data: {"id":1,"jsonrpc":"2.0","result":{"capabilities":{"completion":true},"tools":[{"description":"Fetches latest AWS news and announcements","name":"aws_news","parameters":{"properties":{"category":{"description":"Optional category to filter news","type":"string"}},"type":"object"}}]}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-19T19:00:54+0000)\n\n**AWS HealthOmics now supports Nextflow profiles**\n\n\u003cp\u003eAWS HealthOmics now supports Nextflow profiles, enabling customers to activate predefined execution settings at run time. Nextflow profiles allow customers to define reusable settings and select them at the point of execution, making it easy to switch between execution settings without modifying workflow source code. \u003ca href=\"https://aws.amazon.com/healthomics/\"\u003eAWS HealthOmics\u003c/a\u003e is a HIPAA-eligible service that helps healthcare and life sciences customers accelerate scientific breakthroughs at scale with fully managed bioinformatics workflows.\u003c/p\u003e\n\u003cp\u003eWith Nextflow profiles, you can cleanly separate platform-specific settings such as resource limits or execution options from core workflow logic. You can switch between development and production settings without creating separate workflow definitions. This reduces errors from manual edits, accelerates workflow portability, and saves time when scaling from development to production. If you use nf-core workflows, you can now activate the built-in and institutional profiles those pipelines already ship with.\u003c/p\u003e\n\u003cp\u003eYou can now specify one or more Nextflow profiles in your workflow runs in all AWS HealthOmics Regions: US East (N. Virginia), US West (Oregon), Europe (Frankfurt, Ireland, London), Israel (Tel Aviv), and Asia Pacific (Singapore, Seoul). To learn more, visit the Nextflow Profiles section on HealthOmics \u003ca href=\"https://docs.aws.amazon.com/omics/latest/dev/starting-a-run.html#start-run-api-engine-settings\"\u003eNextflow engine settings\u003c/a\u003e documentation.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-22T20:51:42+0000)\n\n**AWS introduces Lambda MicroVMs for isolated execution of user and AI-generated code **\n\n\u003cp\u003eAWS introduces Lambda MicroVMs, a new serverless compute primitive that provides VM-level isolation, near-instant launch and resume speeds, and state preservation for executing user or AI-generated code. You can now give each user or job their own compute environment to securely run code without managing virtualization infrastructure or choosing between isolation, speed, and state retention.\u003c/p\u003e\n\u003cp\u003eDevelopers are increasingly building multi-tenant applications that execute code supplied by end users or AI for use cases such as interactive coding environments, data analytics platforms, coding assistants, and vulnerability scanning platforms. For these applications, developers need to allocate a separate, isolated execution environment per user or session to limit the impact of incorrect or malicious code on other concurrently running users or jobs. Previously, developers needed to choose between strong isolation, fast launch times, and state retention when building these applications. Starting today, Lambda MicroVMs provides you these capabilities without any trade-offs. You get VM-level isolation, near-instant launch speeds, and the ability to suspend and resume execution for up to 8 hours. Lambda MicroVMs is built on Firecracker virtualization, the technology powering more than 15 trillion monthly Lambda Function invocations.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTo get started, create a MicroVM image from your Dockerfile, then launch MicroVMs from that image. Give each user or job their own MicroVM with a dedicated HTTPS URL that supports popular connectivity protocols such as HTTP/2, gRPC, and WebSockets.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eLambda MicroVMs is available today in the following AWS Regions: US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Tokyo), and Europe (Ireland). To learn more, visit the \u003ca href=\"https://docs.aws.amazon.com/lambda/latest/dg/lambda-microvms-guide.html\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAWS Lambda MicroVMs developer guide\u003c/a\u003e\u0026nbsp;and the \u003ca href=\"https://aws.amazon.com/blogs/aws/run-isolated-sandboxes-with-full-lifecycle-control-aws-lambda-introduces-microvms\" target=\"_blank\" rel=\"noopener noreferrer\"\u003elaunch blog post\u003c/a\u003e. Get started with MicroVMs through the AWS Lambda console, AWS CloudFormation, AWS Cloud Development Kit, or use the \u003ca href=\"https://github.com/aws/agent-toolkit-for-aws/tree/main/skills/specialized-skills/serverless-skills/aws-lambda-microvms\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAgent Toolkit for AWS\u003c/a\u003e\u0026nbsp;with your preferred Agentic development tools. You pay for baseline compute resources while your MicroVM is running, and only for the active duration of additional resources consumed when your workload exceeds the baseline. To learn more about pricing, see \u003ca href=\"https://aws.amazon.com/lambda/pricing/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eLambda MicroVMs pricing\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: compute\nProducts: ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-22T16:56:26+0000)\n\n**AWS Transform for migrations now supports all AWS commercial regions as migration targets**\n\n\u003cp\u003eAWS Transform for migrations now supports all AWS commercial regions as migration targets. A migration target region is the AWS region where migrated resources are deployed, including landing zones, network infrastructure, and server rehosting. Customers can now deploy workloads in any commercial region, making it easier to meet data residency requirements.\u003cbr\u003e\n\u003cbr\u003e\nThe new migration target regions are: US East (N. California), Africa (Cape Town), Asia Pacific (Bangkok), Asia Pacific (Hong Kong), Asia Pacific (Hyderabad), Asia Pacific (Jakarta), Asia Pacific (Kuala Lumpur), Asia Pacific (Melbourne), Asia Pacific (New Zealand), Asia Pacific (Taipei), Canada (Calgary), Europe (Milan), Europe (Spain), Europe (Zurich), Mexico (Querétaro) and Middle East (Tel Aviv).\u003cbr\u003e\n\u003cbr\u003e\nTarget region selection is available in the AWS Transform for migrations workflow. For the most up-to-date availability information, see the supported migration \u003ca href=\"https://docs.aws.amazon.com/transform/latest/userguide/transform-vmware-connect-target-account.html#transform-vmware-cta-supported-regions\"\u003etarget region list\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: migration\nProducts: aws-transform-vmware","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-05-28T17:54:54+0000)\n\n**AWS Network Firewall updates default drop action for improved connection reliability**\n\n\u003cp\u003e\u003ca href=\"https://aws.amazon.com/network-firewall/\"\u003eAWS Network Firewall\u003c/a\u003e now uses \u0026quot;Application drop established (server-directed only)\u0026quot; as the default stateful action for all newly created firewall policies, replacing the previous default of \u0026quot;Application drop established (bidirectional)\u0026quot; (formerly named \u0026quot;Application layer drop established\u0026quot;). No action is required to benefit from this change when creating new policies.\u003cbr\u003e\n\u003cbr\u003e\nAWS Network Firewall is a managed service that lets you deploy network protections across your Amazon VPCs. Previously, the “Application drop established (bidirectional)” default could silently drop legitimate server-to-client TCP packets, such as window updates, keep-alives, and resets — causing intermittent connection failures that were difficult to diagnose. With the safer default now in place, new policies avoid this issue.\u003cbr\u003e\n\u003cbr\u003e\nIf your existing environment requires “Application drop established (bidirectional)” to support post-quantum cryptography (PQC) fragmented TLS handshakes, refer to our documentation for guidance on on switching to \u0026quot;Application drop established (server-directed only)\u0026quot; or adding the “to_server” flag to your TCP drop rules so legitimate flow control packets are not blocked.\u003cbr\u003e\n\u003cbr\u003e\nThis update is available in all AWS Regions where AWS Network Firewall is offered. To get started, see \u003ca href=\"https://docs.aws.amazon.com/network-firewall/latest/developerguide/suricata-rule-evaluation-order.html\"\u003eManaging evaluation order for Suricata compatible rules\u003c/a\u003e in the AWS Network Firewall service documentation.\u003c/p\u003e\n\n\nCategory: security-identity-and-compliance\nProducts: aws-network-firewall","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-20T00:36:57+0000)\n\n**AWS Batch now supports customer-ordered instance allocation strategies**\n\n\u003cp\u003eAWS Batch now offers the Best Fit Progressive Ordered (BFPO) and Spot Capacity Optimized Prioritized (SCOP) allocation strategies, giving you more control over instance type prioritization in your compute environments. BFPO and SCOP enable you to manually define instance type ordering based on your workload-specific performance characteristics.\u003cbr\u003e\n\u003cbr\u003e\nTo use these features in AWS Batch, specify BEST_FIT_PROGRESSIVE_ORDERED allocation strategy for your on-demand compute environments or SPOT_CAPACITY_OPTIMIZED_PRIORITIZED for your Amazon EC2 Spot compute environments and provide an ordered list of instance types or families. These features are available via the AWS Batch API (\u003ci\u003eCreateComputeEnvironment \u003c/i\u003eor \u003ci\u003eUpdateComputeEnvironment\u003c/i\u003e) or the AWS Batch Management Console.\u003cbr\u003e\n\u003cbr\u003e\nBFPO and SCOP allocation strategies are supported today in all \u003ca href=\"https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/\"\u003eAWS Regions\u003c/a\u003e where AWS Batch is available. For more information, see the \u003ca href=\"https://docs.aws.amazon.com/batch/latest/userguide/allocation-strategies.html\"\u003eAWS Batch User Guide\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: TBD\nProducts: ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-22T16:15:45+0000)\n\n**AWS IAM Identity Center now supports separate quotas for AWS accounts and applications**\n\n\u003cp\u003eAWS IAM Identity Center now supports separate quotas for the number of AWS accounts and applications that can be configured in an IAM Identity Center instance. By default, you can configure up to 7,000 AWS accounts and up to 7,000 applications independently, so that using more of one does not consume capacity from the other. Quotas can be further increased by submitting a quota increase request through AWS Service Quotas console.\u003c/p\u003e\n\u003cp\u003eCustomers with existing higher limits are automatically granted the same limit for both accounts and applications, with no action required. Organizations managing thousands of AWS accounts can now onboard applications without consuming account quota capacity.\u003c/p\u003e\n\u003cp\u003eThis update is available in all AWS Regions where IAM Identity Center is available.\u003c/p\u003e\n\u003cp\u003eTo learn more, see \u003ca href=\"https://docs.aws.amazon.com/singlesignon/latest/userguide/limits.html\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eQuotas for IAM Identity Center\u003c/a\u003e. Visit the \u003ca href=\"https://aws.amazon.com/iam/identity-center/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eIAM Identity Center product page\u003c/a\u003e to get started.\u003c/p\u003e\n\n\nCategory: TBD\nProducts: ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-19T17:56:12+0000)\n\n**Amazon MSK now offers AI Agent Skills to help developers operate MSK efficiently and accelerate migrations to MSK**\n\n\u003cp\u003eAmazon MSK now offers AI Agent Skills that give AI coding assistants expert, up-to-date guidance for operating Amazon MSK. The skills provide expert guidance for common operational tasks such as troubleshooting, sizing, configuring, monitoring, and migration from external Kafka clusters.\u003cbr\u003e\n\u003cbr\u003e\nTeams can leverage these skills to keep their clusters healthy and performant, and to migrate their external Kafka workloads to MSK Express to take advantage of up to 3 times more throughput per broker, scale up to 20 times faster, and reduced recovery time by 90 percent as compared to Standard brokers running Apache Kafka. The skills turn tasks that once required specialized knowledge into a guided experience developers can complete quickly, on their own.