Author Archives:

Build Better AI Agents: 5 Developer Tips from the Agent Bake-Off

The Google Cloud AI Agent Bake-Off highlights a shift from simple prompt engineering to rigorous agentic engineering, emphasizing that production-ready AI requires a modular, multi-agent architecture. The post outlines five key developer tips, including decomposing complex tasks into specialized sub-agents and using deterministic code for execution to prevent probabilistic errors. Furthermore, it advises developers to prioritize multimodality and open-source protocols like MCP to ensure agents are scalable, integrated, and future-proof against rapidly evolving model capabilities.

Get ready for Google I/O: Livestream schedule revealed

Google I/O returns May 19–20 to showcase major updates in AI, Android, Chrome, and Cloud, beginning with a keynote on the "agentic era" of development. The event will focus on new tools designed to automate complex workflows and simplify the creation of high-quality, AI-ready applications. Attendees can register to access live sessions, technical demos, and professional development resources both live and on-demand.

Long Term Support Channel Update for ChromeOS

A new LTC  version 144.0.7559.248 (Platform Version: 16503.80.0), is being rolled out for most ChromeOS devices. 

This version includes selected security fixes including:

[489381399] High CVE-2026-4441: Use after free in Base.

[485935305] High CVE-2026-4440: Out of bounds read and write in WebGL.

[486421954] High CVE-2026-4446: Use after free in WebRTC. 

[490254124] High CVE-2026-4460: Out of bounds read in Skia. 


If you have devices in the LTC channel, they will be updated to this version. The LTS channel remains on LTS-138 until April 21st, 2026. 


Release notes for LTC-144 can be found here 

Want to know more about Long-term Support? Click here


Andy Wu

Google Chrome OS

April 2026 update to Display & Video 360 API

Today we’re announcing the April 2026 update to the Display & Video 360 API. This update includes the following:

While Demand Gen campaign support is in beta, it is only available to allowlisted customers. See our guide for detailed instructions on how to create a Demand Gen ad campaign. If your partner is allowlisted:

  • Demand Gen line items, ad groups, and the relevant targeting will be included in relevant get and list requests.
  • Demand Gen line items, ad groups, ads, and the relevant targeting can be created, deleted, and updated.

We aim to launch full Demand Gen support for the Display & Video 360 API in general availability later this year. This will be announced with a future release.

For a complete list of new features in this update, see the Display & Video 360 API release notes. Before using these new features, make sure to update your client library to the latest version.

If you have any questions or want to discuss this post, please reach out to us on our “Google Advertising and Measurement Community” Discord server.

- Trevor Mulchay, Display & Video 360 API Team

Gemini in Google Classroom is now available in all Classroom-supported languages

Last year, we launched Gemini in Google Classroom in English to support educators with planning and creating engaging lessons, and to help students in higher education to study and learn. Starting this week, we’re beginning to expand availability to all Classroom-supported languages in which Gemini is also available. This expansion makes Gemini tools in Classroom increasingly accessible to educators and higher education students whose preferred language is now supported.

In the Gemini tab in Classroom, educators can get help creating and adapting resources, based on learning objectives, starting with the following features:

  • Outline a lesson plan
  • Generate a quiz
  • Write an informational text
  • Tackle common misconceptions
  • Translate text
More content generation features will become available in these languages in the coming weeks.

Educators can also collaborate with Gemini using starter prompts for the Gemini app that help with common tasks like:

  • Brainstorming real world examples
  • Gamifying an activity
  • Generating differentiation strategies
  • Drafting an exemplar and non-exemplar
  • Creating Depth of Knowledge (DOK) questions

Higher education students using the Gemini tab can:

  • Learn about a topic: Get personalized and step-by-step explanations with Guided Learning.
  • Take a quiz: Prepare for upcoming exams by testing your knowledge and getting hints and feedback.
  • Make flashcards: Turn class materials into custom flashcards for extra practice.
  • Create a study guide: Make a study guide about a certain topic, or upload class materials for more personalized resources.

Getting started

Rollout pace

Availability

  • Education: Education Fundamentals, Standard, and Plus

Resources