Google’s ADK enables AI agents to dynamically load specialized domain expertise and independently generate new expertise areas without overwhelming system prompts.
Gemini CLI now supports specialized subagents that handle complex tasks in parallel, each with its own tools and context window, making the main session faster and more efficient.
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.
Google I/O 2025 takes place May 19–20 with keynotes on May 15, focusing on agent-driven software development, enhanced Android tools, and intelligent web technologies, with live sessions broadcast directly from Mountain View.
Google I/O 2025 takes place on May 15, 19, and 20. The focus areas are agentic AI workflows, improved Android development tools, and intelligent web applications. The complete livestream schedule is now available.
Google Cloud launches Agents CLI – a new tool for AI coding assistants that revolutionizes the development of AI agents, dramatically shortening the path from concept to production and offering a unified interface to Google Cloud Services.
Google introduces TorchTPU, a native integration between PyTorch and TPUs, enabling developers to easily migrate their models to Google’s custom chips with a focus on ease of use, portability, and maximum performance in distributed hyperscale AI systems.
Agents CLI unifies AI agent development, evaluation and deployment on Google Cloud, dramatically reducing time to production and enabling AI coding assistants to seamlessly leverage the entire infrastructure.
Google introduces TorchTPU, a solution enabling native PyTorch on TPUs, allowing developers to migrate their ML workloads to Google’s supercomputing infrastructure with minimal code changes and full utilization of TPU resources.
Google Genkit introduces a new middleware system for extending and securing AI applications, with modular hooks enabling retries, fallbacks, and human oversight—available in TypeScript, Go, and Dart, with Python support coming soon.
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.
