Google Engineering Blog & Tech Articles
Global technology leader developing innovative software, cloud services, and AI solutions across mobile, web, and enterprise platforms
430 engineering articles, tutorials, and technical insights from Google's engineering team
Top Technologies
Latest Articles
Filter:
The article discusses how to leverage Gemini to create interactive XR experiences from creative prompts, highlighting its capabilities in generating 3D web graphics and immersive simulations.
Benjamin Hersh, Ruofei Du
4 min read
Has Summary
--
Google I/O 2026 is set to take place on May 19–20, featuring the latest AI breakthroughs and product updates from Google.
The Google I/O team
1 min read
Has Summary
--
The article introduces the Automated Review feature of Conductor, an extension for the Gemini CLI that enhances AI-assisted engineering by providing validation through comprehensive post-implementa...
Sherzat Aitbayev, Mahima Shanware, Jay Kornder
3 min read
Includes Code
Has Summary
--
Google introduces extension settings for Gemini CLI, a structured configuration system that prompts users for required settings (API keys, URLs, project IDs) during extension installation.
Jack Wotherspoon, Christine Betts, Bala Narasimhan
6 min read
Includes Code
Has Summary
--
Google has launched a hosted Data Commons MCP (Model Context Protocol) service on Google Cloud Platform, eliminating the need for local Python environments.
Kara Moscoe
3 min read
Includes Code
Has Summary
--
Google announces the public preview of the Developer Knowledge API and its associated Model Context Protocol (MCP) server, providing a canonical, machine-readable gateway to Google's official devel...
Jess Kuras
3 min read
Includes Code
Has Summary
--
This tutorial demonstrates how to fine-tune FunctionGemma, a small language model for translating natural language into API calls, using Google's Tunix library on TPUs.
Wei Wei
4 min read
Includes Code
Has Summary
--
This article presents a blueprint for building trustable AI systems, demonstrated through a real-world field test at Thunderhill Raceway where Google Developer Experts built a real-time AI racing c...
Matt Thompson, Ajeet Mirwani
5 min read
Has Summary
--
LiteRT has evolved from its TensorFlow Lite foundation into a universal on-device AI inference framework, now offering production-ready GPU acceleration across six platforms and streamlined NPU int...
Lu Wang, Chintan Parikh, Jingjiang Li, Terry Heo
9 min read
Includes Code
Has Summary
--
This article introduces Gemini CLI hooks, a customization mechanism that lets developers control and extend the agentic loop of Gemini CLI without modifying its source code.
This article demonstrates how to fine-tune FunctionGemma, a specialized 270M parameter Gemma 3 model designed for function calling in agentic AI systems.
Juyeong Ji
5 min read
Includes Code
Has Summary
--
The Universal Commerce Protocol (UCP) is an open-source standard developed by Google to facilitate seamless commerce experiences across various platforms.
This article serves as a practical guide for developers working with JAX on Cloud TPUs, focusing on essential tools and techniques for debugging and profiling machine learning workflows.
The article discusses the advancements in agentic AI with Gemini 3, emphasizing its role as a core orchestrator for complex workflows.
The article introduces Conductor, a new extension for Gemini CLI that facilitates context-driven development.
Keith Ballinger, Jay Kornder, Sherzat Aitbayev
5 min read
Includes Code
Has Summary
--
The article introduces the Agent Development Kit (ADK) for TypeScript, an open-source framework that enables developers to build AI agents using a code-first approach.
Toni Klopfenstein
3 min read
Includes Code
Has Summary
--
Gemini 3 Flash is now available in Gemini CLI, designed to enhance high-frequency workflows in terminal-based environments.
Taylor Mullen
5 min read
Includes Code
Has Summary
--
Learn how to build modular and reliable agentic applications using 8 effective multi-agent design patterns with the Agent Development Kit (ADK).
The article introduces A2UI, an open-source project designed for agent-driven interfaces that allows agents to generate contextually relevant user interfaces.
The article discusses the transition in AI development towards stateful, multi-turn workflows with the introduction of the Interactions API and its integration with the Agent Development Kit (ADK).
Mike Smith, Xiang (Sean) Zhou, Alan Blount
6 min read
Includes Code
Has Summary
--
The article discusses the new Session Management feature in Gemini CLI, which allows users to automatically save their sessions and resume work without losing context.
The article discusses the importance of protecting sensitive data during processing in cloud environments, introducing Google Cloud's Confidential Space as a solution.
Alberto Gonzalez, Rene Kolga
10 min read
Includes Code
Has Summary
--
The article discusses the advancements in on-device AI powered by MediaTek's Neural Processing Unit (NPU) and the introduction of the LiteRT NeuroPilot Accelerator.
Lu Wang, Arian Arfaian, Luke Boyer
10 min read
Includes Code
Has Summary
--
The article discusses the evolution of AI agent development, emphasizing the need for efficient context management in multi-agent systems.
