All news with #vertex ai tag

🚀 Google announced Gemini 3.1 Pro, an upgraded foundation model in the Gemini 3 series that emphasizes deeper reasoning and complex problem solving. The model is available in preview in Vertex AI and Gemini Enterprise, and developers can access it through Google AI Studio, the Gemini API, Android Studio, Google Antigravity, and the Gemini CLI. Early customers report meaningful gains in speed, efficiency, and accuracy across code, 3D transformations, and product design workflows.

⚙️ Provisioned Throughput on Vertex AI standardizes reserved capacity across first-party, third-party, and open-source models, adding multimodal and operational enhancements to support production-scale AI agents. The update introduces Anthropic integration (private preview), PT for popular open models such as Llama 4, Qwen3, and GLM-4.7, and native support for high-bandwidth modalities including Gemini 3, Nano Banana, and Gemini Live API. Operational improvements — one-week PT terms, scheduled change orders, and explicit caching for long contexts — enable predictable latency, flexible commitments, and lower input costs for peak events and high-concurrency workloads.

🔧 This guide explains how to adapt foundation models on Google Cloud by fine-tuning both managed and self-managed workflows. It contrasts a fully managed Vertex AI Supervised Fine-Tuning path for models like Gemini with a customizable GKE approach using LoRA on open-source models such as Llama. The labs walk through data preparation, baseline evaluation, tuning, and automated evaluation metrics, as well as GKE infrastructure, GPU provisioning, security with Workload Identity, and containerized training for production readiness.

🧰 The Google Cloud samples team describes building a specialized end-to-end system that uses Gemini on Vertex AI and Genkit to produce production-ready educational code samples across many languages and products. Their architecture separates generation, validation, and delivery so LLM outputs are combined with deterministic automations, linters, unit tests, and human review. The post presents seven practical technical takeaways—decomposition, determinism, precise prompts, vetted evaluation, scaled downstream processes, end-to-end testing, and solid engineering practices—that drove reliable, scalable sample generation.

🚀 The Vertex AI team deployed the GKE Inference Gateway, built on the Kubernetes Gateway API, to reduce inference latency and improve cache efficiency without a custom scheduler. The gateway applies load-aware routing—scraping Prometheus metrics like KV cache utilization and queue depth—and content-aware routing that inspects request prefixes to send traffic to pods with warm context. In production this cut Time to First Token by ~35% for Qwen3-Coder, improved P95 by ~52% for a bursty chat model, and doubled prefix-cache hit rates from 35% to 70%.

🚀 Google Cloud has added Anthropic's Claude Opus 4.6 to Vertex AI, extending its curated model catalog for enterprise and agentic workloads. Opus 4.6 is positioned for complex coding, polished document and spreadsheet generation, advanced tool calling, and sophisticated multi-step agents. Feature highlights include GA support for adaptive thinking, an effort parameter, 128k output tokens, and previews for a 1M context window and compaction API. Google emphasizes managed agent tooling, governance, and infrastructure to deploy Claude-powered agents at scale.

🚀 Google Cloud is launching a two-day roadshow across North America focused on building production-grade and multimodal AI systems. Day 1, the Production-Ready AI Intensive, covers stability, security, and scalable architecture including multi-agent orchestration with the Agent Development Kit (ADK), A2A protocols on Cloud Run, automated evaluation via the Vertex AI Gen AI Evaluation SDK, and defenses like Model Armor and Sensitive Data Protection. Day 2, the Multimodal Frontier, is a hands-on, code-first workshop on real-time perception and interaction: simultaneous audio/video processing, Graph RAG with Spanner Graph, Persistent Memory Banks, and the Gemini Live API for zero-latency, interruptible agents. Sessions include labs, credits, and networking; seats are limited.

🔧 This guide explains how to build custom employee onboarding agents using the Agent Development Kit (ADK), Vertex AI Agent Engine, and Application Integration to connect conversational AI with enterprise systems such as ITSM, ERP, and CRM. It describes a grounded agentic workflow where a Gemini Enterprise front-end captures intent, a low-code Application Integration layer performs deterministic transformations and authentication, and backend systems execute transactions. The result is a role-aware, auditable onboarding experience that automates tasks like laptop provisioning while keeping business rules and approvals intact.

🚀 Google.Cloud.VertexAI.Extensions brings Microsoft.Extensions.AI abstractions to .NET developers, enabling access to Google Gemini models on Vertex AI via a unified API. The preview package implements core interfaces — IChatClient, IEmbeddingGenerator, and an experimental IImageGenerator — and supports chat, streaming responses, embeddings, and image generation samples. It targets developers who want provider-agnostic integration and invites feedback while in pre-release.

🚀 Google Cloud has launched a new Bangkok (asia-southeast3) region to deliver low-latency, high-performance cloud services while enabling local data residency under Thailand’s PDPA. The region is part of a USD $1 billion investment and is expected to generate THB 1.4 trillion (US$41 billion) in economic value over five years and support roughly 130,000 jobs annually. It offers certified security controls (ISO/IEC, PCI DSS, SOC), default encryption, customer-managed keys, and direct access to Vertex AI, enterprise Gemini, and generative models to accelerate local AI adoption.