\u003cbr\u003e\n\u003cbr\u003e\nYou can use the MSK skills with your existing AI coding agent - Kiro, Claude Code, or Cursor. To get started, configure the \u003ca href=\"https://docs.aws.amazon.com/agent-toolkit/latest/userguide/what-is-agent-toolkit.html\"\u003eAgent Toolkit for AWS\u003c/a\u003e using the \u003ca href=\"https://docs.aws.amazon.com/agent-toolkit/latest/userguide/aws-cli.html\"\u003eAWS CLI\u003c/a\u003e, then ask your coding agent a question, such as \u003ci\u003e\u0026quot;What broker type and size should I use for my MSK cluster?\u0026quot; or \u003c/i\u003e\u0026quot;Is my Kafka cluster compatible with MSK Express?\u0026quot;\u003c/p\u003e\n\n\nCategory: analytics\nProducts: amazon-msk","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-22T20:48:18+0000)\n\n**Introducing self-service lifecycle management capabilities for AWS Outposts**\n\n\u003cp\u003eAWS Outposts now provides self-service capabilities for configuration, quoting, ordering, subscription management, renewal, and decommissioning directly from the AWS Management Console, CLI, and API. Previously, customers relied on AWS teams for managing their Outposts lifecycle, from evaluation through end of term.\u003cbr\u003e\n\u003cbr\u003e\nA new configuration and quoting tool generates real-time cost estimates across payment options and term lengths, and proactively surfaces account and regional constraints before order submission. Quotes are generated in seconds and can be converted to orders directly in the console, for both new deployments and capacity additions. Subscription details, including term dates and billing, are now available in the console and programmatically, eliminating the need to contact AWS for contract information. When your term approaches its end date, self-service workflows let you renew with a new term and payment option, or decommission your Outpost through a guided workflow that handles resource cleanup.\u003cbr\u003e\n\u003cbr\u003e\nThese features are available in all commercial AWS Regions that support AWS Outposts. To learn more, refer to the \u003ca href=\"https://aws.amazon.com/blogs/compute/simplify-aws-outposts-lifecycle-management/\"\u003eLaunch Blog\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: TBD\nProducts: ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T15:27:31+0000)\n\n**Announcing the general availability of a new AWS Local Zone in Hanoi, Vietnam  **\n\n\u003cp\u003eToday, AWS announces the general availability of a new Local Zone in Hanoi, Vietnam, bringing AWS infrastructure closer to end users. This new Local Zone is one of the first AWS Local Zones in the Asia Pacific with support for Amazon Simple Storage Service (Amazon S3) and Amazon Elastic Block Store (Amazon EBS) Local Snapshots,\u0026nbsp;enabling customers to meet data residency requirements by storing and backing up data locally.\u003c/p\u003e\n\u003cp\u003eAWS Local Zones are AWS infrastructure deployments that extend core services, such as compute, storage, networking, and other select services, closer to metropolitan areas worldwide. AWS Local Zones help you achieve single-digit millisecond latency for end-user workloads, meet data residency requirements, support AI/ML inference workloads, and accelerate migration and modernization of legacy applications to the cloud, all while maintaining consistent AWS APIs, tools, and services as AWS Regions.\u0026nbsp;AWS Local Zones are available in more than 30 metropolitan areas worldwide.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe Hanoi Local Zone supports Amazon Elastic Compute Cloud (Amazon EC2) with C7i, M7i, and R7i instances, Amazon S3 with the One Zone-Infrequent Access storage class, Amazon EBS with Local Snapshots and volume types gp3, gp2, io1, sc1, and st1, Amazon Elastic Container Service (Amazon ECS), Amazon Elastic Kubernetes Service (Amazon EKS), Amazon Virtual Private Cloud (Amazon VPC), AWS Direct Connect, and Application Load Balancer.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTo get started, enable the Hanoi Local Zone (ap-southeast-1-han-1a) from the \u003ca href=\"https://us-east-1.console.aws.amazon.com/ec2/home?region=us-east-1\u0026amp;refid=769a1a2b-8c19-4976-9c45-b6b1226c7d20#Settings:tab=zones;Category=local-zone\"\u003eRegions and Zones\u003c/a\u003e tab in the AWS Global View or by using the \u003ca href=\"https://docs.aws.amazon.com/AWSEC2/latest/APIReference/API_ModifyAvailabilityZoneGroup.html?refid=769a1a2b-8c19-4976-9c45-b6b1226c7d20\"\u003eModifyAvailabilityZoneGroup\u003c/a\u003e API. For pricing information, visit the \u003ca href=\"https://aws.amazon.com/about-aws/global-infrastructure/localzones/pricing/?nc=sn\u0026amp;loc=4\"\u003eAWS Local Zones pricing page.\u003c/a\u003e To learn more, visit the \u003ca href=\"https://aws.amazon.com/about-aws/global-infrastructure/localzones/\"\u003eAWS Local Zones overview page\u003c/a\u003e. \u0026nbsp;\u003c/p\u003e\n\n\nCategory: compute\nProducts: aws-local-zones","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-18T22:45:13+0000)\n\n**Amazon CloudWatch Synthetics now supports multilocation canaries**\n\n\u003cp\u003eToday, Amazon CloudWatch Synthetics announces support for multilocation canaries, allowing developers and site reliability engineers to run the same canary across multiple AWS Regions simultaneously from a single point of management. Previously, monitoring application availability from multiple geographic locations required creating and managing separate canaries in each Region, adding operational overhead and increasing the risk of configuration drift. With multilocation canaries, you create and manage a canary in one primary Region, and CloudWatch Synthetics automatically replicates it to the additional Regions you choose, consolidating all run data, metrics, and artifacts in the primary Region.\u003c/p\u003e\n\u003cp\u003eMultilocation canaries help you ensure consistent user experience worldwide, identify region-specific performance bottlenecks, and validate that third-party dependencies like CDNs and payment processors work across all locations. Replica canaries run independently, giving you resilient monitoring coverage across geographic locations. You can also configure alarms that activate only when issues are detected from multiple locations, increasing alert confidence and helping your team focus on real customer-impacting problems. Amazon CloudWatch Synthetics multilocation canaries are available in all AWS commercial Regions that support CloudWatch Synthetics. You can upgrade existing single-region canaries to multilocation by adding replica Regions without recreating them. For more information about regional availability, see the \u003ca href=\"https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/\"\u003eAWS Region table\u003c/a\u003e.\u003c/p\u003e\n\u003cp\u003eTo learn more about CloudWatch Synthetics, see \u003ca href=\"https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/CloudWatch_Synthetics_Canaries.html\"\u003eUsing synthetic monitoring\u003c/a\u003e in the Amazon CloudWatch User Guide. To get started, visit the \u003ca href=\"https://aws.amazon.com/cloudwatch/\"\u003eAmazon CloudWatch\u003c/a\u003e product page.\u003c/p\u003e\n\n\nCategory: management-and-governance\nProducts: amazon-cloudwatch","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-18T23:27:14+0000)\n\n**Amazon MSK Express brokers now support Intelligent Rebalancing on existing clusters**\n\n\u003cp\u003eAmazon MSK Provisioned clusters with Express brokers now support Intelligent Rebalancing on all existing clusters, at no additional cost. Previously available only on newly created clusters, Intelligent Rebalancing is now available on all MSK Provisioned clusters running Express brokers, making it effortless for customers to benefit from automatic partition balancing when scaling their Express-based clusters up or down.\u003c/p\u003e\n\u003cp\u003eIntelligent Rebalancing maximizes the capacity utilization of MSK Express-based clusters by optimally rebalancing Kafka resources for better performance, eliminating the need for customers to manage partitions themselves or via third-party tools. Intelligent Rebalancing performs these operations up to 180 times faster compared to Standard brokers. Clusters are continuously monitored for resource imbalance or overload based on intelligent Amazon MSK defaults to maximize cluster performance. When required, brokers are efficiently scaled without affecting cluster availability for clients to produce and consume data.\u003c/p\u003e\n\u003cp\u003eIntelligent Rebalancing is now available on all MSK Provisioned clusters with Express brokers in all AWS Regions where Express brokers are available. To learn more, see the \u003ca href=\"https://docs.aws.amazon.com/msk/latest/developerguide/intelligent-rebalancing.html\"\u003eAmazon MSK Developer Guide\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: analytics\nProducts: aws-govcloud-us, amazon-msk","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-18T18:22:48+0000)\n\n**Amazon ECS announces faster service auto scaling **\n\n\u003cp\u003eAmazon ECS service auto scaling now detects and responds to load changes faster with support for high resolution (20-second) metrics and metric publishing optimizations. In AWS benchmarking tests, time to trigger scale-out improved from 363 seconds to 86 seconds (76% faster, 4.2x), and total time to scale and provision new tasks improved from 386 seconds to 109 seconds (72% faster, 3.5x). Faster service auto scaling also enables you to reduce baseline capacity and lower compute costs while maintaining service reliability and performance as workload demand fluctuates.\u003cbr\u003e\n\u003cbr\u003e\n\u003ca href=\"https://docs.aws.amazon.com/AmazonECS/latest/developerguide/service-auto-scaling.html\"\u003eAmazon ECS service auto scaling\u003c/a\u003e automatically adjusts task counts to meet workload demand with comprehensive scaling policies, including predictive scaling for recurring traffic patterns, scheduled scaling for planned events, and target tracking to scale dynamically on real-time metrics. With today's launch, target tracking policies for CPU and memory utilization now support 20-second metric resolution, in addition to the default 60-second resolution, for faster scaling signal detection. To get started, use the AWS Console, CLI, CloudFormation, or AWS SDKs to configure 20-second resolution for CPU or memory utilization metrics when creating or updating your ECS service, then configure a target tracking policy selecting the corresponding high-resolution predefined metric.\u003cbr\u003e\n\u003cbr\u003e\nThis feature is available in all AWS commercial and AWS GovCloud (US) Regions, across all ECS compute options: AWS Fargate, Amazon ECS Managed Instances, and Amazon EC2. High-resolution metrics are subject to standard CloudWatch charges; for a pricing example, see \u003ca href=\"https://aws.amazon.com/cloudwatch/pricing/\"\u003eAmazon CloudWatch pricing\u003c/a\u003e. To learn more, see our \u003ca href=\"https://docs.aws.amazon.com/AmazonECS/latest/developerguide/target-tracking-faster-auto-scaling.html\"\u003edocumentation\u003c/a\u003e and the \u003ca href=\"https://aws.amazon.com/blogs/aws/amazon-ecs-introduces-new-high-resolution-metrics-for-faster-service-auto-scaling/\"\u003elaunch blog post\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: containers\nProducts: aws-fargate, auto-scaling, amazon-ecs","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-17T21:03:49+0000)\n\n**Amazon EC2 G7 instances are now generally available**\n\n\u003cp\u003eToday, AWS announces the general availability of Amazon Elastic Compute Cloud (Amazon EC2) G7 instances, accelerated by NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs. G7 instances deliver up to 4.6x AI inference performance and up to 2.1x graphics performance compared to G6.\u003c/p\u003e\n\u003cp\u003eYou can use G7 instances for AI inference workloads such as language translation, video and image analysis, speech recognition, and recommender systems. Additionally, G7 instances also accelerate graphics workloads such as creating and rendering real-time, cinematic-quality graphics, and game streaming, as well as data analytics workloads such as large-scale data processing pipelines. G7 instances feature up to 8 NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs with 32 GB of memory per GPU, custom Intel Xeon 6 processors, and up to 700 Gbps of Elastic Fabric Adapter (EFA) networking bandwidth.\u003c/p\u003e\n\u003cp\u003eYou can start using Amazon EC2 G7 instances today in two AWS Regions: US East (Ohio) and US West (Oregon). You can purchase G7 instances as On-Demand Instances, as part of Savings Plans, or Spot Instances.