All news in category “Vendor and Hyperscaler Watch”

🔒 Amazon Bedrock AgentCore now lets administrators apply Chrome Enterprise policies to AgentCore Browser and upload custom root CA certificates for both AgentCore Browser and Code Interpreter. These capabilities enable enforcement of organizational controls such as URL restrictions, disabling downloads or password managers, and implementing URL blocklists while agents operate. Custom root CA support allows agents to connect to internal systems and work with corporate TLS interception without certificate errors. The features are available in 14 AWS Regions where AgentCore is offered.

⚡ AWS now supports NVIDIA Inference Xfer Library (NIXL) with Elastic Fabric Adapter (EFA) on all EFA-enabled EC2 instances and regions. This integration accelerates disaggregated LLM inference by increasing KV-cache throughput, lowering inter-token latency, and optimizing KV-cache memory use between prefill and decode nodes. NIXL interoperates with frameworks such as NVIDIA Dynamo, SGLang, and vLLM. Supported versions are NIXL 1.0.0+ and EFA installer 1.47.0+, available at no extra cost.

🔐 Amazon Redshift now supports federated permissions with AWS IAM Identity Center (IdC) across multiple AWS Regions, letting you extend IdC from a primary Region to additional Regions for improved proximity-based performance and resilience. In those Regions you can create Redshift and Lake Formation Identity Center applications without replicating identities, so existing workforce identities can query warehouses while row-, column-level and masking controls continue to apply automatically. Users benefit from single sign-on access via Amazon QuickSight, the Redshift Query Editor, or third-party SQL tools, simplifying access and compliance across regions.

🚀 Amazon Web Services has expanded availability of Amazon EC2 C8gn instances—powered by the latest-generation AWS Graviton4 processors—to additional regions including Jakarta, Hyderabad, Tokyo, São Paulo, and Zurich. C8gn provides up to 30% better compute performance versus Graviton3-based C7gn instances, and uses 6th-generation Nitro Cards to deliver up to 600 Gbps network bandwidth. Instance sizes scale to 48xlarge with up to 384 GiB of memory, up to 60 Gbps EBS bandwidth, and EFA support on larger SKUs to improve cluster latency and throughput for network‑intensive and CPU‑bound inference workloads.

🔍 AWS Lambda now exposes Availability Zone (AZ) metadata through a new metadata endpoint in the execution environment. Developers can retrieve the AZ ID (for example, use1-az1) to implement AZ-aware routing and prefer same-AZ endpoints to reduce cross-AZ latency. The feature supports all runtimes, custom runtimes, and container images, and works with SnapStart, provisioned concurrency, and VPC-enabled functions. Available at no extra cost in all commercial Regions.

🔒Google outlines five practical defenses to help users spot and avoid tax‑season scams. It describes on‑device AI protections on Pixel phones including Call Screen and optional real‑time Scam Detection alerts, plus text‑vetting with Circle to Search and Lens. The post highlights real‑time Safe Browsing, high‑visibility Gmail warning banners and security steps like Passkeys and 2‑Step Verification to reduce fraud risk.

📡 AWS has opened a new AWS Direct Connect location at Equinix SY5 in Sydney, Australia. From this site you can establish private, direct network access to all public AWS Regions (except China), AWS GovCloud Regions, and AWS Local Zones. The location supports dedicated 10 Gbps and 100 Gbps connections and offers MACsec encryption. This is the fourth Direct Connect site in Sydney and the tenth in Australia, providing a more consistent private networking option than the public internet.

🔒 The integration of Prisma AIRS with ServiceNow's AI Control Tower embeds AI runtime security and model governance directly into enterprise workflows. Prisma AIRS delivers real‑time detection and blocking of threats such as prompt injection and offensive outputs, while Model Security supplies risk profiles, red‑teaming results and vulnerability reports for third‑party and custom models. Together they provide centralized visibility, policy enforcement and safer AI adoption without disrupting user productivity.

⚙️ Amazon RDS Custom for SQL Server now enables customers to view and schedule operating system updates for RDS provided engine versions (RPEV), where each RPEV is a SQL Server version pre-installed on an Amazon Machine Image. Customers can check pending updates via the describe-pending-maintenance-actions API or subscribe to event RDS-EVENT-0230 for alerts. They can apply updates immediately or use apply-pending-maintenance-action to schedule installation during the next maintenance window. These capabilities are available in all AWS Regions that offer RDS Custom for SQL Server.

📢 Amazon Bedrock now supports GLM 5 and Minimax M2.5, expanding its frontier model selection across select AWS Regions. GLM 5 targets complex systems engineering and long‑horizon agentic tasks, offering improved multi‑step reasoning, math (including AIME‑style capabilities), advanced coding, and long context support for sophisticated agents. Minimax M2.5 is agent‑native and optimized for efficient task decomposition, high inference throughput, and token‑efficient decisioning to deliver fast, cost‑sensitive task completion. Both models are available in Bedrock for enterprise and agentic workflows.