🔐 Tom Curry and Anton Chuvakin from Google Cloud’s Office of the CISO present practical guidance for implementing the Secure AI Framework (SAIF) on Google Cloud. The piece emphasizes three operational principles: treat data as the perimeter, treat prompts like code, and require identity propagation for agentic AI. It maps 15 common AI risks to controls and highlights concrete tools and patterns—IAM, Dataplex, Vertex AI, Model Armor, Gemini, Apigee, and the Agent Development Kit—to operationalize SAIF.

🤖 Palo Alto Networks automated creation of its internal Document of Record (DOR) using an agent built with Google's open-source Agent Development Kit (ADK) and hosted on Vertex AI Agent Engine. The agent leverages Vertex AI RAG Engine, Vertex AI Discovery Search, Gemini models, and Cloud Storage to retrieve and synthesize grounded answers to a standardized set of 140+ questions. A FastAPI webserver on GKE orchestrates parallel processing, manages state, and publishes completed DORs back to Salesforce via Cloud Pub/Sub, reducing manual effort and improving consistency.

🤖 Google Public Sector summarizes a year of AI, cloud, and security milestones, spotlighting Gemini for Government, Vertex AI, and FedRAMP High authorizations for productivity and analytics offerings. The post highlights DoD IL6 and CMMC Level 2 certifications, partnerships with DLA and GDIT, and large-scale deployments such as GenAI.mil. It emphasizes secure, agentic workflows, edge-capable deployments, and a focus on delivering accredited commercial cloud services to accelerate mission impact.

🚀 These hands-on labs guide developers through three Google Cloud deployment options to move AI agents from local prototypes to production. The Vertex AI Agent Engine offers a fully managed, Python-optimized runtime that handles execution, memory, and tool invocation. Cloud Run provides a serverless container experience with autoscaling and language flexibility, while GKE delivers orchestrated control for microservice deployments.

🛡️ Google Cloud has integrated Cloud API Registry into Vertex AI Agent Builder, giving administrators centralized governance over agent tools and a curated catalog developers can access via a new ApiRegistry ADK object. The update broadens ADK support — including Gemini 3 Pro/Flash and TypeScript — and improves state management, interactions, and recovery. An early A2UI toolkit and Interactions API support aim to simplify multimodal I/O and shared UI components. Agent Engine features such as Sessions and Memory Bank are GA, regional availability is expanding, and several pricing adjustments take effect in December 2025 and January 2026.

🚀 CHNA 2.0 combines Wayne State’s PHOENIX data warehouse with Syntasa Sentiment Analytics and Google Vertex AI to automate Community Health Needs Assessments. The solution ingests EHR, social and environmental data alongside real‑time search and social signals to surface community concerns and priorities. By decomposing reporting tasks and embedding human oversight, CHNA 2.0 delivers comprehensive, updateable CHNA reports in weeks rather than months.

🔍 This article outlines a practical, metrics-driven approach to testing generative AI systems, moving teams from ad-hoc inspection to systematic evaluation. It introduces four hands-on labs that cover evaluating single LLM outputs, assessing RAG systems with Vertex AI Evaluation, tracing and grading agent behavior with the Agent Development Kit (ADK), and validating SQL-generating agents against BigQuery. Each lab emphasizes measurable metrics—safety, groundedness, faithfulness, and factual accuracy—to help productionize GenAI with confidence.

🔊 The post announces general availability of Gemini Live API on Vertex AI, powered by the Gemini 2.5 Flash Native Audio model. It presents a unified, low-latency native audio architecture that replaces multi-stage STT/LLM/TTS pipelines and enables real-time multimodal reasoning over audio, text, and visual streams via a stateful WebSocket. Two quickstart templates (Vanilla JS and React) and three production demos illustrate common integration patterns, partner telephony/WebRTC support, and recommended backend proxying for secure credentials.

🔗 This post explains how to expose Looker’s semantic layer to Gemini Enterprise quickly by using the MCP Toolbox for Databases and the Agent Development Kit (ADK). It outlines three concise steps: deploy the MCP Toolbox (recommended to Cloud Run), build and deploy an ADK agent to Vertex AI Agent Engine, and register that agent with Gemini Enterprise. The result: trusted Looker models available inside Gemini for natural‑language business queries.

🔊 Gemini Live API, powered by the Gemini 2.5 Flash Native Audio model, is now generally available on Vertex AI. It enables low-latency, multimodal conversational agents that combine voice, vision, and text to deliver human-like, contextual interactions. The API supports natural turn-taking, acoustic cue analysis, and visual understanding, and is optimized for enterprise-scale, regional deployments and compliance. Early adopters including Shopify, United Wholesale Mortgage, and SightCall report improved efficiency and real-time assistance.