---
format: "aidr-story-markdown/v1"
id: "a36bebc20a9c3fe7f66d6fa06083f3c8f1e7eb92046ab785feaace22d76648bf"
canonical_url: "https://aidr.today/a36bebc2?lang=en"
title: "Fast, reliable A2UI, with swappable inference formats"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-27T15:21:02.000Z"
category: "Frameworks"
topics: ["google","inference","framework"]
source_urls: ["https://developers.googleblog.com/fast-reliable-a2ui/"]
summary: "A2UI now supports swappable inference formats, including A2UI Express which uses up to 3x fewer tokens and reduces latency by compiling compact Python-style syntax into standard A2UI JSON via Agent SDKs. Developers can use controlled generation with TypeSafe's Jev system-decision models to render known-shape screens in under 300 ms while smaller models stream text. These updates require no changes to frontend renderers or component catalogs and support Python, TypeScript, and Dart."
---

# Fast, reliable A2UI, with swappable inference formats

> [Open the canonical story](<https://aidr.today/a36bebc2?lang=en>)

**Published:** 2026-10-27T15:21:02.000Z
**Category:** Frameworks
**Topics:** google, inference, framework

## Summary

A2UI now supports swappable inference formats, including A2UI Express which uses up to 3x fewer tokens and reduces latency by compiling compact Python\-style syntax into standard A2UI JSON via Agent SDKs\. Developers can use controlled generation with TypeSafe's Jev system\-decision models to render known\-shape screens in under 300 ms while smaller models stream text\. These updates require no changes to frontend renderers or component catalogs and support Python, TypeScript, and Dart\.

## Sources

- [Story source](<https://developers.googleblog.com/fast-reliable-a2ui/>)