Google Developers BlogLabs
Fast, reliable A2UI, with swappable inference formats

A2UI now supports swappable inference formats, introducing A2UI Express which uses up to 3x fewer tokens and cuts latency by compiling compact Python-style syntax into standard A2UI JSON via Agent…
Read at Google Developers Blog ↗More from Google Developers Blog on Accept All

LabsCost per task: Using cheap classifiers to route across Gemini models and thinking levels Google Developers Blog

LabsDevFest is back! Google Developers Blog

LabsBuild Generative UI Apps with A2UI & CopilotKit Agents Google Developers Blog

LabsSmaller apps and faster GPU inference with LiteRT in Google Play services Google Developers Blog

LabsHill-Climbing Agent Quality with Agents CLI Evaluation Google Developers Blog
