of Shenzhen keep teams of 8 people on salaries for the same volume, while he keeps only API tokens. 6 agents work through a single orchestrator on Claude Code Router. Usage is about 4 million tokens a day, the average API bill is just $480 a month. All 6 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions. And here is the system prompt he gave the orchestrator before launch: "you are the orchestrator of a one-man UI agency. you delegate read-only research tasks to 5 sub-agents and own all writes. sub-agents: // Hunter (finds SaaS and e-commerce sites with outdated UI) // Auditor (runs each site through Lighthouse, accessibility, and design system checks) // Pitcher (writes cold outreach and redesign proposals with before/after screenshots) // Splitter (breaks accepted projects into typed milestones) // Designer (generates Figma mockups and Tailwind components) // Checker (runs evals on every artifact before it leaves the harness). you never let 2 sub-agents touch 1 file. you stop and request human approval only when an invoice exceeds $5,000 or when the design system eval score drops below 0.88." Meaning the system knows exactly what it is and within what boundaries it operates. It knows it is supposed to find clients on its own. It knows it is supposed to write proposals with screenshots and mockups without intervention. It knows the human only plugs in when the amounts go above $5,000 or when the design system eval does not converge. → The system runs 24 hours a day → Hunter finds about 200 sites with outdated UI a day → Auditor runs each one through Lighthouse and WCAG → Pitcher prepares about 28 personalized proposals with before/after screenshots → Splitter breaks 3 accepted projects per week into milestones → Designer generates mockups and components, Checker runs evals on every artifact And only when the invoice breaks $5,000 or the eval drops below 0.88 does the orchestrator wake the human. Here is what the system outputs in his log during 1 of the sessions: "hunter report, tuesday: 213 sites found, 31 with last redesign before 2020, 14 with Lighthouse score below 65, 6 with active redesign RFP. passing top 6 to auditor." "pitcher: 27 cold outreach sent with before/after screenshots, 5 replies, 3 discovery calls scheduled. passing to splitter." "designer: milestone 2 of Lotus Tea Co redesign complete. Figma frames exported to /Users/dev/agency/clients/lotus/v2. checker running design system evals." "eval flag: proposal for $6,800 exceeds the approved limit of $5,000. sending for manual review." He has no remote server. No separate backend. Just a local file sandbox in /Users/dev/agency, an MCP router, and an API key to Claude. Out of everything I have seen this year, this is the cleanest one-person UI design agency: $480 in, about $32,000 out, and between them 6 prompts and 1 file system.

This Chinese developer launched 6 agents under 1 orchestrator, and they run his UI design agency at $32,000 a month on their own. He built a system of 6 agents on Claude Sonnet 4.6 that single-handedly runs his agency for UI auditing and redesign for SaaS startups and e-commerce. No contractors, no project manager, and no team. Just him, a MacBook, and 1 API key. Traditional design agencies out of Shenzhen keep teams of 8 people on salaries for the same volume, while he keeps only API tokens. 6 agents work through a single orchestrator on Claude Code Router. Usage is about 4 million tokens a day, the average API bill is just $480 a month. All 6 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions. And here is the system prompt he gave the orchestrator before launch: "you are the orchestrator of a one-man UI agency. you delegate read-only research tasks to 5 sub-agents and own all writes. sub-agents: // Hunter (finds SaaS and e-commerce sites with outdated UI) // Auditor (runs each site through Lighthouse, accessibility, and design system checks) // Pitcher (writes cold outreach and redesign proposals with before/after screenshots) // Splitter (breaks accepted projects into typed milestones) // Designer (generates Figma mockups and Tailwind components) // Checker (runs evals on every artifact before it leaves the harness). you never let 2 sub-agents touch 1 file. you stop and request human approval only when an invoice exceeds $5,000 or when the design system eval score drops below 0.88." Meaning the system knows exactly what it is and within what boundaries it operates. It knows it is supposed to find clients on its own. It knows it is supposed to write proposals with screenshots and mockups without intervention. It knows the human only plugs in when the amounts go above $5,000 or when the design system eval does not converge. → The system runs 24 hours a day → Hunter finds about 200 sites with outdated UI a day → Auditor runs each one through Lighthouse and WCAG → Pitcher prepares about 28 personalized proposals with before/after screenshots → Splitter breaks 3 accepted projects per week into milestones → Designer generates mockups and components, Checker runs evals on every artifact And only when the invoice breaks $5,000 or the eval drops below 0.88 does the orchestrator wake the human. Here is what the system outputs in his log during 1 of the sessions: "hunter report, tuesday: 213 sites found, 31 with last redesign before 2020, 14 with Lighthouse score below 65, 6 with active redesign RFP. passing top 6 to auditor." "pitcher: 27 cold outreach sent with before/after screenshots, 5 replies, 3 discovery calls scheduled. passing to splitter." "designer: milestone 2 of Lotus Tea Co redesign complete. Figma frames exported to /Users/dev/agency/clients/lotus/v2. checker running design system evals." "eval flag: proposal for $6,800 exceeds the approved limit of $5,000. sending for manual review." He has no remote server. No separate backend. Just a local file sandbox in /Users/dev/agency, an MCP router, and an API key to Claude. Out of everything I have seen this year, this is the cleanest one-person UI design agency: $480 in, about $32,000 out, and between them 6 prompts and 1 file system.

Blaze

56,062 просмотров • 5 месяцев назад