Building cross-cloud solutions with best-of-breed cloud-native databases means learning multiple SDKs, translating queries, handling different errors, and testing across providers. The Multicloud DB SDK for Java lets you share that work across Azure Cosmos DB, Amazon DynamoDB, and Google Cloud Spanner. You (or your coding agent) write CRUD and query logic against one Java API, with provider selection […] The post MulticloudDB SDK: Cross-cloud portability in the coding agent era appeared first on Azure Cosmos DB Blog.
AWS Security Token Service (AWS STS) has simplified session token size limits, giving you more room for your session policies and session tags. STS has replaced the packed policy size and the overall session token size limits with a single token size limit of 4,096 bytes. STS now reports session token size in API responses, […]
AWS CloudTrail, a service that records API activity across your AWS account for security auditing, compliance, and operational troubleshooting, now integrates with Amazon Q Console to help you investigate your AWS account activity using natural language. You can ask Amazon Q Console questions about your CloudTrail configuration, query your logged events for security investigations, and troubleshoot operational issues without writing queries or manually parsing log files. With this integration, you can ask Amazon Q Console to check whether your CloudTrail trails are properly configured, identify gaps in your logging coverage, and confirm which data event sources you are tracking. You can investigate security concerns by asking who accessed a specific IAM role, what changes were made to your VPC configuration, or whether there were unauthorized access attempts in the past week. For operational troubleshooting, you can ask Amazon Q Console to find who created or deleted specific resources, identify which API calls are generating errors, trace activity from a specific IP address, or determine why your bill spiked. Amazon Q Console can query your CloudTrail trails, associated CloudWatch log groups, and event data stores on your behalf, providing answers grounded in your actual account activity rather than generic documentation. This integration is available in all AWS commercial regions where Amazon Q Console is supported. To get started, open Amazon Q in AWS Management Console and ask questions about your CloudTrail configuration or account activity. For more information, visit the AWS CloudTrail documentation.
Learn how Abnormal AI deployed Amazon Bedrock AgentCore Code Interpreter as an ephemeral compute scratch pad for the agents behind its real-time email threat detection at billion-message scale, plus the sandbox design decisions and practical lessons for builders deploying Code Interpreter in production.
AvioBook, a Thales Group Company, prototyped Connected Analytics on Amazon Bedrock AgentCore to turn AvioBook Connect's operational data into plain-language, evidence-based answers for airline managers and dispatchers, helping them find and act on the causes of flight turnaround delays.
Organizations with geographically distributed workforces face a trade-off between security and low-latency access. This post explores how to use AWS Local Zones and Secure Access Service Edge (SASE) solutions to deploy virtual security appliances closer to end users, covering key design principles, capacity planning, and traffic routing.
Build a high-concurrency async Python rideshare application with Tortoise ORM and Amazon Aurora DSQL. This post walks through the key adaptations: UUID primary keys, IAM-authenticated asyncpg connections with a connection-pool patch, individual DDL execution, and optimistic concurrency control (OCC) retry logic.
Your consumer identity and access management (CIAM) system is the foundation of your customer experience. It’s how users sign in, access services, and engage with your applications. As your business scales across geographies, ensuring authentication is always available becomes a core architectural requirement. However, building multi-Region authentication has traditionally required complex custom replication solutions that […]
AWS Billing Conductor now lets you define custom rate pricing for AWS services, including defining custom usage tiers to configure rates by the desired usage volume. Customers and Partners using AWS Billing Conductor to model commercial agreements with subsidiaries, affiliates, or end customers can now more easily reflect their negotiated pricing on pro forma billing data. Using SKU-scoped pricing rules, you can enter a custom rate and configure usage tier thresholds — instead of marking up or down from the public on-demand rates tied to pre-defined AWS usage tiers. By configuring exact rates and tier breaks directly in a pricing rule, you no longer need to calculate percentage-based markups or markdowns against public on-demand pricing to model your commercial agreements. This gives you precise control over your pro forma billing configuration. Custom rates and custom usage tiers configuration via SKU-scoped pricing rules is available in all commercial AWS Regions, excluding the Amazon Web Services China (Beijing) Region, operated by Sinnet, and the Amazon Web Services China (Ningxia) Region, operated by NWCD. To learn more, visit the AWS Billing Conductor product page, or review the User Guide.
Today, Amazon SageMaker AI announces instance preference lists for training and processing jobs, making it easier and faster to find compute capacity for your workloads. Many AI training, fine-tuning, and data processing workloads run comparably well on any of several instance types or sizes. However, before now, you had to name only one instance type at the time of job submission and wait for SageMaker to find that specific instance for your job. For high-demand GPUs during peak periods, where wait times can be unpredictable, customers sometimes had to build complex retry logic or concurrently submit multiple jobs with different instance types to find the first available option. Now you can simply provide a prioritized list of the instance types your workload accepts, and SageMaker automatically runs your job on the first available configuration from your preferences. With this solution, your training or processing job will likely start sooner. To use this feature, you specify your instance type and count preferences in priority order when submitting the training or processing job. For example, your list might contain a preference of two instances of ml.g6.48xlarge or four instances of ml.g5.48xlarge. SageMaker works through the list and launches your job on the first configuration where capacity is available. You can also configure the capacity sourcing from on-demand sources or from your reserved SageMaker Flexible Training Plans within the same job submission. This feature simplifies the process of getting compute for your jobs during high-demand periods and reduces the undifferentiated manual retrying you would otherwise do, all within the SageMaker training and processing job APIs you already use. Instance preference lists for SageMaker training and processing jobs is available today in all AWS Regions where SageMaker is available through the SageMaker CLIs, APIs, SDKs and Console UI. To learn more, see our documentation or our launch blog.