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTo get started, visit the \u003ca href=\"https://console.aws.amazon.com/\"\u003eAWS Management Console\u003c/a\u003e, \u003ca href=\"https://aws.amazon.com/cli/\"\u003eAWS Command Line Interface\u003c/a\u003e (CLI), and AWS SDKs. To learn more, visit this \u003ca href=\"https://aws.amazon.com/blogs/aws/announcing-amazon-ec2-g7-instances-accelerated-by-nvidia-rtx-pro-4500-blackwell-server-edition-gpus/\"\u003eblog post\u003c/a\u003e and the \u003ca href=\"https://aws.amazon.com/ec2/instance-types/g7/\"\u003eG7 instance page\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: amazon-ec2","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-18T18:42:59+0000)\n\n**Amazon MQ for RabbitMQ now supports private networking connectivity**\n\n\u003cp\u003eAmazon MQ for RabbitMQ now supports private networking, enabling your brokers to connect to private resources in your VPC without exposing those resources publicly.. This helps you meet your security and compliance requirements when your brokers need to reach private identity providers (such as LDAP and OAuth 2.0), other Amazon MQ for RabbitMQ brokers, or self-hosted RabbitMQ brokers. Previously, this connectivity for RabbitMQ Federation, Shovel, or authentication required\u0026nbsp;Network Load Balancer and NAT Gateway workarounds.\u003cbr\u003e\n\u003cbr\u003e\nAmazon MQ establishes this connectivity using Amazon VPC Lattice, AWS Resource Access Manager (AWS RAM), and AWS PrivateLink, and manages the underlying infrastructure on your behalf. To get started, create a VPC Lattice resource gateway, package your resource configurations into an AWS RAM resource share, and associate it with your broker.\u003cbr\u003e\n\u003cbr\u003e\nPrivate networking is available only for Amazon MQ for RabbitMQ brokers, in all \u003ca href=\"https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAWS Regions\u003c/a\u003e where \u003ca href=\"https://aws.amazon.com/vpc/lattice/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAmazon VPC Lattice\u003c/a\u003e is available. To learn more, see \u003ca href=\"https://docs.aws.amazon.com/amazon-mq/latest/developer-guide/private-networking.html\" target=\"_blank\" rel=\"noopener noreferrer\"\u003ePrivate networking\u003c/a\u003e in the Amazon MQ Developer Guide and the \u003ca href=\"https://aws.amazon.com/amazon-mq/pricing/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAmazon MQ pricing page\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: developer-tools\nProducts: amazon-mq","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-22T13:56:31+0000)\n\n**AWS Parallel Computing Service supports P6e-GB200 and P6e-GB300 UltraServers**\n\n\u003cp\u003eAWS Parallel Computing Service (PCS) now supports Amazon EC2 P6e-GB200 and P6e-GB300 UltraServer instances, enabling customers to run large-scale GPU workloads using the NVIDIA Blackwell architecture within Slurm-managed clusters. You can reserve UltraServers through EC2 Capacity Blocks for ML, associate them with a PCS compute node group via an EC2 launch template, and PCS automatically configures Slurm with the correct topology plugin.\u003cbr\u003e\n\u003cbr\u003e\nWith P6e-GB200 UltraServers, you can access up to 72 NVIDIA Blackwell GPUs within one NVLink domain to use 360 petaflops of FP8 compute (without sparsity) and 13.4 TB of total high bandwidth memory (HBM3e). P6e-GB300 UltraServers provide 1.5x GPU memory and 1.5x FP4 compute (without sparsity) compared to P6e-GB200.\u003cbr\u003e\n\u003cbr\u003e\nAWS PCS is a managed service that simplifies running and scaling HPC workloads on AWS using Slurm. You can build complete, elastic environments that integrate compute, storage, networking, and visualization tools, while the service handles cluster operations with managed updates and built-in observability features.\u003cbr\u003e\n\u003cbr\u003e\nYou can use P6e UltraServers with PCS in all AWS Regions where both PCS and EC2 Capacity Blocks for UltraServers are available. To learn more about P6e UltraServers, visit \u003ca href=\"https://aws.amazon.com/ec2/instance-types/p6/\"\u003eAmazon EC2 P6 instances\u003c/a\u003e. To reserve P6e UltraServers, contact your AWS sales representative. Read more about PCS support for P6e UltraServers in the \u003ca href=\"https://docs.aws.amazon.com/pcs/latest/userguide\"\u003ePCS User Guide\u003c/a\u003e and make sure to set the right \u003ca href=\"https://docs.aws.amazon.com/pcs/latest/userguide/security-min-permissions.html#security-min-permissions_capacity-blocks\"\u003ePermissions\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: compute\nProducts: aws-parallel-computing-service","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-18T19:02:32+0000)\n\n**Nested virtualization is now available on additional Intel platforms and US Gov Cloud regions**\n\n\u003cp\u003eStarting today, Nested virtualization is now available on additional Intel platforms and additional Regions. Nested virtualization is now available on C7i,R7i, M7i, C8id,R8id, M8id, C7i-flex, M7i-flex, I7i, C8i-flex,R8i-flex, M8i-flex,and X8i, in addition to already available support on C8i, M8i and R8i instances. This capability is also now available in US GovCloud (US-East) and US GovCloud (US-West), in addition to existing support in all commercial regions.\u003cbr\u003e\nWith nested virtualization capabilities, customers can create nested environments by running KVM or Hyper-V on virtual EC2 instances. Customers can leverage this capability for use cases such as running emulators for mobile applications, simulating in-vehicle hardware for automobiles, and running Windows Subsystem for Linux on Windows workstations. To learn more see \u003ca href=\"https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/amazon-ec2-nested-virtualization.html\"\u003edocumentation\u003c/a\u003e .\u003c/p\u003e\n\n\nCategory: compute\nProducts: amazon-ec2","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-15T19:49:47+0000)\n\n**Amazon Connect Customer launches the ability to interrupt an agent with an urgent contact**\n\n\u003cp\u003eAmazon Connect Customer now supports the ability to interrupt an agent with a contact, overriding their usual routing configuration in case of urgent or time-sensitive work. For example, an agent may be waiting for a time-sensitive callback on their personal extension, while taking customer service calls in the meantime. When that urgent call comes in, it can now ring the agent even if the agent is currently already on another call, so the agent can decide whether to put the first caller on hold to pick up the callback as well.\u003cbr\u003e\n\u003cbr\u003e\nYou can also use this feature to directly assign certain contacts to a specific agent even though that agent has set themselves to a custom status where they normally could not be offered queued contacts. For example, you may want to ensure that a specific agent cannot take customer service calls while in “Back Office Work” but still allow calls to their personal extension to ring through, improving efficiency for urgent contacts.\u003cbr\u003e\n\u003cbr\u003e\nThis feature is available in all \u003ca href=\"https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/\"\u003eAWS regions\u003c/a\u003e where Amazon Connect Customer is offered. To learn more about this feature, see the \u003ca href=\"https://docs.aws.amazon.com/connect/latest/adminguide/interrupt-agent.html\"\u003e\u003cu\u003eAmazon Connect Customer Administrator Guide\u003c/u\u003e\u003c/a\u003e. To learn more about Amazon Connect Customer, the AWS cloud-based contact center, please visit the\u003ca href=\"https://aws.amazon.com/connect/\"\u003e \u003c/a\u003e\u003ca href=\"https://aws.amazon.com/connect/\"\u003e\u003cu\u003eAmazon Connect Customer website\u003c/u\u003e\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: applications\nProducts: amazon-connect","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-18T17:36:59+0000)\n\n**all-MiniLM-L12-v2 for semantic search and sentence similarity is now available in Amazon SageMaker JumpStart**\n\n\u003cp\u003eToday, AWS announced the availability of all-MiniLM-L12-v2 in Amazon SageMaker JumpStart, expanding the portfolio of models available to AWS customers. This model from Sentence Transformers maps sentences and paragraphs to a 384-dimensional dense vector space, enabling customers to build high-quality semantic search, text clustering, and sentence similarity applications on AWS infrastructure.\u003c/p\u003e\n\u003cp\u003eall-MiniLM-L12-v2 excels at encoding sentences and short paragraphs into dense vector representations that capture semantic meaning, making it ideal for information retrieval, semantic search systems, document clustering, duplicate detection, and paraphrase identification. Its compact architecture delivers fast inference while maintaining strong embedding quality, well suited for production workloads that require efficient text representations at scale.\u003c/p\u003e\n\u003cp\u003eWith SageMaker JumpStart, customers can deploy this model with just a few clicks to address their specific AI use cases. To get started with this model, navigate to the Models section of SageMaker Studio or use the SageMaker Python SDK to deploy the model to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the\u0026nbsp;\u003ca href=\"https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html\"\u003eAmazon SageMaker JumpStart documentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: aiml, amazon-sagemaker, amazon-sagemaker-jumpstart","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-02T18:57:10+0000)\n\n**AWS Compute Optimizer enhances EBS volume recommendations with additional performance metrics **\n\n\u003cp\u003eAWS Compute Optimizer now includes improved visibility into IOPS and throughput spikes when deliverings Amazon EBS volume rightsizing recommendations. Compute Optimizer analyzes two additional Amazon CloudWatch metrics, VolumeIOPSExceededCheck and VolumeThroughputExceededCheck, which report whether your workload consistently attempted to drive IOPS or throughput beyond your volume's provisioned performance in any given minute. By factoring in these signals, Compute Optimizer helps you make rightsizing decisions to balance cost with performance for workloads that experience bursts of high IOPS or throughput.\u003c/p\u003e\n\u003cp\u003eThis enhancement is available in all AWS Regions where AWS Compute Optimizer is available, except the AWS GovCloud (US) Regions, and the China Regions. The underlying CloudWatch metrics are available at no additional charge for all EBS volumes attached to Nitro-based EC2 instances, excluding standard and Multi-Attach enabled volumes. To get started, go to AWS Compute Optimizer in the AWS Management Console. To learn more, visit the AWS Compute Optimizer \u003ca href=\"https://docs.aws.amazon.com/compute-optimizer/latest/ug/view-ebs-recommendations.html\"\u003eUser Guide\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: cost-management\nProducts: aws-compute-optimizer","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-18T17:36:58+0000)\n\n**Ministral-3-14B-Instruct for multimodal reasoning and agentic AI is now available in Amazon SageMaker JumpStart**\n\n\u003cp\u003eToday, AWS announced the availability of Ministral-3-14B-Instruct-2512 in Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. This model from Mistral AI delivers frontier-class multimodal capabilities in a compact 14B-parameter architecture optimized for edge deployment, enabling customers to build advanced AI assistants, agentic systems, and vision-enabled applications on AWS infrastructure.\u003c/p\u003e\n\u003cp\u003eMinistral-3-14B-Instruct excels at analyzing images and providing insights based on visual content in addition to text, agentic capabilities with native function calling and JSON output, and multilingual understanding across dozens of languages including English, French, Spanish, German, Chinese, Japanese, Korean, and Arabic.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eWith SageMaker JumpStart, customers can deploy this model with just a few clicks to address their specific AI use cases. To get started with this model, navigate to the Models section of SageMaker Studio or use the SageMaker Python SDK to deploy the model to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the \u003ca href=\"https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html\"\u003eAmazon SageMaker JumpStart documentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: amazon-sagemaker, aiml, amazon-sagemaker-jumpstart","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-12T22:39:26+0000)\n\n**Amazon EKS now supports customer-routed control plane egress**\n\n\u003cp\u003eToday, \u003ca href=\"https://aws.amazon.com/eks/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAmazon Elastic Kubernetes Service\u003c/a\u003e (Amazon EKS) introduces customer-routed control plane egress, a capability that lets you route outbound Kubernetes API server traffic through your own Amazon VPC. This includes admission webhook callbacks, OpenID Connect (OIDC) provider lookups, and aggregate API server requests. With customer-routed control plane egress, this traffic flows through your VPC, where you control the routing, security groups, and egress path.