#521 Issue
Sept. 21, 2026
Welcome to issue #520 September 14th, 2026
News
AgentsMCPOfficial BlogIntroducing the Google Cloud Developer Plugin for AI Coding Agents - Discover new Google Cloud plugins for AI coding agents. Package skills and MCP servers into installable bundles to streamline cloud workflows.
AntigravityOfficial BlogPower agent hubs or custom harnesses with the Antigravity SDK in one toolkit - If you are building a centralized agent hub from the ground up, you need tools that run predictably, log everything, and stay in their sandbox. That's why today, we're breaking down how the Antigravity SDK powers a complete multi-agent control plane.
ADKAIKotlinAnnouncing ADK for Kotlin 1.0: Building Production-Ready AI Agents in Kotlin, Android, and Beyond - Google has officially released version 1.0 of the Agent Development Kit (ADK) for Kotlin, achieving full feature parity with the Python and Java ADK cores to enable idiomatic, multi-agent AI development. Built on Kotlin Multiplatform (KMP), the framework leverages Kotlin Symbol Processing (KSP) for zero-reflection, type-safe function calling, alongside advanced orchestration capabilities like human-in-the-loop workflows and context compaction. Additionally, the release introduces a robust suite of Android-first extensions, allowing mobile developers to integrate local models via LiteRT-LM, cloud reasoning through Firebase AI, session persistence using Room, and semantic memory powered by AppSearch.
AgentsData AnalyticsMCPOfficial BlogAgentic analytics with the Data Agent Kit - Data Agent Kit is a set of MCP servers and agent skills that helps data developers run data workflows from their IDEs. It’s available both as an extension for VS Code forks (Antigravity IDE, Cursor) and as a plugin for other tools (Antigravity 2.0, Antigravity CLI, Claude Code, Codex).
Cloud SpannerDatabasesOfficial BlogSpanner: Removing cumulative mutation limits for DML transactions - Spanner removes cumulative mutation limits for DML statements, enabling larger and more flexible transactions without artificial splits.
AlloyDBDatabasesOfficial BlogEnterprise-grade PostgreSQL with AlloyDB Omni RPM Orchestrator is generally available - Enjoy flexible deployment models to help you maximize performance, scale read throughput, or ensure robust high availability in your organization.
Official BlogQuadrantGoogle is a Leader in the 2026 Gartner® Magic Quadrant™ for Enterprise AI Assistants - Gartner has named Google a Leader in its inaugural 2026 Magic Quadrant for Enterprise AI Assistants. Gartner placed Google in the Leaders quadrant for its evaluation across both Completeness of Vision and Ability to Execute.
Articles, Tutorials
Infrastructure, Networking, Security, Kubernetes
Official Blog Threat IntelligenceGTIG AI Threat Tracker: From Prompting to Autonomy – The Evolution of Adversarial AI - This AI threat update provides GTIG’s findings on adversarial misuse of AI including Gemini and other non-Google tools.
GCP Experience Media CDN Networking Official BlogHow Airtel delivered its flawless Indian Premiere League 2026 cricket broadcasts - Media CDN offered deep local edge proximity and excellent cache efficiency; combined with real-time monitoring, Airtel achieved exceptional broadcast reliability.
GPU KubernetesThe Idle Half of a GPU Pod - When running AI inference on high-end Google Cloud GPU nodes, the host CPUs and RAM sit mostly idle because the hardware is heavily over-provisioned to support data loading and tokenization. A recent technical study demonstrates that backfilling these underutilized cores with demanding workloads like CPU benchmarks increases CPU usage significantly while having a negligible impact on inference latency.
Infrastructure Networking Private Service Connect VPCVPC Peering, Private Services Access and Private Service Connect: What Happens at the Boundary - This article explores how Google Cloud’s three private connectivity options—VPC Peering, Private Services Access (PSA), and Private Service Connect (PSC)—behave at network boundaries.