Prompt caching in Amazon Bedrock can cut input token costs by up to 90% when you repeatedly send the same context to foundation models. This post walks through six practical prompt caching scenarios using the Converse API: message content, system prompt, tool definition, mixed TTL, tenant isolation, and LangChain integration.
Manually tagging thousands of catalog products is slow and inconsistent. This walkthrough shows how to customize Qwen3-8B with supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) on Amazon SageMaker serverless model customization, then deploy it for asynchronous inference to build a cost-efficient product tagging system.
Amazon SageMaker AI now offers instance preference lists for training and processing jobs. Specify an ordered list of up to five instance types, and SageMaker AI automatically launches on the first type with available capacity, eliminating manual retry loops and capacity-watching scripts.
Amazon Connect Customer now enables agents to bid on preferred shifts, giving them more control over their work schedules. Schedulers first establish agent ranking either by uploading a CSV file or generating a randomized ranking. Connect Customer then uses forecasted demand and shift profiles to generate available shifts and presents them to agents to rank. For example, in a Monday–Friday 6AM–10PM shift profile with 9-hour shifts, required shifts are 6AM–3PM (500 agents), 9AM–6PM (800 agents), and 1PM–10PM (600 agents). Once the bidding window closes, Connect Customer automatically assigns each agent to their highest-ranked available shift while using agent ranking as a tiebreaker. Shift bidding gives agents a structured way to influence their own schedules, while reducing the time schedulers spend on manual shift assignments, improving both agent satisfaction and scheduling efficiency. This feature is available in all AWS Regions where Amazon Connect Customer agent scheduling is available. To learn more about Amazon Connect Customer agent scheduling, click here.
The principle of least privilege is straightforward to articulate but challenging to maintain at scale. When teams first deploy applications to AWS, they often grant broader permissions than strictly necessary; it’s faster to get things working, and the plan is always to tighten permissions later. But later rarely comes. Permissions accumulate, AWS Identity and Access […]
Amazon Bedrock AgentCore Identity now offers a Consent portal, a managed web experience and session binding endpoint for AgentCore Gateway. This post walks through provisioning a portal, configuring GitHub and Slack authorization code grant targets, and the end-user consent flow, and shows how to review activity in AWS CloudTrail.
AWS root user sign-in is now served across US East (N. Virginia), US East (Ohio), and US West (Oregon), with sign-in traffic distributed across all three Regions. This change reduces reliance on US East (N. Virginia) and improves resiliency during service disruptions. AWS automatically routes your root user sign-in to a supported Region without requiring you to select a Region or change how you sign in. This improvement is available now for all AWS accounts. In AWS CloudTrail, ConsoleLogin events for root user sign-ins are recorded in the Region that processed the sign-in request. To maintain full visibility into root user sign-in activity, update your monitoring and alerting to cover US East (N. Virginia), US East (Ohio), and US West (Oregon). To learn more, see the AWS Sign-In documentation and the CloudTrail ConsoleLogin event reference.
Orchestrating specialized Amazon Bedrock AgentCore agents with AWS Step Functions gives you the reasoning power of generative AI with the guardrails of deterministic validation. Agents propose options, and deterministic code validates them before any action is taken, demonstrated here with an airline rebooking workflow.
Part 1 showed how row lock contention degrades Amazon Aurora PostgreSQL throughput. In Part 2, use Amazon CloudWatch Database Insights and its Lock Tree to pinpoint blocking sessions, then resolve contention with query termination, timeout parameters, and architectural patterns such as SKIP LOCKED and row splitting that restore throughput.
Row lock contention can collapse database throughput during a flash sale even when CPU and I/O look healthy. In Part 1 of this series, learn how PostgreSQL row locking works and how to monitor lock contention in Amazon Aurora PostgreSQL and Amazon RDS for PostgreSQL using system views, the pgrowlocks extension, and the log_lock_waits parameter.
Learn how Ninth Wave built Compass, a multi-agent AI onboarding assistant on Amazon Bedrock AgentCore that validates bank APIs against Financial Data Exchange (FDX) standards, scores compliance, and compresses open finance onboarding from weeks to minutes while meeting SOC 2 and PCI DSS requirements.
Pick the right generative AI customization approach on AWS with an 8-step decision framework, from prompt engineering and RAG to fine-tuning, continued pre-training, and Amazon Nova Forge. Start simple and escalate only when you must.
Foundation models made catalog-wide demand forecasting easy; the hard part is now acting on the forecast. This post builds a closed detect-decide-act loop on Databricks and Amazon Quick that reconciles demand surges against live supplier availability and places replenishment orders unattended, escalating to a human only when no supplier can cover a surge.
Multi-agent systems fail in ways traditional monitoring misses. This post presents a dual-layer approach to monitoring production agents: Amazon Bedrock AgentCore Evaluations for continuous quality scoring and AWS DevOps Agent for autonomous infrastructure investigation, shown on a four-agent airline reservation system.
Comparing models on dollars per million tokens misses what production workloads actually pay for: outcomes. This post shares an open-source benchmarking harness that measures cost per correct answer, agent trajectory cost, and rubric-graded deliverable quality across OpenAI models on Amazon Bedrock.
Learn how to build and deploy an MCP App with interactive HTML widgets on Amazon Bedrock AgentCore. Because MCP Apps is a host-agnostic standard, the same server delivers the same rich experience across AI hosts like ChatGPT and Claude that support the extension.