\u003cbr\u003e\n\u003cbr\u003e\nOrganizations with data perimeter requirements, compliance mandates, or private network infrastructure can use customer-routed control plane egress to reach private OIDC providers and webhook servers that are accessible only within their VPC, and control how that traffic routes through their network. To get started, set controlPlaneEgressMode to CUSTOMER_ROUTED when creating a new cluster or updating an existing cluster. To enforce this configuration organization-wide, use the eks:controlPlaneEgressMode IAM condition key with AWS Organizations Service Control Policies.\u003cbr\u003e\n\u003cbr\u003e\nCustomer-routed control plane egress is available at no additional cost in all AWS Regions where Amazon EKS is available. To learn more, see \u003ca href=\"https://docs.aws.amazon.com/eks/latest/userguide/control-plane-egress.html\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eConfigure control plane egress routing\u003c/a\u003e in the \u003ci\u003eAmazon EKS User Guide\u003c/i\u003e.\u003c/p\u003e\n\n\nCategory: containers\nProducts: amazon-eks","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-18T19:34:36+0000)\n\n**Amazon SageMaker AI Announces New observability capability For Inference Endpoints     **\n\n\u003cp\u003eAmazon SageMaker AI's new observability capability allows customers to operate production generative AI inference workloads with confidence by providing comprehensive visibility into token performance, GPU health, inference component placement, and autoscaling behavior. It takes away the manual work of searching CloudWatch for per-endpoint metrics, correlating latency spikes with GPU saturation or KV cache exhaustion and diagnosing why scaling operations are slow. This capability tracks inference performance metrics in real-time, including Time to First Token, inter-token latency, queue depth, and tokens per second, and surfaces them alongside infrastructure health so customers can identify and resolve issues in minutes rather than hours.\u003c/p\u003e\n\u003cp\u003eSageMaker AI detailed observability transforms how customers monitor and optimize their inference fleet. The new pre-built SageMaker AI Insights dashboard in Amazon CloudWatch gives customers token latency, GPU utilization, inference component copy counts, scaling events, and cold start breakdowns in a single view with OpenTelemetry native metrics published automatically, no instrumentation required. This allows teams to quickly diagnose TTFT degradation, verify availability zone compliance, and tune autoscaling policies. Customers who have standardized on observability tools like Grafana can connect directly using the regional PromQL endpoint and import a pre-configured dashboard template. This capability helps customers self-serve operational issues and maximize the performance of their AI investments.\u003c/p\u003e\n\u003cp\u003eSageMaker AI Inference observability is available in the following AWS Regions: US East (N. Virginia), US East (Ohio), US West (Oregon), US West (N. California), Canada (Central), South America (São Paulo), Europe (Ireland), Europe (Frankfurt), Europe (London), Europe (Stockholm), Europe (Zurich), Asia Pacific (Mumbai), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Asia Pacific (Seoul), and Asia Pacific (Jakarta). To learn more, visit the \u003ca href=\"https://docs.aws.amazon.com/sagemaker/latest/dg/monitoring-cloudwatch-detailed-observability.html\"\u003eDocumentation\u003c/a\u003e and \u003ca href=\"https://aws.amazon.com/sagemaker/ai/?trk=df5b8c0e-2f56-49fa-a37d-691eba3e8954\u0026amp;sc_channel=ps\u0026amp;trk=c5e59169-d233-4eef-b6e2-e3e751bfb3f2\u0026amp;ef_id=:G:s\u0026amp;s_kwcid=AL!4422!3!!e!!o!!amazon%20sagemaker%20ai!487441853!1151190521794397\u0026amp;msclkid=9745f631dad319a20f8e9c02eb1bda85\"\u003eAmazon SageMaker AI\u003c/a\u003e webpage.\u003c/p\u003e\n\n\nCategory: business-productivity\nProducts: amazon-sagemaker","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T16:30:31+0000)\n\n**Amazon SNS now supports sending SMS in the Asia Pacific (Seoul) Region**\n\n\u003cp\u003eCustomers that use \u003ca href=\"https://aws.amazon.com/sns/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAmazon Simple Notification Service (Amazon SNS)\u003c/a\u003e in the Asia Pacific (Seoul) Region can now send text messages (SMS) to subscribers in more than 200 countries and territories.\u003c/p\u003e\n\u003cp\u003eAmazon SNS is a fully managed pub/sub messaging service that enables message delivery to multiple endpoints including AWS Lambda, Amazon SQS, Amazon Data Firehose, mobile devices, and email. With this launch, customers using SNS in the\u0026nbsp;Asia Pacific (Seoul) Region can subscribe phone numbers to SNS topics and broadcast SMS messages via \u003ca href=\"https://aws.amazon.com/end-user-messaging/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAWS End User Messaging\u003c/a\u003e.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTo learn more about sending SMS messages with SNS, visit \u003ca href=\"https://docs.aws.amazon.com/sns/latest/dg/sns-mobile-phone-number-as-subscriber.html\"\u003eMobile text messaging with Amazon SNS\u003c/a\u003e.\u0026nbsp;For the list of supported countries and regions, visit \u003ca href=\"https://docs.aws.amazon.com/sns/latest/dg/sns-supported-regions-countries.html\"\u003eSupported countries and regions\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: serverless\nProducts: amazon-simple-notification-service","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-17T15:46:45+0000)\n\n**Amazon GameLift Servers adds new container fleet improvements**\n\n\u003cp\u003eAmazon GameLift Servers now supports two significant container fleet improvements that enhance flexibility and inter-container communication for game server deployments. These new capabilities address common challenges faced by game developers using containerized architectures, providing greater control over container permissions and enabling seamless discovery of co-located containers on the same instance.\u003c/p\u003e\n\u003cp\u003eYou can now customize Linux capabilities for containers in your container group definitions, giving you finer control beyond Docker's default capability set. This is particularly valuable for game servers requiring specialized capabilities such as NET_RAW for custom networking protocols or SYS_PTRACE for attaching debuggers and profiling tools. Additionally, game servers can now call the new ListContainersNetworkInfo() server SDK action to retrieve comprehensive network information, including container name, ID, local IP address, and container group type for all containers running on the same instance. This enables automatic service discovery and simplified communication between game servers and auxiliary services like metrics collectors, logging agents, or caching systems.\u003c/p\u003e\n\u003cp\u003eThese improvements are available through the Amazon GameLift Servers console, AWS CLI, AWS SDK, and AWS CloudFormation. The ListContainersNetworkInfo() action is supported in server SDK 5.x for Go, C++, and C#, as well as in plugins for Unreal Engine and Unity. Both features are available in all AWS regions where Amazon GameLift Servers is supported, except China. To learn more, visit the Amazon GameLift Servers \u003ca href=\"https://docs.aws.amazon.com/gameliftservers/latest/developerguide/release-notes.html\" target=\"_blank\" rel=\"noopener noreferrer\"\u003edocumentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: game-development\nProducts: amazon-gamelift","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-18T19:06:26+0000)\n\n**Amazon WorkSpaces Personal Supports Ubuntu 24.04**\n\n\u003cp\u003eAWS announces availability of Ubuntu 24.04 LTS bundles for Amazon WorkSpaces Personal in the AWS China (Ningxia) Region, operated by NWCD. With this bundle, customers in China can launch Ubuntu WorkSpaces and take advantage of updated Linux packages, toolchains, and security improvements only available in Ubuntu 24.04.\u003cbr\u003e\n\u003cbr\u003e\nThe new Ubuntu 24.04 option brings access to the latest software ecosystem, an improved security posture, and an extended support lifecycle. This new bundle also provides a migration path for customers running older Amazon Linux 2 WorkSpaces who want to stay current with upstream packages and receive the longest available maintenance window from Canonical.\u003cbr\u003e\n\u003cbr\u003e\nYou can get started using the managed Ubuntu 24.04 WorkSpaces bundle by selecting it when creating a new Linux WorkSpace. This new bundle is available in the AWS China (Ningxia) Region. For pricing information, visit the \u003ca href=\"https://www.amazonaws.cn/en/workspaces/pricing/\" target=\"_blank\"\u003eAmazon WorkSpaces pricing page\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: business-productivity\nProducts: amazon-workspaces","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-18T21:03:41+0000)\n\n**Amazon RDS for SQL Server increases the maximum size and provisioned performance of General Purpose (gp3) volumes**\n\n\u003cp\u003e\u003ca href=\"https://aws.amazon.com/rds/sqlserver/\" target=\"_blank\"\u003eAmazon Relational Database Service (Amazon RDS) for SQL Server\u003c/a\u003e now supports higher volume-level limits for General Purpose (gp3) storage. With this update, each gp3 volume can scale up to 64 TiB in size (4X the previous 16 TiB limit), up to 80,000 IOPS (5X the previous 16,000 IOPS limit), and up to 2,000 MiB/s throughput (2X the previous 1,000 MiB/s limit).\u003cbr\u003e\n\u003cbr\u003e\nWith these improvements, customers can now run larger Microsoft SQL Server databases on Amazon RDS. Workloads with demanding I/O requirements such as high-throughput OLTP systems and large-scale analytical workloads can take advantage of higher IOPS and throughput on a single volume with simplified storage management, and get better performance for mission-critical SQL Server workloads. Additionally, you can configure \u003ca href=\"https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/USER_PIOPS.ModifyingExisting.AdditionalVolumes.html\" target=\"_blank\"\u003eadditional storage volumes\u003c/a\u003e to add up to three gp3 or io2 volumes per DB instance, increasing total capacity up to 256 TiB per instance. There is no change to pricing - customers pay for storage and any additional IOPS and throughput they provision beyond the baseline default.\u003cbr\u003e\n\u003cbr\u003e\nFor more information, refer to the \u003ca href=\"https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/Appendix.SQLServer.CommonDBATasks.DatabaseStorage.html\" target=\"_blank\"\u003eAmazon RDS for SQL Server User Guide\u003c/a\u003e. See \u003ca href=\"https://aws.amazon.com/rds/sqlserver/pricing/\" target=\"_blank\"\u003eAmazon RDS for SQL Server Pricing\u003c/a\u003e for pricing details and regional availability.\u0026nbsp;\u003c/p\u003e\n\n\nCategory: databases\nProducts: aws-govcloud-us, amazon-rds-for-sql-server","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-17T19:11:05+0000)\n\n**AWS Glue Interactive Sessions now support Spark Connect for interactive workloads**\n\n\u003cp\u003eAWS Glue Interactive Sessions now support Apache Spark Connect, using which you can now develop and run Apache Spark applications from your preferred environment, including managed notebooks in Amazon SageMaker Unified Studio, or your preferred notebook environments and IDEs like Jupyter, Visual Studio Code, while running them on AWS Glue's serverless infrastructure without managing clusters.\u003cbr\u003e\n\u003cbr\u003e\nWith Spark Connect, you submit Spark jobs to AWS Glue Interactive Sessions using a thin client architecture that decouples your client application from the Spark execution environment. This unlocks workflows like ad hoc data exploration, iterative step-by-step debugging, and incremental PySpark job development before deploying to production, all from the tools you already use. Spark Connect also simplifies upgrades and improves stability by isolating client dependencies from the server-side Spark runtime. For observability, you get real-time session monitoring via the Spark UI, history tracking through the Spark History Server, and session management using the AWS Glue API, CLI, or SDK.\u003cbr\u003e\n\u003cbr\u003e\nAWS Glue Interactive Sessions with Spark Connect is available in Asia Pacific (Mumbai, Seoul, Singapore, Sydney, Tokyo), Canada (Central), Europe (Frankfurt, Ireland, London, Paris, Stockholm), South America (São Paulo), US East (Ohio, N. Virginia), and US West (Oregon).