ADK Gemini Enterprise Agent Platform TerraformEnterprise AgentOps: Decoupling Terraform Infrastructure from Google ADK Agent Deployments on Vertex AI - This article explores an enterprise-grade deployment pattern that decouples infrastructure management from application code updates for AI agents on Google Cloud Vertex AI. By utilizing a two-phase approach, infrastructure teams can use Terraform to provision stable placeholder Reasoning Engine IDs on Day One, while application developers use CI/CD pipelines and the Google Agent Development Kit (ADK) to seamlessly patch agent code in place. The guide also shares crucial production lessons, including how to avoid deployment traps by using `source_code_spec` and maintaining Python 3.11 code compatibility.
DevOps KubernetesGitOps for AI Agents on Google Cloud: ArgoCD, Config Sync, and GKE - How to bring version control, auditability, and repeatable rollouts to a new kind of workload: the autonomous AI agent.
App Development, Serverless, Databases, DevOps
Cloud SQL Database Migration Service Databases Official BlogBeyond DMS: Accelerating Migrations SQL Server Logins and Users to Cloud SQL - Replicate SQL Server logins and passwords to a Cloud SQL database while avoiding migration errors, maintaining security and pruning stale credentials.
Firebase Gemini Generative AI5 ways to use Gemini text-to-speech (TTS) in your apps with Firebase AI Logic - Discover how to integrate Google Cloud's Gemini text-to-speech models directly into your mobile and web applications using Firebase AI Logic for low-latency, natural audio generation.
Firebase GeminiThree ways to save a billion tokens with Firebase AI Logic and on-device AI for Chrome - This article explores how developers can drastically reduce cloud token consumption and cut AI costs at scale by combining Firebase AI Logic with on-device AI in Chrome.
ADK Agents Cloud Run VPCFrom Prototype to Production: Deploying ADK Agents on Cloud Run with Enterprise VPC Governance - This article gives a walks throughod deploying AI agent built with Google's Agent Development Kit from a local prototype to a secure production deployment on Cloud Run.
Cloud Run WorkspaceTaking Advantage of Cloud Run Sandboxes with Google Apps Script for Google Workspace - Deterministic Sub-Second Python and Bash Execution, Zero-Trust gVisor Isolation, and Zero Idle Cost.
Agents LLMHow Google Cloud Plugins are the Ultimate Cloud Toolkit for Claude Code - Discover how Google Cloud Plugins streamline your development workflow by seamlessly integrating official Agent Skills and Model Context Protocol servers directly into Claude Code. The article provides a step-by-step guide on how to easily discover, browse, and install these powerful foundational and domain-focused bundles straight from your terminal or workspace.
Cloud SQLEmbedding versions management, TOAST and bloating in PostgreSQL - This article explores the database performance impacts and table bloating that occur in PostgreSQL and AlloyDB when refreshing or updating AI vector embeddings. It demonstrates how bulk updates double storage size due to TOAST and index growth, and discusses why standard vacuuming only reclaims dead tuples rather than shrinking disk allocation.
Big Data, Analytics, ML&AI
ADK GCP Experience Official Blog TelecommunicationsHow KDDI built Buffmee, a faster, reliable consumer RAG app - KDDI's RAG app 'Buffmee' case study: Learn how they utilized an automated evaluation framework and Agent Development Kit to reduce total latency by 38% and successfully scale Gen AI performance.
Apache Beam Cloud DataflowHow We Lit Up Dataflow’s Black Box with OpenTelemetry tracing - Why standard bottleneck detectors leave you blind — and how an unbroken trace chain exposes what’s really stalling your stream.
AI Cloud Pub/Sub Data Analytics Machine LearningIntroducing Pub/Sub AI Bytes — Part 1: In-flight Inference with SMTs - Welcome to Pub/Sub AI Bytes — Our Fall blog series covering latest features, emerging AI architectures and industry reference patterns!
AI BigQuery Data ScienceEngineering Agent Observability with BigQuery - Transitioning from Batch Logging to Systems of Action.
