GoogleVishal Motwani, Google A2UI TeamAnnouncement
A2UI 1.0: Build delightful, fast, reliable, agentic experiences
Summary
A2UI 1.0 is the first stable release of an open protocol for generative UI, enabling AI agents to respond with interactive screens instead of text. The protocol includes bidirectional function calls, accessibility support, and extensions for metadata. Developers can use open-source renderer SDKs for web, Android, and iOS, along with agent SDKs for Python, TypeScript, and Dart. Companies such as Atlassian, Alation, Bloomberg, and ByteDance are already building with A2UI. The protocol supports fast, reliable UI generation through A2UI Express and system-one decision models, with server-side data binding to keep sensitive values secure.
Context
User interactions with AI agents today are text-heavy, making tasks like comparing products or editing plans cumbersome. A2UI 1.0 addresses this by enabling agents to answer with native, interactive UI components that adapt to each user’s needs and brand design systems. Companies such as Atlassian, Alation, Bloomberg, and ByteDance are already building with it.
Approach / What changed
A2UI 1.0 is an open protocol for generative UI that lets AI agents respond with interactive screens instead of text. Developers use open-source renderer SDKs for web, Android, and iOS, and agent SDKs for Python, TypeScript, and Dart. The protocol supports bidirectional function calls, accessibility, and extensions. It includes A2UI Express for LLM-based composition and system-one decision models for efficient component selection. Data binding and component expansion happen server-side so sensitive values never reach the model.
Takeaways
A2UI 1.0 is an open protocol that lets AI agents respond with interactive, native UI components instead of text, supporting web, Android, and iOS via renderer SDKs.
The protocol uses A2UI Express for LLM-based composition or system-one decision models for efficient component selection, with server-side data binding to keep sensitive values secure.
A2UI integrates with MCP Apps, allowing A2UI screens to appear in AI assistants like Claude and Gemini, and supports bidirectional function calls for real-time interactions.
FAQ
What is A2UI 1.0?
A2UI is an open protocol for generative UI that lets AI agents respond with interactive screens, such as forms or charts, instead of walls of text. It provides renderer SDKs for web, Android, and iOS, and agent SDKs for Python, TypeScript, and Dart.
How does A2UI ensure fast and secure UI generation?
A2UI uses A2UI Express for LLM-based composition or system-one decision models that pick components instead of writing text. Data binding and component expansion happen server-side, so sensitive values never reach the model, and the UI streams in as the agent works.
How does A2UI integrate with MCP Apps?
A2UI and MCP Apps work together. Alation uses both to show A2UI feeds in Claude. The A2UI in MCP Apps guide explains how to run A2UI screens inside an MCP App, and the web and Flutter renderers support this integration.
Source and freshness
- Source
- developers.googleblog.com
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.