\u003cbr\u003e\n\u003cbr\u003e\nTo get started, connect to Glue Interactive Sessions using Spark Connect from notebooks in \u003ca href=\"https://docs.aws.amazon.com/sagemaker-unified-studio/latest/userguide/notebooks-spark-connect.html\"\u003eAmazon SageMaker Unified Studio\u003c/a\u003e, your favorite IDE with a Python interpreter, or the AWS API, SDK, and CLI. To learn more, visit the \u003ca href=\"https://docs.aws.amazon.com/glue/latest/dg/interactive-sessions-spark-connect.html\"\u003eAWS Glue Interactive Sessions documentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: analytics\nProducts: aws-glue, amazon-sagemaker","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-15T15:46:58+0000)\n\n**AWS HealthOmics now streams workflow engine logs to Amazon CloudWatch in real time**\n\n\u003cp\u003eAWS HealthOmics now streams workflow engine logs to Amazon CloudWatch in real time, enabling customers to monitor workflow execution progress as it happens. \u003ca href=\"https://aws.amazon.com/healthomics/\"\u003eAWS HealthOmics\u003c/a\u003e is a HIPAA-eligible service that helps healthcare and life sciences customers accelerate scientific breakthroughs at scale with fully managed bioinformatics workflows.\u003c/p\u003e\n\u003cp\u003eReal-time engine log streaming accelerates iterative workflow development and debugging by giving researchers, bioinformaticians, and workflow developers immediate access to execution details during a run. The streamed engine logs provide visibility into workflow orchestration events, task scheduling details, import/export activity, and full stack traces on errors — all routed into the engine log stream in real time. Customers can set up CloudWatch alarms on log patterns to detect anomalies early, build dashboards for ongoing monitoring, and integrate with existing observability tooling.\u003c/p\u003e\n\u003cp\u003eReal-time engine log streaming is now available for Nextflow, WDL, and CWL workflow runs in all AWS HealthOmics regions: US East (N. Virginia), US West (Oregon), Europe (Frankfurt, Ireland, London), Israel (Tel Aviv), and Asia Pacific (Singapore, Seoul). To learn more, visit the \u003ca href=\"https://docs.aws.amazon.com/omics/latest/dev/monitoring-cloudwatch-logs.html\"\u003eMonitoring HealthOmics with CloudWatch Logs documentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-15T20:52:52+0000)\n\n**AWS DevOps Agent adds release management capability (preview)**\n\n\u003cp\u003eAWS DevOps Agent now offers a release management capability in preview, reviewing code changes for release readiness and running autonomous release testing to help you ship code to production safely and with confidence. With this addition, AWS DevOps Agent now works across both delivery and operations. It accelerates and validates the deployment of code changes, then keeps your applications running optimally across AWS, multicloud, and on-prem environments, so your team ships faster, reduces MTTR, and achieves operational excellence.\u003cbr\u003e\n\u003cbr\u003e\nWith release readiness review, AWS DevOps Agent evaluates code changes for production safety during code generation by checking for drift from your internal standards, dependency impacts, and access controls. It maps cross-repository dependencies to surface breaking changes before commit and uses deterministic proofs to review that infrastructure changes do not drift from AWS Well-Architected best practices. With release testing, AWS DevOps Agent generates and runs test plans for web and API-based applications in customer-provisioned environments, catching regressions, UX issues, and integration failures a human reviewer may miss.\u003cbr\u003e\n\u003cbr\u003e\nTo get started with the preview, connect your code repositories and pipelines in your AWS DevOps Agent space. AWS DevOps Agent release management is available in the US East (N. Virginia) Region and at no additional cost during the preview period. For the list of AWS Regions where AWS DevOps Agent production operations is available, see the \u003ca href=\"https://docs.aws.amazon.com/devopsagent/latest/userguide/about-aws-devops-agent-supported-regions.html\"\u003esupported Regions table\u003c/a\u003e. For pricing of production operations features, which are generally available, see \u003ca href=\"https://aws.amazon.com/devops-agent/pricing/\"\u003eAWS DevOps Agent pricing\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-17T03:34:49+0000)\n\n**Amazon RDS for PostgreSQL, MySQL, and MariaDB now supports M9g database instances**\n\n\u003cp\u003eAWS Graviton5-based M9g database (DB) instances are now generally available for \u003ca href=\"https://aws.amazon.com/rds/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAmazon Relational Database Service (RDS)\u003c/a\u003e for PostgreSQL, MySQL, and MariaDB. Graviton5-based instances provide up to a 30% performance improvement and up to a 23% price/performance improvement for on-demand pricing over Graviton4-based instances of equivalent sizes on Amazon RDS open source databases, depending on database engine, version, and workload.\u003cbr\u003e\n\u003cbr\u003e\nAWS Graviton5 processors are the latest generation of custom-designed AWS Graviton processors built on the AWS Nitro System. M9g DB instances are available with new 24xlarge and 48xlarge sizes. With these new sizes, M9g DB instances offer up to 192 vCPU, up to 100Gbps enhanced networking bandwidth, and up to 72Gbps of bandwidth to the Amazon Elastic Block Store (Amazon EBS).\u003cbr\u003e\n\u003cbr\u003e\nThese instances are now available in the US East (N. Virginia, Ohio), US West (Oregon), and Europe (Frankfurt) Regions. For complete information on pricing and regional availability, please refer to the Amazon RDS \u003ca href=\"https://aws.amazon.com/rds/pricing/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003epricing page\u003c/a\u003e. For information on specific engine versions that support these DB instance types, please see the \u003ca href=\"https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/Concepts.DBInstanceClass.Support.html\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAmazon RDS documentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: databases\nProducts: amazon-rds","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-17T16:54:09+0000)\n\n**Amazon Aurora and RDS for MySQL expand Extended Support for MySQL 5.7 through June 2029**\n\n\u003cp\u003eAmazon Aurora MySQL-Compatible Edition and Amazon Relational Database Service (RDS) for MySQL now offer \u003ca href=\"https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/extended-support.html\"\u003eAmazon RDS Extended Support\u003c/a\u003e for MySQL 5.7 through June 30, 2029, from the previous end date of February 28, 2027. This applies to Aurora MySQL version 2 (with MySQL 5.7 compatibility) and RDS for MySQL version 5.7, giving customers additional time to plan and complete their upgrades to a supported major version while continuing to receive critical security patches and bug fixes.\u003cbr\u003e\n\u003cbr\u003e\nRDS Extended Support delivers security patches for critical and high CVEs, bug fixes for critical operational issues, and access to AWS Support within the standard Aurora and RDS SLAs. There is no price increase with this extension, and customers using RDS Extended Support for MySQL 5.7 will continue to pay Year 3 pricing through June 30, 2029. For pricing details, see \u003ca href=\"https://aws.amazon.com/rds/aurora/pricing/\"\u003eAurora pricing\u003c/a\u003e and \u003ca href=\"https://aws.amazon.com/rds/mysql/pricing/\"\u003eRDS for MySQL pricing\u003c/a\u003e.\u003cbr\u003e\n\u003cbr\u003e\nWe recommend upgrading to MySQL 8.0 or MySQL 8.4 compatible versions to benefit from the latest database features, performance improvements, and security enhancements. You can upgrade using \u003ca href=\"https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/blue-green-deployments.html\"\u003eAmazon RDS Blue/Green Deployments\u003c/a\u003e, in-place upgrade, or snapshot restore. To learn more, see the \u003ca href=\"https://docs.aws.amazon.com/AmazonRDS/latest/AuroraUserGuide/AuroraMySQL.Updates.MajorVersionUpgrade.html\"\u003eAurora MySQL\u003c/a\u003e and \u003ca href=\"https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/USER_UpgradeDBInstance.MySQL.html\"\u003eRDS for MySQL\u003c/a\u003e user guides. This extension is available in all AWS Regions where Aurora MySQL and RDS for MySQL are available.\u003cbr\u003e\n\u003cbr\u003e\nAmazon Aurora is designed for high performance and availability at global scale with full MySQL and PostgreSQL compatibility. Amazon RDS for MySQL, PostgreSQL, and MariaDB make it simple to set up, operate, and scale open source deployments in the cloud. Visit the getting started pages for \u003ca href=\"https://aws.amazon.com/rds/aurora/\"\u003eAurora\u003c/a\u003e and \u003ca href=\"https://aws.amazon.com/rds/\"\u003eRDS\u003c/a\u003e to begin.\u003c/p\u003e\n\n\nCategory: databases\nProducts: amazon-rds","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T06:43:16+0000)\n\n**AWS Outposts racks now support bmn-cx3a instances, the first AMD-based instances with accelerated networking on Outposts**\n\n\u003cp\u003eAWS announces the availability of bmn-cx3a instances on second-generation AWS Outposts racks. Bmn-cx3a instances feature 5th Gen AMD EPYC processors with a maximum frequency of 4.1 GHz and NVIDIA ConnectX-7 (CX7) network interface cards, delivering up to 800 Gbps of bare-metal accelerated network bandwidth operating at near line rate.\u003cbr\u003e\n\u003cbr\u003e\nBmn-cx3a instances offer up to 256 cores and 1.5 TB of memory across two sizes, bmn-cx3a.metal-32xl and bmn-cx3a.metal-64xl, with 2x 8 TB NVMe SSD storage. With native Layer 2 (L2) multicast and hardware Precision Time Protocol (PTP) support, bmn-cx3a instances are designed for high-throughput workloads such as real-time market data ingestion and distribution, market and risk analytics, telecom 5G core network applications, and media distribution.\u003cbr\u003e\n\u003cbr\u003e\nBmn-cx3a instances on AWS Outposts racks are available in all countries and regions where second-generation Outposts racks are supported. For a current list of AWS Regions and countries/territories where Outposts racks are supported, check out the \u003ca href=\"https://aws.amazon.com/outposts/rack/faqs/#product-faqs%23in-which-countries-and-territories-is-outposts-rack-available-trigger\"\u003eOutposts rack FAQs page\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: compute\nProducts: amazon-ec2","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-17T20:48:10+0000)\n\n**Amazon Quick announces autonomous agents, multi-dataset analytics, and redesigned activity feed**\n\n\u003cp\u003eToday, AWS announces multiple new features for Amazon Quick, including autonomous agents, multi-dataset analytics capabilities, and a redesigned activity feed. Amazon Quick is the AI assistant that connects to popular business applications and learns user workflows. These new capabilities enable Quick to handle recurring tasks continuously while providing unified analytics across multiple data sources.\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\nWith autonomous agents, users can describe tasks in natural language and set granular autonomy levels—from step-by-step approval to broad goal-based execution. Agents operate continuously to automate workflows like following up on stalled deals, summarizing regulatory changes, and processing purchase orders, eliminating manual repetitive work and notification overload. The new multi-dataset analytics feature enables users to query across data sources including Snowflake and relational databases using natural language, without requiring technical data preparation or pre-joining datasets. Quick inherits semantic intelligence from existing data catalogs such as AWS Glue, Databricks Unity Catalog, and Collibra, while enforcing security through identity propagation that respects existing permissions.\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\nThe redesigned activity feed provides a personalized, conversational interface where users can prioritize updates using thumbs up/down feedback, reply to emails and Slack messages, and approve requests directly—all without switching between applications. Users can also share Quick applications as public websites, extending collaboration capabilities beyond their organization.