Run ad hoc SQL analytics on your Amazon DynamoDB data with DuckDB. A zero-ETL integration replicates your table into Apache Iceberg tables on Amazon S3 Tables, and an AWS Lambda function running DuckDB serves SQL queries through an IAM-authorized function URL.
Combine zero-shot forecasting with Amazon Chronos2 and multi-agent orchestration on Amazon Bedrock AgentCore to turn demand forecasts into validated purchase orders. No per-product model training, with business rules, auditability, and cost that scales to zero.
Amazon SageMaker Unified Studio now supports ODBC connections, so data users can connect Microsoft Power BI and other ODBC-compatible tools directly to governed data in SageMaker Unified Studio projects using the Amazon Athena ODBC driver. This adds a native connection path for analysts who have standardized on Power BI to work with governed data using their existing tools and workflows. Amazon SageMaker Unified Studio adds an ODBC connection details view to the project overview page, alongside the existing JDBC view. From the project's JDBC and ODBC connections tab, data users can copy the connection string and its parameters for a DSN-less connection, or use them to configure a named DSN. The Amazon Athena ODBC driver (version 2.2.0.1 or later) works directly with SageMaker Unified Studio through two modes: SageMakerBrowserIdc, which opens a browser to sign in through AWS IAM Identity Center and your external identity provider, and SageMakerIam, which uses temporary AWS credentials. ODBC connections in SageMaker Unified Studio are available today in all AWS Regions where Amazon SageMaker Unified Studio is available, at no additional cost. To get started, refer to the Amazon SageMaker Unified Studio User Guide and the Amazon Athena ODBC driver documentation.
Amazon SageMaker Inference now offers prefix-aware routing, a routing strategy that sends requests sharing the same prompt prefix to the same instance so the KV cache stays warm. In benchmarks on Llama 3.1 70B, it reduced P50 time-to-first-token by up to 77% and raised KV cache hit rates from about 25% to over 80%.
Amazon SageMaker HyperPod now supports model caching for inference, which pre-loads model weights and container images onto cluster nodes so pods read from local NVMe storage instead of downloading over the network. Learn how model caching cuts cold starts from tens of minutes to seconds, how it works, and how to enable it.
TwelveLabs Marengo Embed 3.0 is now generally available as an embedding model in Amazon Bedrock Knowledge Bases, bringing fully managed natural language search to video, image, and audio content. This walkthrough shows how to build a knowledge base powered by Marengo 3.0 and run semantic queries against your media.
Your teams get an AI assistant that handles real work while your data stays in your environment and your conversations stay private Today, the Amazon Quick desktop application is generally available on macOS and Windows. We’re also adding a new activity feed to the mobile experience on iOS and Android that consolidates email, calendar, CRM, […]
Learn how to build an end-to-end RFI questionnaire workflow with Amazon Quick Automate. Read a multi-tab RFI workbook from Amazon S3, use natural-language prompts to extract and structure the questionnaire data, refine the workflow through conversation, and write clean CSV output back to Amazon S3 — cutting development from days to hours.
A configurable, model-agnostic detector that turns any large language model on Amazon Bedrock into a PII detector. Because the entities to detect live in a prompt rather than in code, one detector adapts to new entity types without retraining, and it outperforms an off-the-shelf tool across five public corpora and nine LLM-based detectors.
Multi-turn agents fail in ways single-turn evaluation misses: one early mistake corrupts every later turn. This post introduces the Agent Evaluation Metric (AEM), a decomposable, turn-level way to measure agent quality, applied to its first dimension, correctness, to pinpoint the turn that caused a failure and separate it from the turns that inherited it.
Amazon API Gateway execution logs help you trace request processing step by step through your REST API stages. They capture authorization results, integration latency, mapping template output, and error details that are otherwise invisible at the API surface. When a production request fails in a way the access log cannot explain, the execution log is […]
Learn how to deploy Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter open-weight model, on Amazon SageMaker HyperPod with vLLM. This walkthrough covers cluster provisioning, NVFP4 quantization, and an OpenAI-compatible endpoint with built-in reasoning, tool calling, and native MTP speculative decoding.
AWS Lambda now supports a 90-minute function timeout for asynchronous and event source mapping (ESM) invocations on Lambda Managed Instances, a 6x increase from the previous 15-minute limit. Data processing, media transcoding, AI inference, and batch workloads can now run on Lambda without re-architecting.
Learn how to build a tiered alerting strategy for Amazon DocumentDB by organizing CloudWatch metrics into Critical, Warning, and Advisory tiers, diagnosing slow queries through three complementary lenses, and monitoring garbage collection health before it becomes a cluster-wide incident.
