Google experts show in their AI Agent Clinic how fragile AI agents are made production-ready — from cost control through error handling to scaling for real-world requirements.
ADK Go 1.0 enables secure, traceable multi-agent systems in Go through OpenTelemetry integration, plugin architecture, and human-in-the-loop approvals.
Starting March 2024, Google is allowing individual users to change their account username. The old email remains as an alternative and uses the same inbox. App developers should check whether their systems support this change.
Google’s new Gemini Embedding 2 unifies text, images, video, audio and documents in a single embedding model, supporting over 100 languages and processing multiple media types simultaneously to enable new multimodal AI applications and intelligent search systems.
Google Developers presents five essential lessons for developing production-ready AI agents, focusing on restructuring a fragile sales research agent called Titanium to avoid typical production issues such as cost control, hallucinations, and silent failures.
Google enhances the Google Pay API with new features for merchant-initiated payments, enabling better control over subscriptions, deferred payments and auto-reloads, plus increased transparency for users.
Google now allows personal users to change their Gmail usernames without losing data or access, with the old email address retained as a linked address, and developers should review their integrations.
Google launches Gemini Embedding 2, the first multimodal embedding model that connects text, images, videos, audio and documents in a unified space, supporting over 100 languages and enabling agent-based RAG applications and visual search.
Google releases A2UI v0.9: A framework-agnostic standard for generative UI that enables AI agents to create custom interfaces in real time. The new version significantly simplifies development and integration of existing component libraries.
Google Pay API receives new features for merchant-initiated transactions, with updates enabling explicit specification of payment conditions for subscriptions and deferred payments while providing users greater transparency.
Google releases Gemma 4, an open-source model for local AI applications that supports autonomous agents, multi-step planning, and audio-visual processing in over 140 languages without requiring specialized fine-tuning.
