Production-Ready AI Agents: 5 Lessons from Restructuring a Monolith

17. May 2026
Google Gemini

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.

Share on:

Developer Guide: Building ADK Agents with Skills

17. May 2026
Google Gemini

ADK’s SkillToolset enables AI agents to dynamically load domain-specific knowledge at runtime; progressive disclosure saves tokens and integrates context information strategically. A developer guide presents four practical application patterns.

Share on:

Gemini Embedding 2: Multimodal AI with Unified Embedding Space

17. May 2026
Google Gemini

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.

Share on:

Google Accounts: Change Username Without Data Loss

17. May 2026
Google Gemini

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.

Share on:

LLM Inference on Google TPUs Accelerated Threefold

17. May 2026
Google Gemini

Google develops new method for LLM acceleration on TPUs using a diffusion-inspired approach — threefold speedup through parallel token prediction instead of sequential bottleneck.

Share on:

Google Pay API Receives New Features for Merchant-Initiated Transactions

17. May 2026
Google Gemini

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.

Share on:

Genkit Middleware: Agentic Apps with Interceptors, Extensions, and Security

17. May 2026
Google Gemini

Google extends its Genkit AI framework with a middleware system that enables developers to make agent-driven applications production-ready through interceptors, advanced error handling, and observability, with TypeScript, Go, and Dart support available.

Share on:

Subagents are now available in Gemini CLI

17. May 2026
Google Gemini

Google introduces subagents for Gemini CLI: specialized AI agents that handle complex tasks in parallel and make the main session more efficient.

Share on:

Gemini 3.1 Flash Live: Google’s Speech Model for Real-Time Conversations

17. May 2026
Google AI Studio, Google Gemini

Google’s new speech model Gemini 3.1 Flash Live improves accuracy and response speed for more natural real-time voice conversations.

Share on:

Reinventing the Mouse Pointer for the AI Age

17. May 2026
Google AI Studio, Google Gemini

Google is developing an AI-powered mouse pointer designed to understand what the user intuitively wants, replacing complex commands with simple pointing and speaking through four interaction principles that automatically capture context.

Share on:

Gemma 4: The most intelligent open-source models in their size class

17. May 2026
Google AI Studio, Google Gemini

Google DeepMind introduces Gemma 4 – high-performance open-source models in four sizes (2B to 31B parameters), with the 31B model ranking 3rd globally, outperforming models 20x its size and running efficiently on edge devices to professional GPUs.

Share on:

Gemini Robotics-ER 1.6: Model for Spatial Understanding and Instrument Reading in Robotics

17. May 2026
Google AI Studio, Google Gemini

Gemini Robotics-ER 1.6 enhances spatial understanding and enables robots to read complex instruments for the first time through specialized embodied reasoning training.

Share on:

« Previous
1
…
6
7
8
9
Next »

Production-Ready AI Agents: 5 Lessons from Restructuring a Monolith

Developer Guide: Building ADK Agents with Skills

Gemini Embedding 2: Multimodal AI with Unified Embedding Space

Google Accounts: Change Username Without Data Loss

LLM Inference on Google TPUs Accelerated Threefold

Google Pay API Receives New Features for Merchant-Initiated Transactions

Genkit Middleware: Agentic Apps with Interceptors, Extensions, and Security

Subagents are now available in Gemini CLI

Gemini 3.1 Flash Live: Google’s Speech Model for Real-Time Conversations

Reinventing the Mouse Pointer for the AI Age

Gemma 4: The most intelligent open-source models in their size class

Gemini Robotics-ER 1.6: Model for Spatial Understanding and Instrument Reading in Robotics

Lumi AI News

Legal

Topics