Google Developers Blog

Overview This guide introduces a suite of six protocols—such as MCP and A2A—designed to eliminate custom integration code by standardizing how AI agents access...

MARCH 24, 2026 Vibe‑coding with Gemini makes it easier than ever to build highly interactive games and apps, leveraging the power of MediaPipehttps://ai.google....

'MARCH 31, 2026

When you’re prototyping locally with AI agents like Gemini CLI, Claude Code, or your own agent, their potential is often bottlenecked by your local machine. Wai...

The newly introduced continuous checkpointing feature in Orbax and MaxText is designed to optimize the balance between reliability and performance during model...

This blog post introduces a workflow for extracting high-quality data from complex, unstructured documents by combining LlamaParse with Gemini 3.1 models. It de...

MARCH 25, 2026 Large language models LLMs have fixed knowledge, being trained at a specific point in time. Software engineering practices are fast‑paced and cha...

MARCH 10, 2026 We are continually looking for ways to reduce friction in the developer workflow and consistently hear that developers experience friction when w...

Overview The launch of the Agent Development Kit ADK for Go 1.0 marks a significant shift from experimental AI scripts to production‑ready services. It emphasi...

Continuous Checkpointing in Orbax and MaxText The newly introduced continuous checkpointing feature in Orbax and MaxText is designed to optimize the balance be...

Workflow Overview The provided workflow streamlines motion‑controlled game development by using Gemini Canvas to rapidly prototype mechanics like the MediaPipe...

March 11, 2026 We’re excited to bring plan mode to Gemini CLI. With plan mode, Gemini CLI focuses first on analyzing your request, planning complex changes, un...

'MARCH 10, 2026

New Features - Google Maps grounding – enables agents to incorporate geographic context directly from Google Maps. - Built-in URL fetching – simplifies data re...

MARCH 17, 2026 When you’re prototyping locally with AI agents like Gemini CLI, Claude Code, or your own agent, their potential is often bottlenecked by your loc...

This blog post introduces a workflow for extracting high-quality data from complex, unstructured documents by combining LlamaParse with Gemini 3.1 models. It de...

Large language models LLMs have fixed knowledge, being trained at a specific point in time. Software engineering practices are fast‑paced and change often, with...

MARCH 10, 2026 We are continually looking for ways to reduce friction in the developer workflow and consistently hear that developers experience friction when w...

Whether you’re a seasoned cloud architect or a developer just starting to explore Google Cloud, finding time to build something new can be tough. Between stand‑...

Overview This guide introduces a suite of six protocols—such as MCP and A2A—designed to eliminate custom integration code by standardizing how AI agents access...

Overview Google has released version 1.0.0 of the Agent Development Kit ADK for Java. This update introduces several powerful capabilities aimed at advancing A...

'MARCH 10, 2026

March 11, 2026 We’re excited to bring plan mode to Gemini CLI. With plan mode, Gemini CLI first analyzes your request, plans complex changes, and understands t...

March 17, 2026 When you’re prototyping locally with AI agents like Gemini CLI, Claude Code, or your own agent, their potential is often bottlenecked by your loc...

This blog post introduces a workflow for extracting high-quality data from complex, unstructured documents by combining LlamaParse with Gemini 3.1 models. It de...

Large language models LLMs have fixed knowledge, being trained at a specific point in time. Software engineering practices are fast‑paced and change often, with...

We are continually looking for ways to reduce friction in the developer workflow and consistently hear that developers experience friction when writing long, pa...

Overview Wednesday Build Hour is a weekly, interactive “technical gym session” led by Google Cloud experts to help developers and architects sharpen their clou...

The provided workflow streamlines motion‑controlled game development by using Gemini Canvas to rapidly prototype mechanics like the MediaPipe Pose Landmarker th...

TensorFlow 2.21 has been released! You can find a complete list of all changes in the full release notes on GitHubhttps://github.com/tensorflow/tensorflow/blob/...

March 11, 2026 We’re excited to bring plan mode to Gemini CLI. With plan mode, Gemini CLI focuses first on analyzing your request, planning complex changes, un...

Workflow Overview Prototyping with Gemini Canvas The workflow streamlines motion‑controlled game development by using Gemini Canvas to rapidly prototype mechan...

Overview This blog post introduces a workflow for extracting high-quality data from complex, unstructured documents by combining LlamaParse with Gemini 3.1 mod...

'MARCH 10, 2026

Overview Wednesday Build Hour is a weekly, interactive “technical gym session” led by Google Cloud experts to help developers and architects sharpen their clou...

When you’re prototyping locally with AI agents like Gemini CLI, Claude Code, or your own agent, their potential is often bottlenecked by your local machine. Wai...

Large language models LLMs have fixed knowledge, being trained at a specific point in time. Software engineering practices are fast‑paced and change often, with...

Overview This guide introduces a suite of six protocols—MCP, A2A, UCP, AP2, A2UI, and AG‑UI—designed to eliminate custom integration code by standardizing how...

Finish Changes Google has introduced Finish Changes for Gemini Code Assist in IntelliJ and VS Code. It acts as an AI pair programmer that completes code, imple...

TensorFlow 2.21 has been released! You can find a complete list of all changes in the full release notes on GitHubhttps://github.com/tensorflow/tensorflow/blob/...

Overview This guide introduces a suite of six protocols—such as MCP and A2A—designed to eliminate custom integration code by standardizing how AI agents access...

March 17, 2026 When you’re prototyping locally with AI agents like Gemini CLI, Claude Code, or your own agent, their potential is often bottlenecked by your loc...

Overview This blog post introduces a workflow for extracting high-quality data from complex, unstructured documents by combining LlamaParse with Gemini 3.1 mod...

Large language models LLMs have fixed knowledge, being trained at a specific point in time. Software engineering practices are fast‑paced and change often, with...

We are continually looking for ways to reduce friction in the developer workflow and consistently hear that developers experience friction when writing long, pa...

Whether you’re a seasoned cloud architect or a developer just starting to explore Google Cloud, finding time to build something new can be tough. Between stand‑...

'MARCH 24, 2026

'MARCH 10, 2026