AI · Article
Meta Open-Sources Astrix, a Design System Built for AI Agents Used in 13,000 Apps
인공지능신문 ·
At a glance
Meta has open-sourced Astrix, a design system it has built internally over about eight years. It is designed so that AI, when creating screens, uses set design components and rules. It is currently in beta and available under the MIT license, so anyone can use and modify it.
Key points
- A design system is a collection of screen components such as buttons, input fields, and menus. Astrix provides more than 150 components, screen templates, dark mode, and accessibility features.
- Command-line tools and MCP (a standard way for AI to connect to external tools) were linked so AI agents can look up how to use components and build screens using set templates.
- The goal is to reduce problems where AI uses non-existent component properties or where designs are inconsistent from screen to screen.
- However, the quality of AI-made screens is not automatically guaranteed, so human review and testing are still needed.
Why it matters
Even if AI writes code quickly, it adds to repair costs if it does not know a company's design rules. This release shows a direction in which people and AI share the same development standards.
Original source
[AI 리뷰] 메타, AI 에이전트가 직접 활용하는 디자인 시스템 ‘아스트릭스’ 오픈소스 공개…1만 3,000개 앱에 적용한 기술 개방
인공지능신문 · Nov 9, 12:39 KST
Read on 인공지능신문 ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to 인공지능신문.
More from this field
- OpenAI Opens ChatGPT Space to Plus Users for Pages, Slides, and Team Sharing
OpenAI opened ChatGPT Space to Plus users on the 20th, local time. Space works as a new home for pages, slides, images, files, and uploads. Users can write pages with ChatGPT, add interactive charts, turn ideas into slides, and invite others to edit together.
AI 매터스 · Nov 21, 11:26 KST - Anthropic Researcher Claims Claude Helped Prove Riemann Hypothesis, Experts Await Review
Wes Roth covers a claim by Anthropic researcher Levent Alpöge that he proved the Riemann Hypothesis with help from the AI model Claude. He looks at the huge Lean formal proof, reactions from mathematicians and AI safety researchers, and what this could mean for AI and math.
Wes Roth · Nov 21, 11:24 KST - Amazon CloudWatch Omni Adds Microsoft Azure Logs, Metrics, and Traces Support
Amazon CloudWatch Omni can now collect Azure resource logs, Azure Monitor platform metrics, virtual network flow logs, and Application Insights traces. Teams running workloads on both AWS and Azure can view all of this telemetry in one place, without separate tools or custom pipelines.
AWS What's New · Nov 21, 10:10 KST - AWS Quick Adds Chat-Built Flows, Updated Web App, and Teamwork Among Agents
AWS Quick added updates that let a team turn one person's work routine into a shared, repeatable process. Flows can now be built and changed entirely in chat, and they can run from the web, desktop, or mobile app. Agents working together can also give more complete answers.
Amazon AWS Machine Learning blog · Nov 21, 10:06 KST