GCP Releases
Google Cloud releases and Terraform Google provider. New features, breaking changes, security advisories and deprecations - each summarised in plain English and updated continuously.
Tracking 829 GCP releases · Updated
- Google Cloud release notes aigcppreviewengineer ·
Document AI: Custom Extractor with Gemini 3.5 Flash LLM in Preview
Google Cloud's Document AI now offers a custom extractor model, 'pretrained-foundation-model-v3.5-2026-05-26', powered by the Gemini 3.5 Flash LLM, available in Preview. This enhancement brings advanced ML processing capabilities to the US and EU regions. It is particularly relevant for engineers and architects working with document processing and AI workloads on Google Cloud.
feature - Google Cloud Blog blogaiengineer ·
11 Principles for Token-Efficient AI Coding Assistants
This guide presents eleven principles for optimizing token consumption with AI coding assistants like Gemini, aiming to reduce latency, improve accuracy, and control costs. By adopting structured habits and efficient prompting strategies, developers can maintain a faster, more precise feedback loop. These practices are relevant for all software engineers and architects using AI-powered development tools.
announcement - Google Cloud Blog blogaigcppreviewengineerretailgovernmentgcp-bigquerygcp-cloud-rungcp-pubsub ·
Build AI Agents on GCP with Gemini Enterprise Agent Platform Demos
Google has released 13 hands-on demos for its Gemini Enterprise Agent Platform, showcasing how to build, scale, govern, and optimize AI agents. These demos utilize the code-first ADK and offer practical patterns for enterprise development, from basic agent creation to complex, long-running, and multi-agent pipelines. Developers can leverage these examples to integrate with services like BigQuery and Cloud Run, with features for security, governance, and optimization built-in.
feature announcement - Google Cloud release notes aigcpgaengineer ·
Gemini Enterprise adds BYOID for mobile apps, rebrands NotebookLM
Gemini Enterprise is now generally available with Bring Your Own Identity (BYOID) support for mobile applications, allowing integration with third-party identity providers. Additionally, NotebookLM Enterprise has been renamed to Gemini Notebook Enterprise, though its functionality and APIs remain unchanged. These updates primarily affect organizations using Gemini Enterprise for mobile app development and those familiar with NotebookLM.
feature patch - Google Cloud Blog blogaigcpengineerfinanceretailgovernmentautomotive ·
Google recognized as leader in Conversational AI by Gartner
Google has been named a leader in the Gartner Magic Quadrant for Conversational AI Platforms for the second consecutive year, receiving top marks for vision and execution. This recognition highlights Google's advancements in AI research and enterprise infrastructure, particularly with Gemini Enterprise for Customer Experience. The platform enables organizations to build sophisticated AI agents that can reason, act, and integrate across enterprise systems for improved customer interactions. The announcement emphasizes the capabilities of CX Agent Studio and its foundation on Google Cloud's AI stack, designed for production-ready AI deployments.
announcement - Google Cloud Blog blogaiinfragcpengineergovernmentgcp-gkegcp-cloud-storage ·
GKE Blueprint for Enterprise AI Workload Security
Google Kubernetes Engine (GKE) now offers a blueprint to secure enterprise AI workloads by integrating controls across multiple Google Cloud services and GKE features. This blueprint addresses infrastructure, model, and application security layers, aiming to protect proprietary models and comply with regulations without hindering developer velocity. It is available for platform engineering teams and CISOs managing AI deployments on GKE.
announcement feature - Google Cloud Blog blogaigcpengineer ·
Accelerate Foundation Model Upgrades with Agentic Workflows
Google Cloud's Applied ML team developed an agentic workflow to upgrade foundation models in hours, drastically reducing the months-long manual process typically required. This approach, outlined in a blog post, leverages Gemini Enterprise Agent Platform and Google Antigravity to offer flexibility and adaptability over rigid automation. Engineering teams managing AI model updates can apply these lessons to improve their own migration pipelines, impacting developers and architects working with AI models.
announcement feature - Google Cloud Blog blogaisecuritygcpengineergovernmentgcp-gke ·
Google Cloud AI Threat Defense Combats AI-Driven Cyberattacks
Google Cloud introduces AI Threat Defense, a unified platform leveraging Gemini, Wiz, CodeMender, and Mandiant to counter AI-powered cyberattacks. This new framework aims to provide defenders with a speed and context advantage over attackers who are increasingly using AI for zero-day exploits and rapid multi-agent attacks. The platform assists organizations in preparing, scanning, prioritizing, remediating, and monitoring threats across their software development lifecycle. It's designed for security engineers and architects managing cloud environments.
feature announcement - Google Cloud Blog blogaigcpengineermedia ·
Google's AI agents collaborate to create short films
Google experimented with teams of AI agents collaborating to produce short films, uncovering insights into inter-agent teamwork in creative domains. Agents with distinct roles like Idea Person, Technical Lead, and Editor worked within Scion, an open-source orchestration testbed. This hackathon demonstrated how AI agents can manage complex, multi-step projects with verification gates, producing over 25 films using models like Gemini and Veo.
announcement feature - Google Cloud Blog blogaisecuritygovernanceeolengineergovernmentenergy ·
Safely Integrate AI for Vulnerability Management
This blog post offers practical guidance from Mandiant Consulting on establishing operational guardrails for AI-assisted vulnerability management. It addresses the risks of deploying AI agents without mature integration processes, suggesting a hybrid approach combining AI with deterministic controls and human oversight. The recommendations are aimed at security teams looking to accelerate vulnerability discovery and remediation workflows while maintaining environmental integrity.