Apache Iceberg BigQuery WorkspaceUnifying Google Workspace and Apache Iceberg: Serverless Lakehouse Management - Turn Google Sheets into a Petabyte Lakehouse with Sub-Second ACID Queries.
Apache Iceberg BigQuery WorkspaceServerless Multimodal Vector Search on Apache Iceberg via Google Apps Script - This article explores a serverless architecture that combines Google Apps Script, Apache Iceberg, and the Gemini API to build a zero-maintenance multimodal vector search engine. It demonstrates how to ingest and index diverse enterprise assets—such as Google Docs, spreadsheets, binary images, and text notes—into an open Parquet table without needing expensive, dedicated vector databases.
Apache Iceberg BigQuery WorkspaceBidirectional Writeback for Apache Iceberg via Google Sheets: Serverless Lakehouse Console - This article explores a serverless, zero-cost architecture that turns Google Sheets into an interactive ACID mutation console for Apache Iceberg on Google Cloud Storage. By combining a Change Data Capture (CDC) engine in Google Apps Script with BigQuery compute, frontline business users can query, edit, and commit data modifications directly back to open lakehouse tables without expensive Reverse ETL SaaS platforms.
AI BigQueryRAG into the Wild: 5 Engines, 5 Truths about your unstructured Data - This article explores how to effectively unlock enterprise unstructured data by benchmarking five different Retrieval-Augmented Generation (RAG) engines on Google Cloud. It details a serverless, event-driven workflow that ingests complex files, generates embeddings, and evaluates performance using Gemini-powered metrics and comparative synthesis.
Agents AIThe Anatomy of Harness Engineering: How to Evaluate, Iterate, and Guard AI Coding Agents - This article explores how to build reliable AI coding agents by shifting away from traditional end-to-end benchmarks toward behavioral evaluations. It outlines a practical framework for testing intermediate actions and specific tool usage, helping developers safely iterate on prompts and upgrade models without causing regressions.
Gemini LLMInside Google’s Gemini 3.8 Flash and FlashAttention-3: The Hardware Physics of 2M Tokens - This article provides an in-depth engineering analysis of how Google Cloud achieves extreme long-context capabilities (up to 2 million tokens) in its Gemini frontier models. It breaks down the mathematical, physical, and architectural mechanics—such as FlashAttention, Grouped-Query Attention, and Ring Attention—that overcome the traditional quadratic memory bottleneck of Transformers.
AI LLM TPUAutonomous LLM post-training with Tunix on TPUs - This article introduces autofinetune, a project that automates the LLM post-training process using AI agents to run iterative experiments overnight on Google Cloud TPUs. It demonstrates how autonomous research loops can handle both supervised fine-tuning and reinforcement learning using tools like Tunix and Gemma, significantly reducing manual hyperparameter tuning.
Slides, Videos, Audio
GCP Bytes Podcast - #49 In the episode we discuss; ReactOS, Omarchy, Exchange Patching, AI Slop Blocker, GDG, Telstra NTP, Gartner Cloud Leader, Always On Cloud Run, Fault Injection Test, Google Tech Breakup, NVIDIA Buys hugginface, Anthropic Cuts, Mac Mini Demand, AI Agents for Fin. Services, Fable and Mythos 5.1, Astra, Gemini Flash 3.8, Muse Spark 1.3, mem0.
Releases
API Gateway - Enable Model Context Protocol (MCP) You can now configure API Gateway to act as a remote Model Context Protocol (MCP) server. This Public Preview feature allows you to expose your existing REST APIs to AI agents as tools, without requiring changes to your backend services. You can enable MCP by annotating your OpenAPI 3.x specification using custom Google extensions. For more information, see Model Context Protocol overview and Configure Model Context Protocol.
AlloyDB - You can now monitor the status, throughput, and backlog of the audit logging pipeline for your AlloyDB for PostgreSQL instances and nodes using Cloud Monitoring. For more information, see Monitor audit log pipeline status.