\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\nTo learn more about these new Amazon Quick capabilities, including autonomous agents, multi-dataset analytics., and redesigned activity feed, read the \u003ca href=\"https://aws.amazon.com/blogs/machine-learning/get-back-hours-every-day-with-amazon-quicks-new-autonomous-agents/\" target=\"_blank\"\u003elaunch blog\u003c/a\u003e. You can create an account for free and get started in minutes at \u003ca href=\"http://aws.com/quick\" target=\"_blank\"\u003eaws.com/quick\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: amazon-quick-suite","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T22:20:43+0000)\n\n**Amazon Bedrock AgentCore introduces new optimization capabilities to continuously improve agents in production**\n\n\u003cp\u003eToday, AWS announces new optimization capabilities in AgentCore that turn production traces into continuous improvement for agents. The most dangerous agent failures are not the ones that throw errors. They are the silent ones that look fine on dashboards. These failures produce no error signal and often surface through customer complaints weeks later. AgentCore closes that gap with a loop to understand what agents are doing, generate fixes grounded in data, and prove they work.\u003cbr\u003e\n\u003cbr\u003e\nTo understand agent behavior, AgentCore surfaces failure, intent, and trajectory insights across hundreds of sessions, revealing patterns no dashboard or one-at-a-time trace review would catch. Failure insights discover recurring failure patterns, including silent behavioral failures, explain the root cause of each, and rank them by how widespread they are, so teams can fix the problems hurting the most users first. Intent insights cluster requests by what users were trying to do, and trajectory insights group the paths agents take through a task, surfacing common patterns and outliers. Customers can enable continuous monitoring or run a targeted investigation in minutes. To fix issues with confidence, recommendations analyze traces and evaluation outputs to suggest specific improvements to system prompts and tool descriptions, grounded in how the agent actually behaves. Each recommendation includes a clear rationale tied to observed failures and comes ready to validate, not a generic suggestion but a targeted change derived from production data. Before a change reaches users, batch evaluation tests recommendations against a defined test dataset and reports aggregate scores across multiple evaluators, catching regressions early. Customers define what \u0026quot;good\u0026quot; looks like, and batch evaluation measures each candidate change against that bar at scale. A/B testing then confirms improvements hold under real conditions, running a controlled comparison between agent versions by splitting live production traffic and measuring outcomes side by side. This provides statistical evidence that a change actually works in production, not just on test data, before customers commit to rolling it out fleet-wide. These capabilities work regardless of where agents run: on AgentCore’s runtime, AWS Lambda, Amazon EKS, or non-AWS environments.\u003cbr\u003e\n\u003cbr\u003e\nFailure, intent, and trajectory insights are available in preview today in \u003ca href=\"https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agentcore-regions.html\"\u003e13 AWS Regions.\u003c/a\u003e Batch evaluations, recommendations, and A/B tests are generally available today in \u003ca href=\"https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agentcore-regions.html\"\u003e14 AWS Regions\u003c/a\u003e. To learn more, visit \u003ca href=\"https://aws.amazon.com/bedrock/agentcore/\"\u003eAmazon Bedrock AgentCore\u003c/a\u003e or explore the \u003ca href=\"https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/optimization.html\"\u003edocumentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: amazon-bedrock","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T22:04:17+0000)\n\n**Amazon Bedrock AgentCore now supports Bedrock Guardrails in policy**\n\n\u003cp\u003eToday, AWS announces that Amazon Bedrock AgentCore now supports Bedrock Guardrails in policy, giving enterprises deeper safety and security controls as they scale AI agents in production. AgentCore policy is an authorization capability within Amazon Bedrock AgentCore that controls which actions AI agents are authorized to take. Guardrails give enterprises defenses against the top security and safety risks with AI agent workloads, including prompt injection attacks and sensitive data exposure.\u003cbr\u003e\n\u003cbr\u003e\nGuardrails can evaluate the outputs of every authorized agent action and inputs of every call to a gateway target (tools, agents, and models) in real-time, helping detect and block prompt injection attacks, harmful content, and sensitive information exposure before they reach downstream systems. Guardrail results are evaluated in policy at the AgentCore gateway perimeter, outside the agent's code, ensuring consistent enforcement regardless of agent autonomy. All policy evaluations are logged via AgentCore observability for optimization and auditing purposes.\u003cbr\u003e\n\u003cbr\u003e\nAgentCore policy works with existing AgentCore gateway deployments and requires no new infrastructure. Customers author policies through natural language or policy-as-code, with consumption-based pricing for policy evaluations.\u003cbr\u003e\n\u003cbr\u003e\nBedrock Guardrails are available in policy in US East (N. Virginia), Europe (London), Europe (Stockholm), Asia Pacific (Sydney), and Asia Pacific (Tokyo). To learn more, visit \u003ca href=\"https://aws.amazon.com/bedrock/agentcore/\"\u003eAmazon Bedrock AgentCore\u003c/a\u003e or explore the \u003ca href=\"https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/policy.html\"\u003edocumentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: amazon-bedrock","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T22:11:45+0000)\n\n**AgentCore harness is now generally available**\n\n\u003cp\u003eToday, AWS announces the general availability of the managed agent harness in Amazon Bedrock AgentCore, taking teams from idea to working agents in minutes. An agent is more than a model. If the model is the brain, the harness is the body: everything the brain needs to get work done. It runs the orchestration loop, executes tools, manages the context window, persists state across turns, recovers from failures, and isolates each session. The harness shapes how well an agent performs as much as the model does, and building a durable one is where most teams spend their time today. AgentCore harness provides that layer as a managed capability. Instead of coding the loop, customers define an agent in configuration: the model it uses, the tools it calls, the skills it accesses, and the instructions it follows, and AgentCore assembles and runs that loop. From that single definition, a production-grade agent runs in minutes in its own isolated environment, with a filesystem and shell, memory across sessions, skills including the AWS-curated catalog, and web browsing. This is not a starter tool teams outgrow: the configuration they start with is what they operate at scale, and when custom orchestration is needed, the harness exports to code on the same platform without rebuilding anything.\u003cbr\u003e\n\u003cbr\u003e\nBesides speed, AgentCore decouples the harness from the model. Customers can choose any model and switch providers mid-session without losing context or touching agent logic, for example planning with one model and writing code with another. The harness is also one piece of a single platform, not a hosting layer wrapped around a framework. It reaches tools through the same gateway that enforces security policies, and connects the agent to organizational knowledge and web search. Identity, memory, and observability come from that same platform, so every agent action is governed and traced from the first call without additional wiring. When a use case needs custom orchestration, a single CLI command exports the harness to Strands-based code on the same compute and primitives, with Claude Agent SDK coming soon as an export target. The agent declared on day one is the agent that runs at the thousandth, on the same foundation throughout.\u003cbr\u003e\n\u003cbr\u003e\nAgentCore harness is generally available today in all \u003ca href=\"https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agentcore-regions.html\"\u003eAWS Commercial Regions\u003c/a\u003e where AgentCore is available. Learn more using the \u003ca href=\"https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness.html\"\u003edocumentation\u003c/a\u003e.\u0026nbsp;\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: amazon-bedrock","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T18:46:51+0000)\n\n**AWS Glue Data Catalog now supports business context and semantic search (Preview)**\n\n\u003cp\u003eToday, AWS announces the preview of business context and semantic search for AWS Glue Data Catalog, helping you discover and understand data by semantic meaning. You can now enrich your Glue Data Catalog tables, including those backed by S3 Tables, with glossary terms and custom metadata fields. You can also add skills to the catalog that direct agents to additional context about your data. With business context indexed alongside technical metadata, you can use the new Glue Search API to find data by semantic meaning, and ground your AI agents in trusted definitions rather than inferred context.\u003c/p\u003e\n\u003cp\u003eYou can use the new search capability to find tables in the catalog both by their structure, such as schema and table format, and by the business meaning you attach through glossary terms and descriptive metadata fields. This means an analyst exploring data or an agent reasoning about it can retrieve a table's definition, what its data represents, and how to use it correctly, in a single step. Any MCP-compatible agent, including Claude Code, Kiro, Cursor, and Codex, can get started with virtually no setup using the aws-data-analytics plugin from the Agent Toolkit for AWS.\u003c/p\u003e\n\u003cp\u003eBusiness context and semantic search for AWS Glue Data Catalog is available in preview in the following AWS Regions: US East (N. Virginia), US East (Ohio), US West (Oregon), and Europe (Ireland). To learn more, visit the \u003ca href=\"https://docs.aws.amazon.com/glue/latest/dg/catalog-business-context-getting-started.html\"\u003eAWS Glue User Guide\u003c/a\u003e. To connect an AI agent to Glue Data Catalog, install the aws-data-analytics plugin from the \u003ca href=\"https://github.com/aws/agent-toolkit-for-aws\"\u003eAgent Toolkit for AWS\u003c/a\u003e repository on GitHub.\u003c/p\u003e\n\n\nCategory: analytics\nProducts: ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T02:16:52+0000)\n\n**Introducing AWS Continuum for security at machine speed **\n\n\u003cp\u003eToday, AWS announces AWS Continuum, which\u0026nbsp;discovers, prioritizes, validates, and remediates security risks at machine speed within guardrails you define. Frontier models have made finding software vulnerabilities faster and cheaper, but the harder work comes after: deciding which vulnerabilities matter to your business, proving which are exploitable, and fixing them without days of cross-team coordination. AWS Continuum closes that gap,\u0026nbsp;so your security team shifts from manual triage to setting direction and approving outcomes.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eAWS Continuum for code vulnerabilities, available in gated preview, works the full lifecycle of a vulnerability at machine speed. It ingests findings from your existing tools and its own scans, prioritizes each one using a context graph of your environment and business, and validates which are exploitable by building reproducible proof in an isolated sandbox. Confirmed exposures then receive fast, reversible mitigations within your guardrails, followed by durable fixes that route through your own review and deployment process, with blast radius visibility and rollback. AWS Security Agent penetration testing and code scanning are now available as Continuum penetration testing and Continuum code scanning (preview). We are also launching Continuum threat modeling in preview, which automatically generates more comprehensive threat models from design documents or source code and outputs results in STRIDE format.\u003c/p\u003e\n\u003cp\u003eAWS Continuum works alongside your existing AWS security services, including Amazon GuardDuty and AWS Security Hub. For more information about the AWS Regions where AWS Continuum is available, see the AWS Region table. To learn more and request access, see the AWS Continuum \u003ca href=\"https://aws.amazon.com/continuum/\"\u003eproduct page\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: security-identity-and-compliance\nProducts: aws-continuum","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T19:01:30+0000)\n\n**Oracle Database@AWS now supports Oracle Autonomous AI Database Serverless**\n\n\u003cp\u003eOracle Database@AWS now supports Oracle Autonomous AI Database Serverless (ADB-S), a fully managed Oracle database service on Exadata infrastructure that automatically handles patching, tuning, and scaling. ADB-S is available through both public and private offers on AWS Marketplace, with support for Bring Your Own License and License Included options.