Google has open-sourced A2UI – a UI language for AI agents

It allows agents generate user interfaces instead of only text.

→ Agents send a JSON description of UI components, and the client app renders them with its own trusted widgets.

The benefits:
- declarative UI format (JSON, not code)
- safe: only approved components can be rendered
- framework-agnostic (web, Flutter, etc.)
- supports incremental UI updates

So agents can "speak UI," while the application keeps control over security and implementation
https://github.com/google/A2UI