Assured Workloads Access Approval - Privileged Access Manager is generally available (GA).
BigQuery - Conversational analytics now supports predictive modeling questions using the AI.PREDICT function. This feature is in Preview. BigQuery generative AI functions now support the following Gemini models: gemini-3.5-flash-lite gemini-3.6-flash gemini-3.7-flash The Data Engineering Agent now integrates with BigQuery Graph to provide additional context between your data source and destination schema, and improves schema mapping accuracy for your data engineering pipelines. This feature is generally available (GA). Conversational analytics in BigQuery now supports the ML.CORRELATION function to calculate statistical correlations between a target column and one or more metric columns in a table. This feature is in Preview. You can use the AI.CAUSAL_EFFECT function to quantify the impact of specific interventions on time series data. This feature is in Preview. You can now use the ML.METRICS function to compute evaluation metrics for machine learning classification or regression tasks on any table or query that contains actual and predicted values. This function lets you evaluate predictions without needing to create or reference a stored model. This feature is in Preview.
Chronicle - Deprecation of write permissions from the chronicle.readonly OAuth scope Effective January 25, 2027, write permissions will be removed from the chronicle.readonly OAuth scope, restricting it strictly to read operations. You can continue using chronicle.readonly for read operations. Make sure you update any workflows performing write operations to use the chronicle OAuth scope.
Cloud Monitoring - A chart on a dashboard can override the dashboard's time-range setting. This feature lets you view trends over a long period or metric data with low sampling rates alongside charts that show only recent data, and is Generally Available (GA). For more information, see the following documents: Google Cloud console: Set a time-range override for a chart or group API: Dashboard with an XyChart widget that sets a time-range override
Cloud Run - To take advantage of reduced pricing for Cloud Run jobs, you can delay job execution to defer non-urgent tasks for up to 12 hours (Preview).
Cloud SQL Postgres - Regional endpoints (REP) are now generally available ( GA ) for the Cloud SQL for PostgreSQL Admin API. Regional endpoints let you interact with Cloud SQL for PostgreSQL instances using regionalized URLs (such as sqladmin. {region}.rep.googleapis.com ) rather than through a single global endpoint. Regional endpoints provide regional frontend and load balancing infrastructure that improves data residency by keeping network traffic within the same region as the instance. This reduces the instance's dependency on global frontend infrastructure. Regional endpoints have strong regional isolation, so the failure of a load balancer or frontend in one region doesn't affect any other region. Regional service load balancers have a separate, regionally isolated control plane. Regional endpoints are designed to meet stringent data residency and sovereignty standards, such as ITAR and Assured Workloads Regions, ensuring data in transit remains within the committed region. Certificate management and TLS termination occurs within each region, on the regional load balancer, so data remains encrypted until it reaches its destination region and stays within that region while being processed there.
Cloud Storage - Storage Intelligence advisor is now generally available. Storage Intelligence advisor lets you monitor and manage your Cloud Storage environment at scale across organizations, folders, and projects. For more information, see About Storage Intelligence advisor.
Cloud Trace - The Observability API supports VPC Service Controls. This integration is generally available. For more information, see the following: Use VPC Service Controls with Google Cloud Observability Observability API overview Supported products: Observability API
Compute Engine - Generally available: You can convert a single-project reservation into a shared reservation, or a shared reservation into a single-project reservation. Modify the share type for a reservation to share your reserved resources with other projects in your Google Cloud organization, or to restrict access to only the reservation's owner project. For more information, see Modify the share type for a reservation.
Contact Center AI Platform - Full notes on the release page.
Dataplex - Data domains in Knowledge Catalog allow you to logically organize the resources within the enterprise to discover and curate your data at scale. This feature is available in Preview. For more information, see About data domains.