\u003cbr\u003e\n\u003cbr\u003e\nWith ADB-S, you can provision an Oracle Autonomous AI Database directly from the AWS Management Console, AWS CLI, or AWS APIs without provisioning dedicated Exadata infrastructure or VM clusters. ADB-S supports four workload types - AI Transaction Processing, AI Lakehouse, AI JSON Database, and Oracle APEX - with compute and storage that scale independently based on workload demand. ADB-S includes Autonomous Data Guard for high availability and disaster recovery, automated backups to Amazon S3, and cross-Region disaster recovery. ADB-S integrates with AWS Key Management Service (KMS) for encryption, Amazon CloudWatch for monitoring, and Amazon EventBridge for event management.\u003cbr\u003e\n\u003cbr\u003e\nOracle Autonomous AI Database Serverless on Oracle Database@AWS is available in the US East (N. Virginia) and US West (Oregon) AWS Regions. To learn more, visit \u003ca href=\"https://aws.amazon.com/marketplace/featured-seller/oracle/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eOracle Database@AWS\u003c/a\u003e and the \u003ca href=\"https://docs.aws.amazon.com/odb/latest/UserGuide/what-is-odb.html\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eOracle Database@AWS User Guide\u003c/a\u003e. To get started, subscribe through \u003ca href=\"https://aws.amazon.com/marketplace/pp/prodview-qks5dl3hr7nfw?applicationId=AWSMPContessa\u0026amp;ref_=beagle\u0026amp;sr=0-1\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAWS Marketplace\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: databases\nProducts: ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-17T21:37:22+0000)\n\n**AWS Secrets Manager introduces safe secrets handling in the Agent Toolkit for AWS**\n\n\u003cp\u003eAWS Secrets Manager now offers a secret safety skill as part of the aws-core plugin in the \u003ca href=\"https://github.com/aws/agent-toolkit-for-aws\"\u003eAgent Toolkit for AWS\u003c/a\u003e, an open-source repository that equips AI coding agents with tools, knowledge, and guardrails for building on AWS. The skill lets developers use secrets within agentic workflows without ever exposing secret values to the underlying model or session logs.\u003cbr\u003e\n\u003cbr\u003e\nUntil now, developers using AI coding agents could retrieve secrets as plain text without any guardrails, bringing sensitive values into agent context. With this skill, agents can securely retrieve and consume secrets without passing secret values through the context window, adding a layer of protection. To achieve this, the skill uses a two-layer approach. First, it steers the agent so the model never requests or receives a raw secret value—instead prompting the developer to clarify intent and constructing a command that \u003ci\u003euses\u003c/i\u003e the secret rather than retrieving it. Second, a child process resolves secret references to actual values only at execution time, outside the agent process. Together, these layers ensure plaintext secrets never appear in model context, session logs, or agent memory—without disrupting the developer's workflow.\u003cbr\u003e\n\u003cbr\u003e\nThe secret safety skill is available today for all agent harnesses supported by the Agent Toolkit for AWS—including Claude Code, Codex, and Cursor—and in all AWS Regions where Secrets Manager is available. To get started, visit the \u003ca href=\"https://github.com/aws/agent-toolkit-for-aws\"\u003eAgent Toolkit for AWS repository on GitHub\u003c/a\u003e and install the aws-core plugin for your preferred coding agent. For details, refer to the \u003ca href=\"https://docs.aws.amazon.com/secretsmanager/latest/userguide/retrieving-secrets-ai-agents.html\"\u003edocumentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: TBD\nProducts: aws-secrets-manager","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T03:35:21+0000)\n\n**Amazon Bedrock Managed Knowledge Base is now generally available**\n\n\u003cp\u003eAmazon Bedrock Managed Knowledge Base, a fully managed retrieval-augmented generation (RAG) service, is now generally available. With Managed Knowledge Base, developers can build production-ready AI agents grounded in enterprise data without managing vector databases, data pipelines, or retrieval infrastructure. The service handles data ingestion, storage optimization, and advanced retrieval so teams can go from prototype to production faster.\u003c/p\u003e\n\u003cp\u003eAmazon Bedrock Managed Knowledge Base includes six native data source connectors—Amazon S3, SharePoint, Confluence, Google Drive, OneDrive, and Web Crawler—with automatic data syncing and managed vector storage optimized for price-performance. Advanced retrieval capabilities include hybrid search, document ranking, and agentic retrieval that automatically orchestrates query planning, interim response evaluation, and re-ranking for complex multi-hop queries. You can use Managed Knowledge Base to power employee assistants, automate customer support, or build multimodal knowledge bases spanning text, video, audio, and images. The service integrates natively with Amazon Bedrock AgentCore, enabling you to connect your knowledge base to agents with auto-generated permissions and built-in observability.\u003c/p\u003e\n\u003cp\u003eAmazon Bedrock Managed Knowledge Base is available today in the US East (N. Virginia), US West (Oregon), Asia Pacific (Sydney, Tokyo), Europe (Dublin, Frankfurt, London), and AWS GovCloud (US-West) Regions.\u003c/p\u003e\n\u003cp\u003eTo learn more, visit the Amazon Bedrock Knowledge Bases \u003ca href=\"https://aws.amazon.com/bedrock/knowledge-bases/\" target=\"_blank\"\u003eproduct page.\u003c/a\u003e To get started, see the Amazon Bedrock Knowledge Bases \u003ca href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base.html\" target=\"_blank\" rel=\"noopener noreferrer\"\u003edocumentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: amazon-bedrock","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-12T21:44:03+0000)\n\n**AWS Security Agent announces support for Threat Modeling**\n\n\u003cp\u003eAWS Security Agent (now part of AWS Continuum) now includes threat modeling, an AI-powered agentic capability that automatically generates threat models for your applications. Available today in public preview, AWS Security Agent analyzes your design documents or application source code, understands the full context of your application architecture, and identifies threats with recommended mitigations using the STRIDE framework.\u003c/p\u003e\n\u003cp\u003eThreat modeling is critical but often requires specialized expertise and significant manual effort. The threat modeling capability brings agentic AI reasoning to this process by deeply analyzing your code and documentation to understand architecture, data flows, and trust boundaries, then producing a contextually relevant threat model with actionable mitigations across all six STRIDE categories.\u003c/p\u003e\n\u003cp\u003eDevelopers can integrate the agent into IDEs such as Kiro and Claude Code to create threat models from specs and address threats early in the design phase. Security teams can use it for pre-deployment assessments against design documents and source code.\u003c/p\u003e\n\u003cp\u003eThe threat modeling capability is available in all regions supported by AWS Security Agent, at no additional cost during the public preview.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTo learn more, visit our \u003ca href=\"https://aws.amazon.com/blogs/aws/aws-security-agent-adds-threat-modeling-kiro-power-and-claude-code-plugin-and-more\"\u003eblog post\u003c/a\u003e or our\u0026nbsp;\u003ca href=\"https://docs.aws.amazon.com/securityagent/latest/userguide/what-is.html\"\u003edocumentation\u003c/a\u003e page.\u003c/p\u003e\n\n\nCategory: developers\nProducts: ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-12T21:38:43+0000)\n\n**AWS Security Agent adds Kiro Power, Claude Code, simulated validations and new integrations support **\n\n\u003cp\u003eAWS Security Agent (now part of AWS Continuum) adds support for Kiro and Claude Code, enabling developers to trigger security scans directly from their development environment. AWS Security Agent now also validates code scanner findings by simulating exploits in a sandbox environment and providing proof of exploit, so teams can trust their results, minimize false positives, and prioritize remediation with confidence. Additionally, this release adds integrations with GitLab.com, GitLab Self Managed, GitHub Enterprise, Bitbucket, and Confluence.\u003c/p\u003e\n\u003cp\u003eWith simulated validations, the code scanner goes beyond detection as it executes findings in an isolated environment and returns evidence demonstrating how a vulnerability can be exploited. Security teams no longer need to spend cycles triaging unverified alerts; they get legitimate, proven findings with the context needed to make the right prioritization decisions.\u003c/p\u003e\n\u003cp\u003eKiro power and Claude Code plugin for AWS Security Agent lets developers connect their existing source control platforms and build threat models, run code scans and remediate validated findings from code review and penetration tests without leaving their IDE.\u003c/p\u003e\n\u003cp\u003eThese features are available in all regions where AWS Security Agent is supported.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTo learn more, visit our \u003ca href=\"https://aws.amazon.com/blogs/aws/aws-security-agent-adds-threat-modeling-kiro-power-and-claude-code-plugin-and-more\"\u003eblog post\u003c/a\u003e or our\u0026nbsp;\u003ca href=\"https://docs.aws.amazon.com/securityagent/latest/userguide/what-is.html\"\u003edocumentation \u003c/a\u003epage.\u0026nbsp;\u003c/p\u003e\n\n\nCategory: security-identity-and-compliance\nProducts: ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-12T23:22:09+0000)\n\n**Amazon Bedrock Guardrails announces a new API targeting agentic AI workflows**\n\n\u003cp\u003e\u003ca href=\"https://aws.amazon.com/bedrock/guardrails/\"\u003eAmazon Bedrock Guardrails\u003c/a\u003e now offers the InvokeGuardrailChecks API, a new resourceless API that lets you apply individual safeguards at any point in your agentic AI applications without creating guardrail resources. The API provides granular, per-request control over which safeguards to run at each step of your agent loop, returning numeric severity and confidence scores so you can implement custom thresholds and actions, whether to block, pass, retry, or log based on your specific requirements.\u003c/p\u003e\n\u003cp\u003eAgentic AI applications operate through iterative loops; planning tasks, calling tools, processing outputs, and iterating again while often executing dozens of steps for a single request. Each step carries a different risk profile, making a one-size-fits-all guardrail difficult to scale. The InvokeGuardrailChecks API addresses this by operating in detect-only mode with no guardrail IDs to track and no versions to manage. You specify which safeguards to run directly in each request, making it straightforward to add, remove, or adjust checks as your workflows evolve.\u003c/p\u003e\n\u003cp\u003eThe API supports content filters (detecting harmful content across categories including hate, violence, sexual, insults, and misconduct), prompt attack detection (identifying jailbreak, prompt injection, and prompt leakage as independent standalone checks), and sensitive information filters (detecting supported PII entity types). Prompt attack detection is exposed as a separate safeguard, giving you the granularity to invoke each supported attack vector independently.\u003c/p\u003e\n\u003cp\u003eThe InvokeGuardrailChecks API is available today in the following AWS Regions: US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (London), Europe (Stockholm), Asia Pacific (Tokyo), and Asia Pacific (Sydney).