Vertex AI Programming Tutorials & Engineering Articles

How our LLM gateway uses Thompson sampling over lognormal latency posteriors to pick the fastest, most reliable model route per request

On May 23, 2026, fresh off the stage at Google I/O, our Google Developer Experts (GDEs) converged on...

Google has released version 1.0.0 of the Agent Development Kit (ADK) for Java, introducing powerful new features like Google Maps grounding, built-in URL fetching, and a standardized Agent2Agent protocol for cross-framework collaboration. The update enhances agent control through a new "App" and "Plugin" architecture, which allows for global logging, automated context window management via event compaction, and "Human-in-the-Loop" workflows for action confirmations. Additionally, the release provides robust session and memory services using Google Cloud integrations like Firestore and Vertex AI to manage long-term state and large data artifacts.

Wednesday Build Hour is a weekly, interactive "technical gym session" led by Google Cloud experts to help developers and architects sharpen their cloud skills. Moving beyond passive slide decks, the program focuses on hands-on building, covering advanced topics like AI agents, Vertex AI, and developer productivity tools. Each hour-long session is designed to provide tangible results that participants can immediately deploy into their own workflows. It serves as a consistent, dedicated space for builders to stay ahead of the curve and connect with a community of cloud engineers.

While keynotes are available online, Google Cloud Next '26 in Las Vegas offers an irreplaceable in-person experience centered on networking, hands-on problem solving, and the transition to agentic AI. The event features specialized technical tracks covering everything from Gemini multimodal breakthroughs to zero-trust security on Cloud Run, providing developers with the tools to balance individual speed with organizational stability. Beyond formal sessions, the "in-person advantage" lies in over 20 developer meetups and collaborative whiteboard sessions designed to foster serendipitous breakthroughs. Ultimately, the conference serves as a high-energy hub for engineers to move beyond the hype and master the modern building blocks of software architecture together.

The article discusses Spotify's multi-agent architecture designed to enhance advertising workflows by addressing structural issues within their ad business.

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...

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.

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.

The article introduces Veo 3. 1 and Veo 3. 1 Fast, which enhance video generation capabilities through the Gemini API.

The article announces the general availability of Gemini 2. 5 Flash Image, an advanced image generation and editing model from Google.

The article provides an in-depth exploration of the EmbeddingGemma architecture, detailing its origins, embedding generation process, and the comprehensive training methodology.

The article announces that Grounding with Google Maps in Vertex AI is now Generally Available (GA), enabling developers to create generative AI applications that utilize real-world, up-to-date info...

The article announces the release of updated versions of Gemini 2. 5 Flash and Flash-Lite, emphasizing improvements in quality and efficiency.

The article provides a detailed postmortem of three infrastructure bugs that affected the response quality of Claude between August and early September.

The article announces the release of Genkit Go 1. 0, a stable, production-ready open-source AI development framework for the Go ecosystem.

EmbeddingGemma is an innovative open embedding model designed for on-device AI applications, featuring 308 million parameters for efficient performance.

The article introduces Gemini 2. 5 Flash Image, a cutting-edge image generation and editing model that enhances creative control and image quality.

The article introduces Gemma 3 270M, a compact AI model designed for hyper-efficient task-specific fine-tuning.

The article discusses the evolution of the Google Developer Program, highlighting new features that enhance access to AI tools, community engagement, and productivity for developers.

The article discusses the advancements in NVIDIA cuVS, a GPU-accelerated vector search library designed for high-performance indexing and low-latency retrieval.

The article announces the stable release of Gemini 2. 5 Flash-Lite, highlighting it as the fastest and most cost-effective model in the Gemini 2. 5 family.

The article announces the availability of Veo 3 in the Gemini API and Vertex AI, highlighting its capabilities in generating high-quality videos with synchronized audio.

This article provides a comprehensive guide on using the logprobs feature in the Gemini model on Vertex AI, enabling developers to gain insights into the model's decision-making process.

The article announces the general availability of the Gemini Embedding text model, gemini-embedding-001, in the Gemini API and Vertex AI.

The article introduces T5Gemma, a new collection of encoder-decoder models derived from pretrained decoder-only models.

The article introduces Gemma 3n, a mobile-first architecture designed for on-device AI, highlighting its multimodal capabilities and architectural innovations.

The article discusses the advancements in the Gemini 2. 5 models for robotics, highlighting their coding, reasoning, and multimodal capabilities.

The article discusses the essential role developers play in data-driven marketing, emphasizing the need for effective data management and analysis tools.

The article discusses significant updates to Google's intelligent agent ecosystem, focusing on the Agent Development Kit (ADK), the Agent Engine UI, and enhancements to the Agent2Agent (A2A) protoc...

The Google I/O 2025 Developer keynote highlighted innovations across Google platforms, focusing on the integration of AI models from Google DeepMind.

The article discusses how Google AI is transforming game development through advanced models like Gemma 3 and Gemini 2. 5, enabling developers to create immersive, AI-driven gaming experiences.

The article discusses the launch of Gemini 2. 5, highlighting its advancements in video understanding capabilities, particularly with the Gemini 2. 5 Pro and Flash models.

The article introduces the new image generation capabilities of Gemini 2. 0 Flash, now available in preview for developers.

The article introduces Gemini 2. 5 Pro Preview, highlighting its enhanced coding performance and capabilities for developers.

The article announces the general availability of Llama 4 as a Model-as-a-Service (MaaS) on Vertex AI, highlighting its advanced capabilities and ease of use.

The article discusses the capabilities of the Live API, which enables developers to create real-time applications that process audio, video, and text with low latency.

The article introduces Gemini 2. 5 Flash, an early version of a hybrid reasoning model available in preview through the Gemini API.

The article discusses three generative AI-powered MarTech solutions introduced by Google to enhance marketing efforts.

The article announces the general availability of the Apigee Extension Processor, a new capability that enhances Apigee's ability to manage and secure backend services and modern application archit...

The article introduces significant updates to the Gemini API, including the release of Gemini 2. 5 Pro, the upcoming Gemini 2. 5 Flash, and the production readiness of Veo 2 for video generation.

The article introduces the Agent Development Kit (ADK), an open-source framework by Google designed to facilitate the development of multi-agent applications.

The Google Developer Program is evolving to include AI-powered tools and expanded resources aimed at enhancing developers' capabilities.

TxGemma is a collection of open models designed to enhance the efficiency of therapeutic development by utilizing large language models.

Gemma 3 is the latest version of the Gemma open-model family, boasting enhanced capabilities such as multimodality, longer context windows, and improved reasoning.

The article discusses the introduction of the Gemini Embedding text model (gemini-embedding-exp-03-07) available through the Gemini API.

The article discusses the capabilities and advantages of the Gemini 2.

The article discusses the expansion of the Gemini 2. 0 family, introducing new models such as Gemini 2. 0 Flash, Flash-Lite, and Pro, aimed at enhancing developer access and performance.

The article discusses the Vertex AI RAG Engine, a tool designed to help developers build grounded generative AI applications by addressing challenges like hallucinations and outdated knowledge.