GKE - (2026-R38) Version updates Note: Your clusters might not have these versions available. Rollouts are already in progress when we publish the release notes, and can take multiple days to complete across all Google Cloud zones. Version 1.35.7-gke.1222000 is now the default version for cluster creation. The following versions are now available: 1.34.11-gke.1056000 1.35.8-gke.1380000 1.36.4-gke.1247000 The following node versions are now available: 1.31.14-gke.2689000 1.32.13-gke.2411000 1.33.13-gke.1636000 1.34.11-gke.1056000 1.35.8-gke.1380000 1.36.4-gke.1247000 The following versions are no longer available: 1.34.10-gke.1079000 is deprecated. This version will be removed in 90 days, or at the end of support, if sooner. 1.35.7-gke.1027000 is deprecated. This version will be removed in 90 days, or at the end of support, if sooner. 1.36.3-gke.1537000 is deprecated. This version will be removed in 90 days, or at the end of support, if sooner. Clusters in this channel running the listed minor version have new general auto-upgrade targets. GKE can upgrade control planes and nodes to the following new versions with this release: GKE upgrades clusters to the following new patch versions if no minor version upgrade is available, or if the cluster has maintenance exclusions or other factors preventing minor version upgrades: 1.35 to 1.35.7-gke.1222000 1.36 to 1.36.3-gke.1640000
IAM - You can get IAM role suggestions from Gemini programmatically by using the Policy Assist API ( Preview ). For more information, see the following documentation: Get predefined role suggestions with Gemini assistance Policy Assist REST reference The Identity and Access Management (IAM) Model Context Protocol (MCP) server is generally available. You can connect to the IAM remote MCP server from AI applications to inspect and manage custom roles and deny policies across your resources. For more information, see the following documentation: Use the IAM remote MCP server IAM MCP reference
Looker - The deprecation of the Looker Mobile (Legacy) application has been postponed to January 31, 2027. Starting on January 31, 2027, support for the Looker Mobile (Legacy) app will be discontinued and the app will be unavailable for download from the App Store or Play Store. Although users will still be able to use the Looker Mobile (Legacy) app if they already have it installed, we recommend that you install the non-legacy Looker mobile app. The Looker extension for VS Code is now generally available, enabling local LookML development and AI-assisted "vibe coding" using the Model Context Protocol (MCP). This update introduces an interactive onboarding walkthrough, support for populating workspaces from bare repositories, and enhanced synchronization between local Git branches and Looker Development Mode. Additional improvements include support for OAuth with the Kiro IDE and more secure storage of API client secrets.
NetApp - Google Cloud NetApp Volumes now supports the Flex Unified service level in the following regions: asia-east1 (Taiwan) australia-southeast2 (Melbourne) europe-southwest1 (Madrid) For more information about available regions, see Supported regions.
Network Connectivity Center - Support for global Google APIs for endpoint propagation through Network Connectivity Center is available in Preview. For information about the new quota for propagated global Google APIs, see NCC quotas.
Network Intelligence Center - You can deploy Monitoring Points optimized for Amazon Web Services (AWS) or Microsoft Azure cloud infrastructure from Cloud Network Insights.
Policy Intelligence - The Policy Assist remote MCP server is available in Preview. To learn about using the Policy Assist remote MCP server to let external AI agents and applications suggest IAM roles, see Use the Policy Assist remote MCP server and the Policy Assist MCP reference. The Policy Assist REST API is available in Preview. Policy Assist lets you get IAM role suggestions for individual principals with AI assistance. To learn about using the Policy Assist API to get role suggestions programmatically, see the Policy Assist REST reference.
Secret Manager - Parameter Manager supports using tags to group and organize parameters and conditionally manage access control using Identity and Access Management (IAM) policies. For more information, see Create and manage tags.
VPC Service Controls - General availability support for the following integration: Observability API
Virtual Private Cloud - Preview: Propagated connections support Private Service Connect endpoints that access global Google APIs. With propagated connections, endpoints that access global Google APIs in one consumer VPC spoke can be privately accessed by other consumer VPC spokes that are connected to the same Network Connectivity Center hub.