Google

Run Ray on TPU, Part 1: The foundations

Enabling distributed Python workloads to run efficiently on Google Cloud TPUs while respecting the strict networking requirements of multi-host TPU slices that must maintain connectivity over their Inter-Chip Interconnect (ICI).

distributed-systems ml-systems
5 min
Google

Run Ray on TPU, Part 2: Ray AI libraries

Efficiently running distributed AI workloads across Google's TPU slices while managing data loading bottlenecks and cross-slice coordination complexity.

distributed-systems ml-systems
5 min
Google

Scaling Agentic RL: High-Throughput Agentic Training with Tunix

TPU idling bottlenecks during multi-turn, tool-using LLM agent training caused by network I/O and environment step latencies reducing hardware throughput.

ml-systems distributed-systems
5 min
Google

Building scalable AI agents with modular prompt transpilation

Monolithic system prompts created scaling bottlenecks and runtime errors in AI agent systems, preventing reliable deployment and maintenance.

ml-systems api-design
5 min
Google

Evolving Spec-Driven Development: Conductor Now Supports Antigravity

Developers experienced workflow friction when using AI assistants for spec-driven development because they had to follow strict command sequences rather than engaging in natural conversation.

api-design sdks
5 min
Google

Expanding Choice in Gemini Enterprise Agent Platform: Introducing Grounding with Parallel Web Search

Enterprise AI agents lacked access to real-time, verifiable web data sources for grounding their responses, leading to hallucinations and reduced factual accuracy in complex workflows.

caching api-design
5 min
Google

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

How to efficiently serve a 397-billion parameter Mixture-of-Experts model on Ironwood TPU7x hardware while overcoming severe sharding constraints and cross-device communication bottlenecks.

distributed-systems ml-systems
5 min
Google

Bridging the Domain Gap: AI Race Coach built with Antigravity and Gemini

Building an AI-powered real-time coaching application that bridges the gap between domain-specific athletic expertise and generative AI capabilities.

api-design ml-systems
3 min
Google

LiteRT.js, Google's high performance Web AI Inference

Google needed to enable high-performance machine learning model inference directly in web browsers without requiring server-side computation or external dependencies.

api-design sdks
5 min
Google

We terminated a TPU mid-training and it recovered in seconds: Introduction to elastic training with MaxText

Distributed AI training jobs fail completely when a single machine fails, requiring expensive full-workload restarts from scratch.

distributed-systems ml-systems
5 min
Google

Build agentic full-stack apps with Genkit

Developers were struggling with the complex implementation details of building conversational AI applications, including managing message history, tool invocation loops, and real-time streaming across full-stack architectures.

api-design ml-systems
5 min
Google

Build reliable multi-agent applications with ADK Go 2.0. Discover our new graph-based workflow engine, built-in human-in-the-loop, and dynamic orchestration

Developers needed a unified runtime to compose and orchestrate complex multi-agent applications without managing separate execution models for single-agent versus multi-agent workflows.

microservices distributed-systems
5 min
Google

Driving the Agent Quality Flywheel from Your Coding Agent

Developers building AI coding agents lack confidence that prompt modifications fixing individual errors won't cause widespread regressions in production systems.

ml-systems observability
5 min
Google

ML Development in VS Code with Google Cloud Power: Workbench Extension Now Available

Machine learning engineers were experiencing context-switching friction and performance constraints by developing locally instead of leveraging scalable cloud infrastructure for their ML workflows.

api-design sdks
5 min
Google

Why we built ADK 2.0

The previous version of ADK had limitations in extensibility, performance, and developer experience that prevented it from supporting Google's evolving platform needs and developer requirements.

api-design sdks
4 min
Google

Build Cross-Language Multi-Agent Team with Google’s Agent Development Kit and A2A

Enabling multiple AI agents written in different programming languages to collaborate seamlessly on complex tasks like contract compliance verification.

api-design microservices
3 min
Google

Measuring What Matters with Jules

How to effectively measure and evaluate the performance and quality of AI coding agents as they evolve from reactive task-completion tools to proactive autonomous systems.