🤖 The post proposes the orchestrator pattern to turn monolithic AI scripts into a team of specialized, distributed microservices that integrate directly with existing frontends. It demonstrates using Google's Agent Development Kit (ADK), the Agent-to-Agent (A2A) protocol, and Cloud Run to host separate researcher, judge, and orchestrator services. The design enables independent scaling, strict JSON contracts for reliable decision-making, and language-agnostic implementations. The authors emphasize production hardening: secure agent endpoints, mitigate latency across hops, and implement robust retries and error handling.

🧠 Amazon has launched EC2 High Memory U7i-6TB instances in AWS Asia Pacific (Malaysia). The u7i-6tb.112xlarge offers 6TiB of DDR5 memory and 448 vCPUs, with up to 100 Gbps for Amazon EBS and network, plus ENA Express for accelerated networking. These instances are powered by custom fourth‑generation Intel Xeon Scalable processors (Sapphire Rapids). They are designed for mission‑critical in‑memory databases such as SAP HANA, Oracle, and SQL Server.

🚀 Amazon Bedrock now supports NVIDIA Nemotron 3 Super, an open hybrid Mixture-of-Experts (MoE) model designed for complex multi-agent and agentic workloads. The model delivers fast, cost-efficient inference for long, multi-step tasks while preserving context, and is released with open weights, datasets, and recipes for customization. Bedrock exposes Nemotron 3 Super via a single, fully managed, serverless API with built-in security controls and compatibility with OpenAI API specifications, and the model is available in select AWS Regions.

🔒 Amazon Elastic Container Registry (Amazon ECR) pull through cache now supports Chainguard as an upstream registry, enabling customers to cache private Chainguard images within ECR. This feature synchronizes frequently with Chainguard's registry so images stay up to date without extra tooling. Cached images can be managed with ECR capabilities like image scanning and lifecycle policies, and the pull through cache is available in all AWS Regions where ECR supports it. By centralizing Chainguard images in ECR, customers gain improved availability, manageability, and security posture.

🔒 Amazon S3 Access Grants are now generally available in the AWS Asia Pacific (New Zealand) Region. The capability maps identities from directories such as Microsoft Entra ID and AWS IAM principals directly to S3 datasets, enabling identity-driven, automated access provisioning for users. This reduces the need for manual policy changes and simplifies large-scale permission management. Local availability also helps improve latency and supports regional compliance and governance requirements for organizations operating in New Zealand.

📍 Amazon has launched Amazon Quick in the AWS Asia Pacific (Tokyo) region (ap-northeast-1), enabling Japan-based customers to use its agentic AI capabilities while addressing local and regional data sovereignty requirements. The service delivers AI-powered chat, Research, Spaces, Flows, and QuickSight dashboards. The announcement states customer data will be stored and processed locally within the London region and supports in-region inference through JP-CRIS, routing inference requests exclusively within Japanese AWS Regions. Regulated industries such as financial services, healthcare, and the public sector are specifically called out as beneficiaries.

🤝 Palo Alto Networks has reimagined the NextWave Partner Program to align partners, customers and platform-driven security in the AI era. The update expands support for MSSPs, increases authorized services capacity with ASC and APS, and supports Distributor Managed Partner growth. It introduces a Partner Development Fund (PDF) to reinvest rebates into partner-led demand generation, training and solution development. New incentives, proficiency-based discounts and streamlined quoting and enablement tools emphasize platform adoption, operational readiness and profitable services within a framework of Access, Commitment and Profitability.

🇩🇪 Amazon Quick is now available in the AWS Europe (Frankfurt) region (eu-central-1). This launch lets customers in Germany use Amazon Quick capabilities—AI-powered chat, Research, Spaces, Flows, and QuickSight dashboards—with data stored and processed locally within the Frankfurt region. The expansion includes in-region inference via EU-CRIS, ensuring inference traffic stays inside European AWS Regions. Regulated industries such as financial services, healthcare, and the public sector can meet GDPR and local data sovereignty requirements.

🚀 Amazon Quick is now available in the AWS Europe (London) region (eu-west-2), enabling UK customers to use Amazon Quick with data stored and processed locally to meet regional requirements. The service delivers AI-powered chat, Research, Spaces, Flows, and QuickSight dashboards that act as an agentic teammate, enabling users to get answers and take actions without switching applications. In-region inference is enforced via EU-CRIS, routing requests exclusively within European AWS Regions and supporting regulated sectors such as financial services, healthcare, and the public sector.

🚀 Starting today, Amazon EC2 M6in and M6idn instances are available in the AWS London Region. These sixth-generation, network-optimized instances use 3rd Generation Intel Xeon Scalable processors and the AWS Nitro System to deliver up to 200 Gbps of network bandwidth—about 2x that of comparable fifth-generation instances. They support up to 128 vCPUs, 512 GiB of memory, up to 100 Gbps of EBS bandwidth and up to 400K IOPS, and M6idn offers up to 7.6 TB of low-latency instance storage. Sizes include metal and 32xlarge (which also support EFA); purchase options include Savings Plans, On-Demand, and Spot.