Hangfei Lin
13 min read
Includes Code
Has Summary
--
The article announces the Data Commons Gemini CLI extension, which simplifies access to a vast repository of public datasets.
Kara Moscoe, Keyur Shah, Christine Betts
3 min read
Includes Code
Has Summary
--
The article discusses the latest updates to the Gemini API for Gemini 3, highlighting its advanced reasoning, coding capabilities, and multimodal understanding.
The article discusses optimizing performance on Qualcomm's Neural Processing Unit (NPU) using LiteRT, Google's high-performance on-device ML framework.
Google Antigravity is a new agentic development platform designed to enhance software development by allowing users to orchestrate complex tasks through AI-powered agents.
The article introduces Gemini 3, Google's latest AI model, now integrated into Jules, an autonomous coding agent for Google AI subscribers.
The article discusses the advancements in AI agents with the introduction of Gemini 3 Pro Preview, highlighting its capabilities for building sophisticated agents using open-source frameworks.
Philipp Schmid, Vishal Dharmadhikari
5 min read
Has Summary
--
The article discusses the JAX AI Stack, a modular framework for building production AI models on Google Cloud TPUs.
Rakesh Iyer, Srikanth Kilaru
6 min read
Includes Code
Has Summary
--
The article discusses the integration of Gemini 3 Pro into Gemini CLI, highlighting its capabilities to enhance productivity and performance in terminal operations.
Taylor Mullen
8 min read
Includes Code
Has Summary
--
The article introduces Code Wiki, a platform designed to enhance code understanding by providing continuously updated, structured documentation for code repositories.
Fergus Hurley, Pedro Rodriguez, Rafael Marques
3 min read
Has Summary
--
The article announces the launch of the Google Colab extension for Visual Studio Code, merging the capabilities of both platforms for AI/ML developers.
Spencer Shumway, Kevin Eger, Ashley Toney
3 min read
Includes Code
Has Summary
--
The article discusses significant upgrades to the Gemini CLI user experience, focusing on enhancing terminal interactions to be more robust, intuitive, and visually stable.
Jacob Richman, Jack Wotherspoon
3 min read
Includes Code
Has Summary
--
Metrax is a high-performance library designed for efficient and robust model evaluation metrics in JAX, addressing the need for standardized metrics during the migration from TensorFlow.
Yufeng Guo, Jiwon Shin, Jeff Carpenter
5 min read
Includes Code
Has Summary
--
The article announces the addition of Go to the Agent Development Kit (ADK), an open-source toolkit for building AI agents.
Toni Klopfenstein
3 min read
Has Summary
--
The article announces the introduction of User Simulation in the Agent Development Kit (ADK), a feature designed to simplify the testing of conversational agents by allowing developers to define hi...
Dima Melnyk, Sita Lakshmi Sangameswaran
7 min read
Includes Code
Has Summary
--
Agent Garden is a platform designed to facilitate the development and deployment of AI agents, making it accessible to all users, not just those on Google Cloud.
Kanchana Patlolla, Tamás Mágedli
3 min read
Has Summary
--
The article discusses the limitations of traditional request-response models in AI agent development and proposes a real-time bidirectional streaming architecture as a solution.
Hangfei Lin
7 min read
Includes Code
Has Summary
--
The article introduces the Jules extension for Gemini CLI, designed to enhance coding workflows by allowing developers to offload tasks asynchronously.
The article introduces Veo 3. 1 and Veo 3. 1 Fast, which enhance video generation capabilities through the Gemini API.
The article introduces enhancements to Gemini CLI, allowing users to run complex interactive commands directly within the CLI environment.
The article introduces Coral NPU, a full-stack, open-source platform designed to enhance Edge AI capabilities on low-power devices.
Billy Rutledge
8 min read
Has Summary
--
The article announces the Genkit Extension for Gemini CLI, which enhances the development of AI applications by providing deep integration with Genkit's architecture and tools.
The article discusses how to fine-tune the Gemma 3 270M model for on-device applications, enabling developers to create custom AI models without the need for expensive hardware.
Ian Ballantyne, Jason Mayes
5 min read
Includes Code
Has Summary
--
The article discusses building high-performance data pipelines using Grain, a data loading library for JAX, and ArrayRecord, an efficient file format.
Jiyang Kang, Shivaji Dutta, Ihor Indyk, Felix Chern
10 min read
Includes Code
Has Summary
--
The article introduces the Jules API, a new tool designed to enhance automation, integration, and innovation throughout the software development lifecycle.
Jane Fine, Jenny Cong
3 min read
Includes Code
Has Summary
--
The article announces the general availability of Gemini 2. 5 Flash Image, an advanced image generation and editing model from Google.
Jules Tools is a command line interface that allows developers to interact with Google's asynchronous coding agent, Jules, directly from their terminal.