observability ml-systems
3 min
Google

A2UI + MCP Apps: Combining the best of declarative and custom agentic UIs

Balancing the tradeoff between highly customizable but isolated iframe environments and native declarative UI rendering when building agent-driven interfaces over Model Context Protocol servers.

api-design security
5 min
Google

Announcing the Agentic Resource Discovery specification

Agents need a standardized way to discover, identify, and verify available tools and skills across distributed systems without centralized coordination.

api-design distributed-systems
3 min
Google

Enhance Security and Trust: New Session Metadata in Sign in with Google

Developers needed deeper session metadata to verify login freshness and authentication methods for implementing risk-based access controls and preventing account takeover attacks.

api-design security
5 min
Google

How A2A is Building a World of Collaborative Agents

AI agents need a secure, flexible way to collaborate and hand off tasks without the constraints and context pollution of traditional API-based communication.

api-design distributed-systems
5 min
Google

Unlocking the Power of the TPU Stack: Introducing our new Developer Hub

Developers lack centralized, practical resources to optimize machine learning workloads and fully utilize the performance capabilities of Google Cloud TPUs.

ml-systems distributed-systems
5 min
Google

DiffusionGemma: The Developer Guide

How to achieve significantly faster text generation inference while maintaining quality and enabling bidirectional context awareness, without requiring expensive specialized hardware.

ml-systems api-design
5 min
Google

Bringing Gemma 4 12B to your Laptop: Unlocking Local, Agentic Workflows with Google AI Edge

Enabling efficient execution of large language models (12B parameters) on resource-constrained devices like laptops with limited RAM while maintaining multimodal and agentic capabilities.

ml-systems api-design
5 min
Google

Gemma 4 12B: The Developer Guide

Running high-performance multimodal AI models efficiently on consumer devices without the computational overhead of traditional visual and audio encoders.

ml-systems api-design
4 min
Google

Introducing the Google Colab CLI

Developers and AI agents needed a way to seamlessly execute code on remote GPU-powered Colab runtimes without context-switching between local terminals and web interfaces.

api-design ml-systems
5 min
Google

Enhancing Android Checkout with Dynamic Callbacks in Google Pay

Android developers needed a streamlined way to integrate Express checkout functionality with Google Pay while handling asynchronous payment callbacks efficiently.

api-design mobile-platforms
3 min
Google

How the community trained Gemma to "Think" with Tunix and TPUs

How to enable developers with limited compute budgets to transform small base language models into capable reasoning engines through efficient training techniques.

ml-systems distributed-systems
5 min
Google

Supercharge your integration workflow with the Google Pay & Wallet Developer MCP server

Developers integrating with Google Pay & Wallet APIs experienced friction by having to context-switch between their IDE and external documentation/tools to validate implementations and manage accounts.

api-design sdks
5 min
Google

The latest updates to Google Pay

Enabling AI agents to autonomously manage payment integrations and commerce workflows while reducing checkout friction across multiple platforms and devices.

api-design microservices
5 min
Google

A Smarter Google AI Edge Gallery: MCP integration, notifications, and session continuity

Enable on-device AI models to coordinate complex tasks across external data sources while maintaining persistent user context and proactive engagement without relying solely on cloud connectivity.

api-design ml-systems
5 min
Google

A2UI v0.9: The New Standard for Portable, Framework-Agnostic Generative UI

AI agents needed a standardized way to generate UI components that work across different platforms and frameworks without being tightly coupled to any specific technology stack.

api-design real-time-systems
5 min
Google

Accelerating on-device AI: A look at Arm and Google AI Edge optimization

Enabling efficient execution of generative AI models on edge devices with limited computational resources while maintaining acceptable latency and performance.

ml-systems api-design
5 min
Google

Agents CLI in Agent Platform: create to production in one CLI

Developers face high context overhead and token waste when scaffolding AI agents locally and struggle to bridge the gap between development environments and production-grade deployment on Google Cloud.