Today, we are announcing the availability of Agent Substrate on Google Kubernetes Engine (GKE). Agent Substrate is an open-source, secure-by-default agent execution runtime engineered to run millions of sandboxes with 10x higher density than standard container runtimes. Purpose-built for the era of autonomous agents, Substrate delivers sub-500ms resume operations at over 500 suspend/resume activations per second with a native zero-trust kernel and network isolation. Agent Substrate is available as an open-source solution that runs on any Kubernetes infrastructure and is optimized for GKE. Leading AI teams are already building on it: Nous Research, the team behind the Hermes Agent, is actively building on top of Agent Substrate. Hermes is currently ranked the #1 AI agent globally by OpenRouter usage across productivity, coding, CLI, and personal agents. From local to 1M-agent scale Developers already run Antigravity, Claude Code, Codex, OpenClaw, Hermes, and other harnesses locally but that’s fundamentally than running hundreds of thousands of concurrent, long-lived agents that generate code, interact with tools, and drive automated execution — challenges that existing architectures often struggle to meet. Scaling an agent platform from a local prototype to running agents at scale fundamentally changes your infrastructure constraints, which can include: Opaque trust boundaries: Models can generate and run arbitrary code on the fly. Without kernel-level isolation and dynamic network controls, running untrusted code that no human has ever looked at risks host escape, credential theft and data exfiltration. Tool access friction: Agents need full computer environments to invoke command-line tools, headless browsers, and filesystem workspaces. Running these safely needs to be fast and easy. Massive bursts: Agent harnesses, benchmarks, and reinforcement learning rollouts can generate thousands of sandboxes per minute. General-purpose schedulers struggle under this churn, a
From running build tools, to data analysis pipelines, to collaborative research, executing data-driven tasks is essential for any enterprise agent. Today, platform teams often stitch together custom workarounds to address agent storage requirements, which could include shuttling state back and forth between agent sandboxes and centralized storage or manually managing local disks and/or self-hosted file systems. However, as agent fleets scale, these approaches force difficult trade-offs between cold-start latency, operational complexity, and the cost of idle, pre-allocated storage. As organizations scale agent sandboxes to thousands or even millions of concurrent sessions, storage must evolve to overcome these trade-offs and meet the needs of these dynamic workloads, which require strict workspace isolation, instant session resumption, elastic pay-per-use economics, and fluid multi-agent collaboration. To meet these emerging demands, we’re expanding our AI storage portfolio and announcing availability of Filestore agent volumes, a new, fully managed capability purpose-built to deliver high-performance, elastic file storage for scaling agentic workloads on Google Cloud. Purpose-built storage for AI agent workspaces Autonomous agents require isolated runtime environments to safely execute dynamic code, install third-party packages, and run tools without putting host infrastructure or tenant data at risk. While Agent Substrate on GKE and GKE Agent Sandbox provide the dedicated compute environments needed to run high-density agent fleets, those sandboxes also need dedicated persistent workspaces to operate on. Filestore agent volumes within Google Cloud Filestore, give you purpose-built agentic storage to complement your agentic compute via a dynamic provisioning architecture designed specifically for the scale and elasticity of AI agent fleets. Co-designed with Agent Substrate to support agentic fleets at scale, Filestore agent volumes provide GKE sandboxes with instant
Cloud outages can range from global service disruptions to issues isolated to a specific region, zone, or even just your project, workload or application. If you suspect a Google Cloud Platform outage is impacting your services, we recommend you follow a structured “Verify→ Investigate→Report→Resolve→Review" workflow to resolve it. And before that outage occurs, you should also have prepared your environment for an eventual disruption by designing for failure, and actively practicing the steps you need to take to restore service. In this blog, we summarize the key reliability incident handling best practices to help you design and practice your reliability incident response capabilities and minimize impact. Rather than an exhaustive guide, this is meant as a primer on only the most important practices for advisory purposes. Please note that we do not cover additional practices specific to security incidents here. Beyond the base steps covered here, you may want to also explore how AI agents and tools are starting to transform incident handling. Check out this episode of the Prodcast, where Googlers explore the latest trends of leveraging agentic AI in Site Reliability Engineering (SRE) to detect issues early and prevent disruptions. Try Cloud Assist investigations, or explore Agent Skills and remote managed MCP servers to give you another set of tools for quickly pinpointing an issue. Before getting into these advanced techniques, we focus below on the foundational steps to good incident handling. 1. Prepare Long before things start to go sideways, you should have spent significant time preparing for an outage along at least four dimensions: design, data, playbooks and training. Design: Think ahead and mitigate future incidents by designing automated response actions, like a load balancer shifting traffic away from slow or unresponsive instances, or by automating as much of your incident response playbook as possible. Review designs of all critical applications to a
We are excited to share that Gartner has named Google a Leader in its inaugural 2026 Magic Quadrant for Enterprise AI Assistants. In this comprehensive evaluation of top enterprise AI assistant vendors, Gartner placed Google in the Leaders quadrant for its evaluation across both Completeness of Vision and Ability to Execute. Gemini Enterprise helps organizations bring helpful, secure AI directly into the daily work of their employees. It moves teams past basic chat interactions to automating multi-step, end-to-end workflows with AI agents. It connects with the tools and infrastructure companies already use and scales easily and cost-effectively, all with security and governance in place. We see this recognition from Gartner as validation of our goal: creating a unified platform where everyone — from business users to developers — can work alongside AI agents to accomplish more together. Our take on Google as a Leader Amid a complex landscape of standalone AI tools and emerging platforms, Gemini Enterprise emerges as a unified, open agentic platform backed by Google’s full AI stack, with strengths mentioned in the report such as: Unified “AI front door”: Gemini Enterprise unifies enterprise chat and search, first and third-party agents, a no-code agent designer, Google Workspace integration, and third-party connectors all in one platform, eliminating the need for organizations to piece together disparate AI tools. Open connectivity: Gemini Enterprise offers extensive connectivity beyond Google's ecosystem — extending to Microsoft 365, other third-party software, and internal enterprise data sources. This open connectivity lets organizations adopt Gemini Enterprise alongside their existing infrastructure without costly system overhauls. Simple economics: Gemini Enterprise offers a straightforward pricing model, with actions like chat and search included in the base SKU. Organizations can select per-user seat subscriptions, as well as a pay-as-you-go option that lets u