\u003c/p\u003e\n\u003cp\u003eTo learn more, visit the Amazon Bedrock Guardrails \u003ca href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-use-invoke-guardrail-checks.html\"\u003etechnical documentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: aiml, amazon-bedrock","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T20:20:52+0000)\n\n**AWS Transform now supports model-to-model migration assessment for generative AI workloads**\n\n\u003cp\u003eAWS Transform now offers a model-to-model migration custom transformation that assesses your generative AI workloads and produces a comprehensive migration plan for moving from third-party providers to Amazon Bedrock. The AI-powered agent scans your codebase, identifies every AI SDK and model in use, gathers your migration requirements through interactive questions, and maps models to Bedrock equivalents with transparent cost comparisons and production-ready code changes. This managed custom transformation helps organizations consolidate their AI workloads on AWS to gain IAM-based security, VPC endpoint isolation, prompt caching, Amazon Bedrock Guardrails, and unified operational tooling through Amazon CloudWatch. \u0026nbsp;\u003cbr\u003e\n\u003cbr\u003e\nThe transformation supports migrations from OpenAI, Google Gemini, direct Anthropic SDK usage, and open-source models via LiteLLM or Ollama. It handles direct SDK integrations, framework-wrapped patterns such as LangChain and LlamaIndex, agentic architectures including CrewAI and LangGraph, and multi-provider routing layers — preserving your application architecture while swapping only the model layer. The agent includes intelligent cost optimization with tiered model routing recommendations, prompt caching analysis, and model lifecycle awareness that excludes models within 90 days of end-of-life from all recommendations. For some workloads, it recommends Amazon Bedrock's OpenAI-compatible endpoints as a zero-code-change migration path.\u003c/p\u003e\n\u003cp\u003eAWS Transform model-to-model migration is available in all AWS Regions where \u003ca href=\"https://aws.amazon.com/transform\"\u003eAWS Transform\u003c/a\u003e\u0026nbsp;is offered, at no additional charge beyond standard AWS Transform pricing. To get started, install the ATX CLI and run the mke-genai-model-migration custom transformation against your codebase. To learn more, see the \u003ca href=\"https://docs.aws.amazon.com/transform/latest/userguide/custom.html\"\u003eAWS Transform Custom Transformations documentation\u003c/a\u003e\u0026nbsp;and the \u003ca href=\"https://aws.amazon.com/blogs/migration-and-modernization/migrate-your-ai-workloads-to-amazon-bedrock-with-aws-transform/\"\u003eannouncement blog\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: migration\nProducts: aws-transform ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-15T23:19:11+0000)\n\n** Amazon S3 Vectors now supports up to 10,000 similarity search results per query**\n\n\u003cp\u003eAmazon S3 Vectors can now return up to 10,000 similarity search results per query, a 100x increase from the previous limit.\u0026nbsp;The higher result limit helps you retrieve a larger, more comprehensive set of candidates during similarity queries. This is especially valuable for applications with multi-stage retrieval pipelines that need to apply additional processing such as reranking, aggregations, or deduplication to produce a more relevant final result set.\u003c/p\u003e\n\u003cp\u003eTo get started with the higher limit, use the latest AWS SDK and update your application code to specify up to 10,000 relevant results (topK nearest neighbors) when making a QueryVectors API request. Query results are now returned across multiple pages, and you can start processing the first page immediately while retrieving additional pages as needed. For queries that return larger result sets, you pay a small data-returned fee based on the total size of results returned. The first 512 KB of data returned per query is free. For full pricing details, visit the \u003ca href=\"https://aws.amazon.com/s3/pricing/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eS3 pricing page.\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003eS3 Vectors supports retrieving up to 10,000 results per query in all \u003ca href=\"https://docs.aws.amazon.com/AmazonS3/latest/userguide/s3-vectors-regions-quotas.html\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eAWS Regions\u003c/a\u003e where it is available. To learn more about S3 Vectors, visit the \u003ca href=\"https://aws.amazon.com/s3/features/vectors/\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eproduct page\u003c/a\u003e and \u003ca href=\"https://docs.aws.amazon.com/AmazonS3/latest/userguide/s3-vectors.html\" target=\"_blank\" rel=\"noopener noreferrer\"\u003eS3 User Guide\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: storage\nProducts: amazon-simple-storage-service","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-17T16:31:17+0000)\n\n**Amazon Bedrock Guardrails adds automated reasoning checks in Sydney**\n\n\u003cp\u003eAutomated Reasoning checks in Amazon Bedrock Guardrails use formal verification techniques to validate AI model outputs with mathematical rigor, providing a fundamentally different approach from traditional sampling-based testing methods. This capability addresses critical challenges in deploying generative AI applications, including AI hallucinations, policy compliance violations, and ambiguous responses that can undermine trust in AI systems. Organizations in regulated industries such as finance, healthcare, and legal services, as well as any enterprise requiring unambiguous validation of AI outputs, can now leverage this advanced verification capability.\u003c/p\u003e\n\u003cp\u003eThe feature delivers up to 99% accuracy in detecting correct responses from large language models, offering provable assurance through mathematical guarantees rather than probabilistic testing. Automated Reasoning checks help enterprises meet regulatory requirements for AI deployment while significantly reducing risks associated with incorrect or fabricated model outputs. Specific use cases include validating AI responses before production deployment in regulated environments, ensuring business rule compliance in enterprise applications, and providing quality assurance for generative AI outputs in critical workflows where ambiguity cannot be tolerated.\u003c/p\u003e\n\u003cp\u003eAutomated Reasoning checks in Amazon Bedrock Guardrails are now available in the Asia Pacific (Sydney) Region, joining existing availability in US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (Frankfurt), Europe (Ireland), and Europe (Paris). Customers can access this capability through the Amazon Bedrock console or the Amazon Bedrock SDK. To learn more about Automated Reasoning checks and Amazon Bedrock Guardrails, visit \u003ca href=\"https://aws.amazon.com/bedrock/guardrails/\"\u003eAmazon Bedrock Guardrails\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: amazon-bedrock","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-16T19:07:21+0000)\n\n**AWS Transform for mainframe now delivers a traceable reimagine workflow**\n\n\u003cp\u003eAWS Transform for mainframe now delivers a connected, traceable reimagine experience from assessment through code generation. Previously, modernizing mainframe applications required months of analysis across multiple tools for discovery, reverse engineering, and code generation with manual handoffs between phases. With this launch, enterprises running z/OS COBOL and PL/I workloads can assess their portfolio to identify the discrete business functions, extract business rules, generate development-ready requirements, and produce traceable cloud-native code in a single connected workflow.\u003c/p\u003e\n\u003cp\u003eThe experience starts with a portfolio assessment, where AWS Transform systematically identifies and catalogs discrete business functions. Selected business functions flow directly into the reimagine workflow, creating a connected path from portfolio analysis through code generation. For each business function, AWS Transform generates development-ready requirements with full traceability, flowing directly into Kiro and other IDEs through MCP-based integrations. Teams can generate interactive documentation for any requirement or code directly in the IDE. Every requirement traces back to the source code, so teams can audit any transformation decision back to its origin. This end-to-end approach compresses what previously took years of manual effort into months of automated, evidence-based modernization.\u003cbr\u003e\n\u003c/p\u003e\n\u003cp\u003eThese capabilities are available in all AWS Regions where AWS Transform for mainframe is available. For more information, see the \u003ca href=\"https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/\"\u003eAWS Region table\u003c/a\u003e.\u003c/p\u003e\n\u003cp\u003eTo learn more, visit \u003ca href=\"https://aws.amazon.com/transform/mainframe/\"\u003eAWS Transform for mainframe\u003c/a\u003e or see the \u003ca href=\"https://docs.aws.amazon.com/transform/\"\u003eAWS Transform for mainframe documentation\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: artificial-intelligence\nProducts: aws-transform ","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-12T18:35:39+0000)\n\n**Announcing Web Search on Amazon Bedrock AgentCore for Agentic Web Retrieval**\n\n\u003cp\u003eAs AI agents become more capable, they need access to information beyond a model's training data - to answer questions, retrieve latest facts, and take action grounded in current developments. Today, we're making that easy with the general availability of Web Search on AgentCore. Web Search is a fully managed tool that enables agents to ground responses in current, accurate web knowledge while keeping data residency within your secured AWS environment with zero data egress.\u003cbr\u003e\n\u003cbr\u003e\nPreviously, adding web search to agents on Amazon Bedrock AgentCore required integrating with external search providers, building custom orchestration, managing authentication and billing, and coordinating security and compliance across multiple services. Web Search removes this undifferentiated heavy lifting, enabling developers to focus on building agents.\u003cbr\u003e\n\u003cbr\u003e\nWeb Search is built on Amazon’s proven search infrastructure, informed by years of experience powering agentic search experiences across Alexa+, Amazon Q Business, and Kiro. It uses a multi-source grounding approach, by combining a web index operated by amazon with structured knowledge graph data. Beyond standard web results, this gives agents access to entity data and verified facts, helping them retrieve more relevant and accurate responses than traditional web search alone.\u003cbr\u003e\n\u003cbr\u003e\nWeb Search is optimized for agentic retrieval, returning high-value excerpts that deliver strong intelligence per token. The tool is exposed as a built-in connector target on AgentCore gateway using the Model Context Protocol (MCP). Your agent sends a natural-language query, and Web Search returns ranked results with relevant snippets, source URLs, titles, and publication dates that the model can reason over to produce a grounded response.\u003cbr\u003e\n\u003cbr\u003e\nWeb Search on AgentCore is generally available today in the AWS Region: US East (N. Virginia). For more information, see the \u003ca href=\"https://docs.aws.amazon.com/bedrock-agentcore/\"\u003eAgentCore documentation\u003c/a\u003e or read the \u003ca href=\"https://aws.amazon.com/blogs/aws/announcing-web-search-on-amazon-bedrock-agentcore-ground-your-ai-agents-in-current-accurate-web-knowledge/\"\u003eAWS News Blog\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: TBD\nProducts: amazon-bedrock","role":"assistant"}}}

data: {"id":0,"jsonrpc":"2.0","result":{"message":{"content":"📢 AWS News Update (2026-06-10T17:55:37+0000)\n\n**AWS Sign-in now supports resource-based policies and resource control policies**\n\n\u003cp\u003eAWS Sign-in now supports resource-based policies and resource control policies (RCPs) for the AWS Management Console. You can use these policies to restrict console sign-in to expected networks. Policies are evaluated during sign-in and whenever the console session requests new credentials.\u003c/p\u003e\n\u003cp\u003eResource-based policies apply to individual AWS accounts. Resource control policies apply organization-wide through AWS Organizations. You can combine these policies with \u003ca href=\"https://docs.aws.amazon.com/awsconsolehelpdocs/latest/gsg/console-private-access.html\" target=\"_blank\"\u003eAWS Management Console Private Access\u003c/a\u003e to control both which networks users can sign in from and which accounts they can access.\u003c/p\u003e\n\u003cp\u003eAWS Sign-in resource-based policies and RCPs are available at no additional cost in all AWS commercial Regions. To learn more, see the \u003ca href=\"https://docs.aws.amazon.com/signin/latest/userguide/what-is-sign-in.html\" target=\"_blank\"\u003eAWS Sign-in User Guide\u003c/a\u003e. For API details, see the \u003ca href=\"https://docs.aws.amazon.com/signin/latest/APIReference/\" target=\"_blank\"\u003eAWS Sign-in API Reference\u003c/a\u003e.\u003c/p\u003e\n\n\nCategory: TBD\nProducts: aws-iam, aws-organizations, aws-identity-and-access-management","role":"assistant"}}}