api-design microservices
5 min
Google

All the news from the Google I/O 2026 Developer keynote

How to enable developers to build applications powered by autonomous AI agents rather than traditional assistive AI interfaces.

api-design sdks
5 min
Google

An important update: Transitioning Gemini CLI to Antigravity CLI

Google needed to unify fragmented AI terminal tooling by consolidating the community-focused Gemini CLI into a more scalable, agent-first platform capable of handling complex multi-agent workflows.

api-design microservices
5 min
Google

Announcing ADK for Kotlin and ADK for Android 0.1.0: Building AI Agents on Android and Beyond

Developers needed a way to build AI agent workflows that could run on Android devices and backend systems without reinventing the core agentic logic across different platforms.

api-design sdks
3 min
Google

Announcing Genkit Middleware: Intercept, extend, and harden your agentic apps

Developers need a way to reliably control, monitor, and extend AI model generation calls in production agentic applications without modifying core business logic.

api-design ml-systems
5 min
Google

Blazing fast on-device GenAI with LiteRT-LM

Running large language models efficiently on mobile and edge devices while preserving multimodal and agentic capabilities without requiring server-side inference.

ml-systems mobile-platforms
5 min
Google

Build Long-running AI agents that pause, resume, and never lose context with ADK

Building production-grade AI agents that can maintain context and state across long-running enterprise workflows spanning days or weeks without losing information during idle periods or server restarts.

api-design distributed-systems
5 min
Google

Building real-world on-device AI with LiteRT and NPU

Mobile developers faced performance and battery inefficiency when running AI models on CPU/GPU, limiting real-time AI applications on edge devices.

api-design ml-systems
5 min
Google

Building with Gemini Embedding 2: Agentic multimodal RAG and beyond

Developers needed a unified embedding model capable of processing interleaved multimodal inputs (text, images, video, audio, documents) in a single semantic space for tasks like retrieval-augmented generation and visual search.

api-design ml-systems
5 min
Google

Empowering Service Providers and Hardware Partners with Gemini for Home

How can Google enable third-party service providers and hardware manufacturers to build intelligent smart home experiences without requiring deep AI/ML expertise or significant R&D investment?

api-design ml-systems
5 min
Google

Google Tensor SDK Beta with LiteRT

Developers needed a unified way to build, deploy, and run high-performance machine learning models directly on edge devices (Google Pixel TPU) with reliable fallback mechanisms.

ml-systems api-design
5 min
Google

MaxText Expands Post-Training Capabilities: Introducing SFT and RL on Single-Host TPUs

Enabling efficient post-training of large language models on single-host TPU configurations without requiring complex multi-host distributed setups.

ml-systems distributed-systems
5 min
Google

New enhancements for merchant initiated transactions with the Google Pay API

Merchants needed greater flexibility and control when initiating payment transactions for recurring subscriptions, deferred payments, and automatic reloads while maintaining user transparency.

api-design
5 min
Google

One Year of Innovation: Celebrating 100k Members in the Google Cloud x NVIDIA Developer Community

Developers needed accessible infrastructure, resources, and structured learning pathways to effectively build and optimize AI applications using GPUs and large language models at scale.

api-design ml-systems
5 min
Google

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

Converting a brittle, monolithic sales research AI prototype into a production-ready agent that eliminates silent failures, fragile parsing, and lacks observability.

microservices observability
5 min
Google

Speeding Up AI: Bringing Google Colossus to PyTorch via GCSFS and Rapid Bucket

AI training pipelines were bottlenecked by slow data I/O when accessing training datasets stored in Google Cloud, limiting throughput and increasing total training time.

storage-systems ml-systems
5 min
Google

Supercharging LLM inference on Google TPUs: Achieving 3X speedups with diffusion-style speculative decoding

Autoregressive LLM decoding suffers from sequential bottlenecks where tokens must be generated one-at-a-time, limiting throughput and inference speed on hardware accelerators like TPUs.

ml-systems real-time-systems
5 min