So, you’ve planned your database modernization journey. You’ve set up Google Cloud’s Database Migration Service (DMS), configured replication, and successfully synchronized your application databases from your on-premises or cloud systems to a fully managed Cloud SQL for SQL Server instance. The replication is complete, the data is up to date, and you’re ready for cutover. But when your application attempts to connect to the newly migrated database, you’re hit with a frustrating roadblock: Msg 18456, Level 14, State 1, Line 1: Login failed for user 'app_user. The culprit is simple: your SQL Server logins didn't migrate with your database. In this post, we’ll look at why this gap exists, why it actually protects your organization's security posture, and how easy it is to bridge using standard, time-tested SQL Server tools. Why DMS doesn't migrate logins: Security and compliance Database Migration Service (DMS) is highly efficient at replicating database-level schemas and transactional data. However, it purposefully doesn’t migrate instance-level objects, such as the system master database or server logins and permissions. While this might feel like a missing feature, it is actually a deliberate design choice built around three core pillars: Security Isolation and Privilege Boundaries: The source environment and the destination Cloud SQL environment operate under different security paradigms. Replicating the master system database directly could lead to unauthorized privilege escalation. For example, an on-premises login with sysadmin privileges shouldn’t have unrestricted sysadmin access to a fully managed Google Cloud database. When the cloud provider manages physical backups, patching, and security, it needs to limit underlying operating system access to ensure correct operation. Compliance and Audit Governance: Automated migration of encrypted password hashes and server-level security credentials without explicit administrator oversight frequently violates enterpr
Google Cloud session management provides flexible options for setting up session controls based on your organization’s security policy needs. To help you improve your security posture and mitigate credential theft and account takeover (ATO) risks, we have rolled out a 16-hour default session length for Google Cloud customers. We’ve now completed extending this security standard to all customers who had not already self-configured session lengths, but today’s cloud environments require even more precision. As we conclude this global rollout, we have also evolved Google Cloud session controls from a broad administrative setting into a deeply integrated, granular feature of Context-Aware Access (CAA). This update gives administrators more flexibility, better automation, and a more natural security workflow. What’s new in Session Controls 1. Automation-first: Terraform, gcloud, and API supportModern infrastructure is managed as code. To support DevSecOps workflows, the Session Controls policy configuration is no longer limited to manual UI configuration. Now generally available, you can define, deploy, and manage your session policies programmatically using: Terraform: Integrates session controls directly into your infrastructure manifests. gcloud CLI: Manages policies from the command line. REST APIs: Automate policy enforcement across complex multi-tenant environments. 2. Granular targeting with Google GroupsOne of the most requested upgrades has been the capability to target policies with precision. Previously, session lengths were tied to organizational units (OUs). Now generally available, the Session Controls policy uses Google Groups. This shift allows you to apply distinct session policies to specific clusters of users — such as requiring a two-hour session for users with elevated privileges (such as billing administrators and project owners) while maintaining a standard 16-hour session for general developers — regardless of where those users sit in your organiz
The telecommunications industry is currently undergoing a paradigm shift, moving from traditional manual human-driven operations to fully Autonomous Network Operations. Modern networks have grown increasingly complex, heterogeneous, and large-scale, making handcrafted rules-based methods and traditional Machine Learning (ML) approaches alone insufficient to automate network operations. While ML methods can identify subtle patterns and make fine predictions from large amounts of structured data, they lack the ability to understand, reason about the data and the system it represents, and ultimately make the kind of decision a human operator would. The growth of AI agents and their ability to reason is a promising solution to this shortcoming. However, in the same way a human operator is not capable of directly ingesting the statistical information spread across the billions of data points created in a large network, AI agents also lack the ability to operate at this scale. To address this challenge, telecommunications companies are adopting Graph Neural Networks (GNNs), a modern form of machine learning designed to operate natively on massive volumes of temporal and relational data. By integrating GNNs with AI agents, operators can combine advanced diagnostics such as root cause analysis, capacity planning, traffic forecasting, what-if simulations, and real-time anomaly detection with the reasoning power required to interpret these insights and execute justified actions. This powerful combination enables networks to safely move towards Level 5 Autonomy as defined by TM Forum, where the system operates autonomously. In this post, we present the three components (Data, ML, and AI) that will power Google Cloud’s Autonomous Network Operations framework. Google Autonomous Network Operations framework architecture Foundation: Digital Twin on Spanner Graph At the heart of Google Cloud’s Autonomous Network Operations framework is the network digital twin: a highly detailed, v
Batch Issue A workaround has been added for the known issue that jobs might fail when specifying Compute Engine (or custom) VM OS images with outdated kernels. Gemini Enterprise Agent Platform Feature Reinforcement learning fine-tuning in the Google Cloud console (Preview) You can create, monitor, and test reinforcement learning fine-tuning jobs for Gemini models in the Google Cloud console (Preview). From the Models > Tuning page, you can configure Python code or model-based reward functions, test reward logic against sample prompts before launching a job, track training and evaluation metrics in real time, and test tuned checkpoints in Agent Studio. For more information, see Quick start: Reinforcement learning fine-tuning using the console. Policy Intelligence Feature Policy Troubleshooter now supports troubleshooting access for agent identities. You can troubleshoot IAM allow policies, deny policies, and principal access boundary policies for agents acting under their own authority by entering the agent's principal identifier or by troubleshooting with an error ID from an access denial event. To learn more, see Troubleshooting access.
