Google Developers Blog

feeds.feedburner.comadded August 2026

Build zero-trust AI agents with Google's Agent Development Kit

Google Developers Blogby Shubham Saboo; Eric Dong4d ago

Frameworks like Agent Development Kit (ADK) make it incredibly simple to build multi-tool, autonomous workflows with just a few lines of configuration.

52%

HeyGen x Google Cloud: Bringing Avatar IV to TPUs

Google Developers Blog8d ago

HeyGen is an AI video generation platform featuring avatar models. Avatar IV, the diffusion stack behind our talking-head videos, runs on more than 18B parameters and is available via Web and API.

62%

Why Go is an Ideal Language for AI-Assisted Software Engineering

Google Developers Blogby Cameron Balahan; Richard Seroter10d ago

For a while now, software engineering has undergone a profound, fundamental shift: Where we once wrote most lines of code by hand, we now ask AI coding assistants and agents to generate large...

55%

Agent Plugins package your skills, tools, and more

Google Developers Blogby Kevin Hou; Haoyu Wang; Alan Blount15d ago

Agent Plugins 1.0.0 is an open, vendor-neutral specification for packaging Agent Skills and MCP servers into portable plugins.

60%

Model routing with Google Cloud API Gateway

Google Developers Blogby Mak Ahmad; Sanjay Pujare17d ago

When building AI applications, developers need the freedom to route traffic to the best model for the job without hardcoding endpoints or managing open-source proxies.

52%

Agent and Model Evaluations in Gemini Enterprise Agent Platform are now GA

Google Developers Blogby Alex Martin; Dima Melnyk21d ago

Agent quality must be measured during development against the cases you wrote, and after launch against the tasks the agent actually performed.

58%

Run Ray on TPU, Part 2: Ray AI libraries

Google Developers Blogby Ivan Nardini; Spencer Peterson28d ago

TL;DR: Part 2 of 2. Part 1 covered the one hardware idea you need and the two layers underneath (GKE and Ray Core).

59%

Scaling Agentic RL: High-Throughput Agentic Training with Tunix

Google Developers Blogby Haoyu Gao; Lance Wang; Shadi Noghabi; Tianshu Bao; Weiren Yu21 Jul 2026

The focus of LLM alignment has rapidly shifted from static chatbot alignment to dynamic agentic workflows.

56%

Run Ray on TPU, Part 1: The foundations

Google Developers Blogby Ivan Nardini; Spencer Peterson20 Jul 2026

TL;DR: If you already scale Python with Ray on GPUs, your code can now run on TPU (Tensor Processing Unit, Google's AI accelerator chip) with fully supported official APIs you already know.

59%

Building scalable AI agents with modular prompt transpilation

Google Developers Blogby Simerus Mahesh16 Jul 2026

When you’re first building an AI agent, a single, monolithic system prompt is usually fine. You have a few instructions, maybe a tool definition or two, and everything lives in one readable file.

57%

Systems Engineering Playbook: Optimizing Qwen 3.5-397B MoE on Ironwood (TPU7x)

Google Developers Blogby Google14 Jul 2026

Deploying and serving a Mixture-of-Experts (MoE) model like Qwen3.5-397B on specialized hardware accelerators presents significant systems engineering challenges.

55%