Gemini improves the software development lifecycle (SDLC). Take this Google Skills course to learn how to develop and build a web application, fix errors, write tests, and query data with help from Gemini →

If you're using AlloyDB and want a quick way to build an AI agent with your data, use the remote MPC server! This codelab provides a guide to getting started, enabling it as part of the toolset for an AI agent, and using it as part of an application →

Google Cloud @googlecloud announced its Day 0 support for Kimi K3 with SGLang! They just published the full guide for serving the 2.8T-param MoE with SGLang on GKE, including DSPARK speculative decoding. A model this size is an infrastructure problem before it's a model problem. A4 and A4X VMs gave SGLang the memory bandwidth and interconnect to keep K3 fast under real concurrency. Three ways to deploy: Model Garden, AI Hypercomputer recipes, GKE. Guide in the comments 👇

Antigravity SDK July 27th 2026 weekly update for v0.1.9: • 🎉 Audio Support: Audio can now be passed as part of prompts for analysis. • Model Retry Configuration: Configure retry capabilities with RetryConfig. • Structured Tool Exception Handling: Tool specific errors are now surfaced as ToolExecutionError to enable easier reactions. • Unified Connection Tracing: DebugConfig can now be used to more easily configure logging for the SDK. • Automatic Tool Name Resolution: Custom callable class instances can resolve tool names automatically. • Top-Level Tool Exports: BuiltinTools now exports the full set of built in tool definitions. 🧵

Gemini Managed Agents with a new release today🚀 ✅- Model selector and Gemini 3.6 Flash 🪝- Agent Hooks for pre_tool and post_tool events 📦- Environments API to inspect, list, and delete envs Try it out today and let us know your feedback!

Don’t spend the compute to spin up a whole fleet of AI agents if the initial prompt is malicious. Watch us test Model Armor live to see how catching prompt injections at the application layer saves your infrastructure from doing unnecessary work →

You can now set a Custom URL for AI Studio Apps when you publish them directly in AIStudio 🥳 No more messing with Cloud Run Custom domains settings 🙃 Inspired by a post from @patloeber I used AIStudio to build a custom interactive resume and published it to 🙌 The custom URL's are all under and they are on a first come first served basis. So hurry up if you want to claim your own 🏃🏃🏽‍♀️🏃🏾‍♂️ Details of how I built this and how you can claim the domain in this short video 👇 #GoogleCloud# #AIStudio# #DevRel#

Today, we’re announcing the general availability of extended capabilities in Gemini Enterprise Agent Platform! Take full advantage of our centralized, end-to-end platform to simply and securely scale and manage your agents and workflows →

Building an AI agent is the easy part. Managing deployments, governance, and security is the real challenge. Join this week's livestream to learn how to scale agents in minutes using the Gemini Enterprise Agent Platform.

Building an AI agent is the easy part. Managing deployments, governance, and security is the real challenge. Join this week's livestream to learn how to scale agents in minutes using the Gemini Enterprise Agent Platform. Tune in on July 28 at 12 PM PT→

When users accidentally drop PII into a prompt, don't block the whole request. Watch how to use Sensitive Data Protection to partially redact prompts on the fly, keeping your agents running without leaking data →

To help you create rich, reliable experiences while reducing regeneration time and costs, we’re adding two new models to Gemini Enterprise Agent Platform: #1# - Nano Banana 2 Lite is GA #2# - Gemini Omni Flash is in public preview Learn more →

GamerXSociety built a globally patented gaming coach in under nine months. Read this Google Cloud Community article to learn how GamerXSociety used Antigravity, ADK, and Gemini to create an AI co-pilot that can coach and reward gamers in real time →

Introducing the Open Knowledge Format (OKF), an open specification that formalizes the LLM-wiki pattern into a portable, interoperable format. AI is only as smart as the context we give it. As we build more advanced, agentic AI systems, they need accurate metadata and context to be useful. But in most organizations, that context is locked inside fragmented data catalogs, isolated wikis, scattered code comments, or the minds of senior engineers. Every time a new AI agent is built, teams are forced to solve the exact same context-assembly problem from scratch. To solve this, we've announced OKF, a vendor-neutral, open specification that formalizes the "LLM-wiki pattern" into a portable, interoperable format. It provides a standardized way to represent the enterprise knowledge that modern AI systems rely on. — Just markdown: readable in any editor, renderable on GitHub, indexable by any search tool — Just files: shippable as a tarball, hostable in any git repo, mountable on any filesystem — Just YAML frontmatter: for the small set of structured fields that need to be queryable: type, title, description, resource, tags, and timestamp We’ve also shipped reference implementations to help you hit the ground running, including an enrichment agent for BigQuery, a static HTML visualizer, and live sample bundles on @github → ➕ Knowledge Catalog can now natively ingest OKF! Stop reinventing data models and building bespoke integrations for every new AI tool. Here's more about how OKF works →