BigQuery now features a suite of augmented analytics Table-Valued Functions (TVFs) designed to automate complex data analysis at scale. Augmented analytics combines AI, ML and statistical methods to automate insight discovery and pattern explanation. These functions allow you to diagnose why metrics changed, uncover underlying trends and relationships across the data, and even isolate the true impact of business decisions. These TVFs run directly where your data lives, which helps speed up analysis and reduces the need to export data into external tools. In addition, since these functions are compact and yield structured SQL outputs, they can easily be integrated as skills for AI agents, which easily enables automated, conversational data investigation workflows. We are introducing six new augmented analytics functions in BigQuery, each created to address a specific analytical challenge: TVF Function What It Helps You Find Real World Question It Answers AI.KEY_DRIVERS Identifies the top drivers behind an increase or drop in a metric between two time periods or groups. Why did revenue spike this quarter compared to last quarter? AI.CAUSAL_EFFECT Quantifies the impact of an action or event by comparing the observed results to an expected baseline. How much of the revenue lift came from our pricing update rather than organic growth? ML.CORRELATION Evaluates the direction and strength of the relationship between pairs of numeric metrics. Does increased user session duration correlate with higher lifetime customer value? ML.DETECT_CHANGE_POINTS Identifies specific dates or intervals where a metric experiences a shift compared to surrounding patterns. During which time periods did our platform latency experience persistent, structural shifts? ML.TREND Separates the underlying growth or decline from short-term fluctuations or noise. What are the underlying trends of my revenue over the past year, abstracting away the outlying spikes and drops? ML.SEASONALITY Discovers pred
OverviewAs enterprises scale their AI and agentic workflows, they require serverless platforms that make data preparation for model training, evaluation, and inference effortless and efficient. Dataflow is a critical component of Google Cloud’s AI stack. It enables our customers to create batch and streaming pipelines that support a variety of analytics and AI use cases. Today, we’re delivering significant enhancements to Dataflow that directly address your top challenges: maximizing compute efficiency for long-running batch jobs and delivering extra inference power for your most demanding AI workloads. We’re thrilled to announce the general availability of Pause/Resume for Dataflow batch jobs as well as support for G4 VMs powered by NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs. With these features, you can accelerate your AI development lifecycle and optimize your costs. Recover wasted compute and increase developer productivity with Pause/Resume for Dataflow batch jobsDataflow customers frequently run large batch workloads that sometimes run for a few days. When these jobs fail, Dataflow users currently cannot access the data that was already processed before the job failure. Instead, they have to retry the entire job, leading to wasted compute resources and decreased engineering productivity. In addition to addressing failures from large jobs, Dataflow customers with AI workloads sometimes want to increase the utilization of accelerated compute resources like GPUs and TPUs by dynamically re-allocating them from already running, lower priority Dataflow batch jobs to higher priority workloads like feature engineering and AI inference. To better support these use cases, we are announcing the GA launch of Pause/Resume for Dataflow batch jobs. Powered by internal Google innovation, this feature enables Dataflow customers to resume their failed long running jobs instead of starting from scratch. It also allows customers to pause and resume their Dataflow batch job
We are excited to share that Google Cloud was named a Leader and received the highest score in the ‘current offering’ category in the Forrester Wave™: Public Cloud Platforms, Q3 2026 report, which examines the 10 most significant public cloud providers across 30 comprehensive criteria, Google also received the highest possible score in 23 out of 30 evaluation criteria, including, but not limited to vision, innovation, AI development services, database services, analytics services, containers and kubernetes services, modernization services, and security services. We believe Forrester’s recognition confirms our belief that to lead in the agentic era, you need a complete, integrated platform that’s engineered from the ground up, from silicon to systems to models. Access the complimentary report: The Forrester Wave™: Public Cloud Platforms, Q3 2026. Build on co-designed infrastructure proven in global enterprises For over a decade, our infrastructure engineers, application developers, and AI researchers worked side by side to co-design infrastructure to power Gemini, Search, YouTube, Maps, and Gmail. We couldn't simply buy the platform and infrastructure we needed; we had to invent it. This led to the creation of everything from TPUs, the Transformer architecture, Kubernetes, Axion, and now Gemini. In the agentic era, you need an integrated AI stack, where compute, orchestration software, modernization tools, and global networks operate together to give you more value from your investments — even if you’re not working at the frontiers of AI research. At Google Cloud, we’ve worked tirelessly to bring these breakthrough innovations to leading enterprises, startups, and frontier labs to help them achieve new levels of scale and efficiency, and we believe Forrester’s evaluation validates that strategy: “Google Cloud’s vision is to enable the ‘agentic enterprise,’ and AI already permeates its platform, positioning the company to push further up the tech stack toward business
Agent Platform Workbench Change 20260911.00_p0 Release Change 20260913.00_p0 Release Change Installed latest packages from upstream dependencies. Change Installed latest packages from upstream dependencies. Fixed Fixed the %%bigquery notebook cell magic, which returned an error instead of query results in JupyterLab 4. Fixed Fixed the %%bigquery notebook cell magic, which returned an error instead of query results in JupyterLab 4. Change 20260913-2230-rc0 Release Change 20260913-2230-rc0 Release Change Installed latest packages from upstream dependencies. Change Installed latest packages from upstream dependencies. Fixed Fixed an issue where the notebook-disable-nbconvert metadata flag was ignored in custom containers. Change The obsolete google-cloud-sdk transitional package is no longer installed. The Google Cloud CLI itself is unchanged; it was already provided by the google-cloud-cli package. Fixed Fixed the %%bigquery notebook cell magic, which returned an error instead of query results in JupyterLab 4. Fixed Fixed an issue where the notebook-disable-nbconvert metadata flag was ignored in custom containers. Fixed Fixed the %%bigquery notebook cell magic, which returned an error instead of query results in JupyterLab 4. Change 20260913-2130-rc0 Release Change Installed latest packages from upstream dependencies. Fixed Fixed the %%bigquery notebook cell magic, which returned an error instead of query results in JupyterLab 4. Change M149 Release Change Installed latest packages from upstream dependencies. Fixed Fixed the %%bigquery notebook cell magic, which returned an error instead of query results in JupyterLab 4.