announcement - Google Cloud release notes aigaengineer ·
Gemini Enterprise Agent Platform: Feature Memory Bank GA
Gemini Enterprise Agent Platform's Feature Memory Bank now offers generally available memory profiles. These profiles enable agents to access structured, LLM-populated data with static schemas, providing low-latency access to evolving information without costly search operations during a session. This feature is now available for all users.
feature - Google Cloud release notes aipreview ·
Gemini Enterprise adds Jira Data Center action filtering
Gemini Enterprise now supports action-filtering for Jira Data Center federated data stores, allowing specification of accessible Jira projects. This enhancement aims to control data access during search queries and action execution, preventing out-of-scope data operations. The feature is currently in Public Preview and applies to users configuring Jira Data Center data stores.
feature - Google Cloud release notes aigcpengineer ·
Agent Platform Workbench Image Releases
New Agent Platform Workbench image releases are available, including version 20260622-2130-rc0 based on Debian 12 and M143 based on Debian 11. The Debian 12 release fixes an issue where a duplicate Python kernel appeared in the launcher, while both releases incorporate updated upstream dependencies. These updates are for users of the Agent Platform Workbench.
feature - Google Cloud release notes aigcppreviewengineer ·
Agent Platform Workbench image release 20260628-2130-rc0
A new Agent Platform Workbench image release, version 20260628-2130-rc0, is now available. This release updates upstream dependencies and includes TensorFlow and PyTorch packages in the default kernel. The update is relevant for users managing and utilizing the Agent Platform Workbench.
feature - Google Cloud release notes aigcpengineer ·
Agent Platform Workbench Image Releases
Two image releases for Agent Platform Workbench are now available: 20260712-2130-rc0 for Debian 12 and M144 for Debian 11. The Debian 12 release includes updated upstream packages and fixes for cupy installation, while the Debian 11 release also updates packages and resolves a JupyterLab reachability issue on GPU instances.
feature - Google Cloud release notes aigcpengineermedia ·
Agent Platform Workbench image release 20260701-2130-rc0
A new Agent Platform Workbench image release, 20260701-2130-rc0, is available for Debian 12 instances. This release installs the latest upstream packages and fixes critical issues including a race condition affecting JupyterLab reachability on GPU instances and termination of long-running requests. This update is important for users experiencing these specific problems and ensures greater stability.
feature - Google Cloud Blog blogaigcppreviewengineermediagcp-bigquerygcp-looker ·
Analyze and Govern Gemini Enterprise App Usage with BigQuery
Google Cloud now allows administrators to analyze and govern Gemini Enterprise app usage at scale using BigQuery. This integration provides a more nuanced, organization-centric perspective beyond product-level dashboards, enabling teams to profile adoption, quantify value, execute compliance audits, and investigate safety alerts. Telemetry is partitioned into five distinct log tables in BigQuery, accessible via Cloud Logging sinks and an asynchronous batch export API, with Gemini in BigQuery simplifying AI-powered analysis.
feature announcement - Google Cloud Blog blogainetworkinggcpengineer ·
IDC Report: Networking Crucial for Agentic AI Production
An IDC report, sponsored by Google Cloud, highlights that infrastructure and networking are the primary bottlenecks preventing enterprises from moving agentic AI from pilot to production. Security, automation, and talent restrictions are key concerns, exacerbated by agentic AI's distributed nature. The report emphasizes that a foundational, infrastructure-level networking approach, balanced between platform and best-of-breed solutions, is essential for operational control, consistent policy enforcement, and end-to-end trust in agentic AI deployments.
announcement - Google Cloud Blog blogaigcpengineermediaenergy ·
Google's approach to shipping AI apps safely in production
Google is addressing the high failure rate of AI prototypes in enterprise environments by introducing a new AI prototyping stack. This stack decouples experimentation from production systems, allowing rapid iteration and validation without risking stability. Engineers are shifting focus from code quality to architecting safe testing environments, enabling faster delivery of AI features.
announcement - Google Cloud release notes aiengineer ·
Google Cloud CCaaS: Agent Assist Hub, Manual Wrap-up, API Chat Access
Google Cloud CCaaS is releasing new features including an Agent Assist hub that unifies agent coaching and knowledge assistance, and manual wrap-up for agents to attribute time and notes. A new API direct access point for chat allows automatic routing based on external API responses, eliminating menu selection. These updates are rolling out automatically, with minor agent sign-out/sign-in required for Agent Assist functionality.
feature patch announcement
About GCP release tracking on ReleaseBytes
Google Cloud publishes release notes per product — BigQuery, GKE, Cloud Run, Cloud SQL, Vertex AI and dozens more — which makes platform-wide awareness hard. ReleaseBytes aggregates the official GCP release notes and the Terraform Google provider changelog into a single feed, with a plain-English summary of each update and tags for breaking changes, deprecations and security fixes.
Frequently asked questions
How often are GCP release notes updated on ReleaseBytes? ›
Continuously. ReleaseBytes monitors the official GCP release channels around the clock and publishes a plain-English summary of each announcement shortly after it lands.
What kinds of GCP changes does ReleaseBytes track? ›
New features, enhancements, bug fixes, security advisories, breaking changes, deprecations and end-of-life announcements. Every item is tagged by type so you can filter to just the changes that need action.
How can I get alerts for new GCP releases? ›
Set up a free email or Slack alert filtered to GCP, subscribe to the weekly digest, or follow the RSS feed. Teams can also install the ReleaseBytes GitHub App or connect via MCP.
Where does the GCP release data come from? ›
From the official sources: Google Cloud releases and Terraform Google provider. Every item links back to the original vendor announcement.