On Tuesday, September 8, Thomas Kurian participated in the Goldman Sachs Tech Conference, providing an update on Google Cloud’s business and strategy. Here are the highlights:Full Stack Approach: Google Cloud is the only provider to offer solutions across the entire AI stack, which expands our total addressable market, differentiates our products from the point of view of performance, cost and quality; and enables us to diversify our revenue streams as the market grows. We have 17 product lines with more than $1 billion in revenues and our customers on average exceeded their commitments by more than 50%. We have also seen more than 2x quarter-over-quarter and year-over-year growth in the number and value of $100 million to $1 billion deals. And we have more than 300 customers each with $100 million-plus contractual commitments.Benefits of Google Cloud’s AI Infrastructure: Our AI Infrastructure is built on highly differentiated products in a large expanding market which helps us lower cost and improve performance and margins for our AI models. We have a 2-year AI server payback period, and TPUs have a much faster expected payback period than GPUs. The majority of our AI infrastructure total contract value is from committed five-year contracts.Benefits of Google Cloud’s broad AI solutions: We have seen strong adoption of Gemini Enterprise, which provides customers with insight across their businesses in a highly cost efficient manner with enterprise control and governance. We have also seen that Google Cloud customers that use our AI products use 1.8 times as many products as those who do not.For more information, please refer to the slide presentation and transcript from the event. This blog post includes statements that could be considered forward-looking. These statements involve a number of risks and uncertainties that could cause actual results to differ materially. Any forward-looking statements in the presentation are based on assumptions as of September 8, 202
Agent skills fit well alongside documentation and remote MCP servers as ways of enabling the success of your AI workflows. They reduce context window usage for certain use cases, and they're straightforward to install. However, you might have noticed that managing individual skills can be unwieldy, or that some skills are most useful when they act alongside other skills or MCP servers toward the same goal. That's where plugins come in to help. Today, we're thrilled to announce a new Google Cloud plugin for AI coding agents! Designed as installable bundles, agent plugins equip the AI agent of your choice with skills and tools to be more effective on Google Cloud. Solving the tool coupling problem As you expand your usage of coding agents, you might find that they become significantly more capable when they use related skills in tandem or with complementary context and tooling. For example, an agent analyzing infrastructure is more effective when combining domain knowledge, workflow recommendations, and the ability to interact with a live environment together. Plugins solve this coupling challenge by packaging related capabilities into cohesive, installable bundles. This allows you to take advantage of both broad foundational capabilities and deep, product-specific tools without managing complex dependencies. For this release, we've started with a foundational plugin that supports agent functionality for all Google Cloud users, focusing on making it easier for agents to retrieve Google Cloud-related skills, make use of official documentation, and handle programmatic interactions with Google Cloud. Built on an open standard We've also built our plugin in compliance with the Agent Plugins specification, an open, vendor-neutral standard for packaging Agent Skills and Model Context Protocol (MCP) servers into portable, interoperable units. Rather than requiring developers to maintain different configurations and wrappers for every AI assistant, the Agent Plugins standard
Want to know the latest from Google Cloud? Find it here in one handy location. Check back regularly for our newest updates, announcements, resources, events, learning opportunities, and more. Tip: Not sure where to find what you’re looking for on the Google Cloud blog? Start here: Google Cloud blog 101: Full list of topics, links, and resources. aside_block <ListValue: []> Sept 7 - Sept 10 Why Your Voice Agent Needs Session AuditingMoving voice agents to production demands robust quality monitoring. This guide dives deep into the inner workings of the Agent Development Kit (ADK) responsible for audio session auditing. Learn how the ADK's save_live_blob feature intercepts, buffers, and stores raw audio chunks during active Gemini Live sessions. We explore building an automated post-processing pipeline to seamlessly stitch these fragments into cohesive, playable audio files. Discover how to leverage these vital audio audit trails to monitor real-world interactions, diagnose failures, and ensure enterprise-grade reliability. Read the full guide here. Pub/Sub SMTs can now AI Inference your Gemini Enterprise Agent Platform models!Pub/Sub AI Inference SMTs allow you to apply inference on an incoming stream of events using models hosted in Gemini Enterprise Agent Platform. The model’s prediction is appended to your event, making it available for downstream processing in your data warehouse (like BigQuery) or operational database (like BigTable). This feature, now generally available, can dramatically simplify or enhance anomaly detection systems you are operating. PostgreSQL Source Connector is now generally available in Managed Service for Apache Kafka!Managed Service for Apache Kafka’s PostgreSQL connector allows customers to capture changes from their PostgreSQL database and ingest them into their Kafka infrastructure with low latency. This source connector is compatible with Cloud SQL for Postgres, AlloyDB, and self-managed PostgreSQL databases. Try this along with our
September 7 - September 10 Pub/Sub SMTs can now AI Inference your Gemini Enterprise Agent Platform models!Pub/Sub AI Inference SMTs allow you to apply inference on an incoming stream of events using models hosted in Gemini Enterprise Agent Platform. The model’s prediction is appended to your event, making it available for downstream processing in your data warehouse (like BigQuery) or operational database (like BigTable). This feature, now generally available, can dramatically simplify or enhance anomaly detection systems you are operating. PostgreSQL Source Connector is now generally available in Managed Service for Apache Kafka!Managed Service for Apache Kafka’s PostgreSQL connector allows customers to capture changes from their PostgreSQL database and ingest them into their Kafka infrastructure with low latency. This source connector is compatible with Cloud SQL for Postgres, AlloyDB, and self-managed PostgreSQL databases. Try this along with our entire portfolio of managed connectors, including MirrorMaker 2.0, BigQuery, Cloud Storage, and Pub/Sub! E-mail kafka-hotline@google.com if you have questions or feedback! Pause-on-failure for Dataflow batch jobs is GADataflow pause-on-failure enables you to preserve the state of a batch Dataflow job before it fails. By pausing your Dataflow job, you can address issues that are external to the pipeline and resume processing without losing completed work. This helps you better manage resource costs and improve job reliability when you face temporary outages or capacity constraints. The insertAll API is now the BigQuery Storage Write API (REST)The legacy insertAll streaming API is now rebranded as the BigQuery Storage Write API (REST). By dropping the "legacy" label, developers can confidently build long-term HTTP-based streaming workflows. This stateless JSON-over-HTTPS endpoint offers a lightweight alternative to heavy gRPC libraries—ideal for serverless web apps, IoT telemetry, and AI logging. The transition is seamless
We are thrilled to announce the general availability of the AlloyDB Omni Red Hat RPM orchestrator, that brings production-ready security, resiliency, and low-downtime operations to PostgreSQL workloads in your enterprise environments. This GA milestone builds on the foundation laid during our preview release and launches alongside AlloyDB Omni version 18.3.0 to bring cloud-like database automation directly to your virtual machines and bare-metal servers with Google’s AI capabilities. As of this GA release, AlloyDB Omni can be deployed in four modes to suit your requirements. Visit AlloyDB Omni documentation for more information. Standalone container (Debian / UBI) Container with Kubernetes operator for Highly Available enterprise deployment Standalone RPM With RPM orchestrator for Highly Available enterprise deployment Why run a self-managed database? For many use cases, a managed cloud database service is the simplest and most cost-effective option. However, there are scenarios where you may choose to run a PostgreSQL database yourself, on or off the cloud. The AlloyDB Omni RPM deployment is built for organizations that need the performance of the cloud with the control of local, non-containerized infrastructure, with use cases including: Workload Modernization: AlloyDB Omni is more than 2X faster for transactional workloads and can deliver up to 100X faster analytical queries than standard PostgreSQL L , revitalizing existing infrastructure without a full migration. Regulated Environments: For industries with strict data residency and security requirements, the RPM orchestrator provides the necessary tools like SELinux and local audit logging to stay compliant. Edge and On-Premises Deployment: Deploying at the edge or on bare-metal servers allows for low-latency processing and disconnected operation. AI-Ready Infrastructure: You can provision database clusters for AI integrations, using AlloyDB AI capabilities such as vector search for modern generative AI applica
For the millions of fervent fans of the Indian Premiere League (IPL), being able to count on a flawless live streaming cricket experience is never up for debate. For Airtel, producing league TV broadcasts with some of the world's most massive concurrent viewership, dropped packets and buffering are simply not options. During the IPL 2026 season, Airtel partnered with Google Cloud to manage this digital delivery. Across 74 matches, the streaming infrastructure delivered several hundred petabytes of egress data. The final match alone processed tens of billions of requests, hitting a peak egress of several Tbps. Delivering video under these concurrency spikes requires an edge architecture designed strictly around localization, paired with proactive operational monitoring. Our goal for IPL 2026 was to deliver an uninterrupted, stadium-grade viewing experience to cricket fans across India, regardless of concurrency surges or network conditions. Partnering with Google Cloud and using Media CDN gave us deep local edge proximity and excellent cache efficiency. Combined with proactive match-day real-time monitoring, we delivered a reliable broadcast experience from start to finish. Architecting for concurrency and edge efficiency One of the primary challenges in live sports broadcasting is seamlessly handling large traffic spikes and never degrading stream performance or overwhelming backend origins. That’s especially important when millions of viewers simultaneously tune in during a final over because every millisecond counts. To accelerate content delivery across India’s diverse ISP landscape, Airtel leveraged Google Cloud’s Media CDN. By utilizing Google’s extensive global edge network, Airtel was able to serve viewer requests from edge locations that were physically close to end users. This deep localization was a cornerstone of the broadcast's success, with 99.9% of all tournament traffic being served locally from within India. This efficient architecture minimized netw
Spanner is Google Cloud’s no-compromise operational database that gives you the horizontal scale and always-on availability of a modern distributed system along with the rich feature set and familiar ecosystem of a relational database. Innovators in industries like banking, retail, media and entertainment, and AI infrastructure rely on Spanner today for their most critical workloads. We’re excited to announce a new, flexible way to handle larger, more complex transactions in Spanner, simplifying applications that need the highest levels of data consistency. Operational workloads typically combine real-time decision making with granular updates: Think: identifying fraud as part of a multi-step checkout process in an ecommerce app. These changes must be transactional; either all of them succeed or none of them do and subsequent requests see the correct data. This update to Spanner’s ACID transactions allows applications to handle more data in an update without compromising on consistency, scalability, or availability using familiar DML. Higher ceiling, more flexibility Previously, Spanner capped the changes a query could perform in a transaction, for example using DML, at 80,000. That was roughly computed as the product of the number of rows and number of columns updated, plus any dependent indexes. Applications evolve over time to handle more data and provide new functionality. These changes increase the size of transactions, potentially causing previously small transactions to hit this limit. This update shifts the 80,000 mutation mod limit from the transaction to individual DML statements. DML statements no longer contribute to an overall transaction-level mutation limit. A single transaction can now contain any number of DML statements, such as INSERT, UPDATE, or DELETE, provided that each individual statement generates fewer than 80,000 mutation mods. Key benefits Larger transactions: Group DML statements logically based on business requirements rather than artif
