All news in category “Vendor and Hyperscaler Watch”

🔍 Amazon Connect Customer now offers generative AI summaries, real-time call analytics, and real-time rules in the Africa (Cape Town) Region. These features complement existing post-contact conversational analytics to provide AI-driven insights that improve customer experience, agent performance, and operational efficiency. Supervisors and agents receive concise AI-generated summaries after contacts, while live transcription and automated rules enable monitoring and immediate interventions during interactions.

🔁 AWS Elastic Disaster Recovery (AWS DRS) introduces Recovery Plans to automate the sequenced launch of multi-server applications during recoveries and drills. You define server groups and ordered steps once, with configurable wait times, approvals, and non-disruptive drill mode to validate procedures. Recovery Plans provide real-time monitoring, reduce recovery time, and remove manual dependency tracking. The feature is available in all Regions where AWS DRS is offered at no extra cost beyond standard usage.

🚀 Amazon Bedrock AgentCore is now available in US West (N. California) and Asia Pacific (Hyderabad), enabling developers to build and run agents closer to end users. The platform supports agent runtime, identity and access control, policy management, session persistence, tool connectivity, evaluations, and observability at launch. AgentCore emphasizes secure infrastructure-level enforcement so agents cannot bypass controls. Regional availability reduces latency and improves performance for local customers.

🔄 Amazon Connect Customer now auto-refreshes scheduling metrics on the scheduling page to give managers immediate visibility into the impact of schedule updates. When changes such as a team meeting for several agents are made, metrics like net available headcount and projected service level update automatically. This feature helps workforce managers assess staffing coverage and make faster, informed decisions throughout the day.

🔒 Amazon FSx for NetApp ONTAP now supports copying backups within and across AWS Regions and across trusted accounts in your AWS organization. This capability lets you store secondary backup copies in different Regions or accounts for improved business continuity, data protection, and compliance. Backups remain secure, incremental, and durably stored across Availability Zones, and you can copy both new and existing backups in all Regions where the service is available.

🔔 AWS Backup now supports copying Amazon FSx for NetApp ONTAP backups across AWS Regions and accounts. You can copy FSx for NetApp ONTAP backups to another AWS Region, another AWS account, or both using policy-based backup plans or on-demand copy jobs. Copies can be managed centrally and automated across your organization with AWS Organizations. This capability is available in all commercial Regions where both services are offered.

🔒 Check Point Research warns that AI is accelerating cyberattacks, requiring faster and broader defensive measures. The company publicly supports OpenAI’s open letter calling for collective action across industry, government, and AI labs to expand access to security tools, share intelligence, and help under-resourced organizations. Check Point emphasizes its 30-year commitment to prevention and pledges to support customers adopting AI securely while contributing to shared defenses and practical remediation efforts.

🧠 Cloudflare’s Big Pineapple platform stores over 250 billion DNS cache entries and reduced per-entry memory by over 50% through five successive storage optimizations. These changes freed roughly 100 TB of RAM across the fleet while improving insert throughput by 43% and lowering lookup latency by 19%. The post details techniques like replacing Vec/String with Box, packing section offsets, inferring record owners, boxing large enum variants, and storing record data as a contiguous byte buffer to improve memory locality and reduce allocations.

🔎 This article compares self-managed PostgreSQL and managed PostgreSQL services, explaining how each model balances control, responsibility, cost, and operational effort. It highlights the operational tax of self-hosting versus the reduced platform responsibilities provided by managed services like Azure Database for PostgreSQL. The piece outlines implications for resilience, security, identity integration, backups, maintenance, and scalability to help technical decision makers choose the right operating model.

🛠️ Amazon Elastic VMware Service (Amazon EVS) now supports the i7i.metal-48xl bare-metal Amazon EC2 instance, providing a higher core-count option with 5th generation Intel Xeon Scalable processors. This instance class delivers up to 23% better compute and >10% better price performance versus i4i instances, plus larger memory and storage to host more VMs per EVS host. The feature is available in Regions where both Amazon EVS and EC2 i7i are offered and enables VCF 9.x capabilities and onboarding automations.

🛡️ This update details new Microsoft Security capabilities for August 2026, focusing on AI agent visibility, broader threat coverage, and improved management across environments. Highlights include expanded Microsoft Defender Experts MDR coverage for third-party data sources, Microsoft Entra Tenant Governance for multi-tenant visibility, and Windows device management improvements. Other updates boost data protection with increased auto-labeling throughput in Microsoft Purview and introduce Secure Now guidance for agentic containment.

🆕 Cloud Run instances provide a low‑cost, dedicated compute option for long‑lived, stateful workloads such as personal AI agents. Unlike Cloud Run services that scale to zero, instances run a single, continuously running replica (up to 7 days) with a stable HTTPS URL, automatic restart policy, and the ability to stop and resume. They use shared vCPU with burst budgets to keep costs predictable — for example, 1 vCPU and 1 GiB continuously for 30 days costs $5.70 — and are currently available in preview.

🔒 Android 17 introduces network protections including support for Encrypted Client Hello (ECH) to hide visited domain metadata and work alongside private DNS. The platform-level ECH support encrypts the TLS Client Hello hostname, reducing ISP and Wi‑Fi operator visibility when using compatible apps and browsers. ECH will be enabled by default for apps targeting Android 17 that use supported networking libraries, with a GREASE fallback for non‑ECH servers to avoid detection.

🔍 Prophet Security's 2026 report shows AI has become mainstream in security operations: 40% of teams use AI daily and 56% are testing it. Teams face massive alert volumes, slow triage, and rising AI-driven attacks, while AI adoption is reducing investigation times and shifting analysts toward advanced roles. Privacy, explainability, and DIY project durability remain key challenges for organizations.

🔒 Amazon Aurora DSQL now supports defining FOREIGN KEY constraints on new and existing tables. This serverless, distributed SQL database with PostgreSQL compatibility and active-active multi-Region availability enforces referential integrity so writes that would create invalid references are rejected. Developers can choose delete/update behaviors: NO ACTION, RESTRICT, CASCADE, SET NULL, and SET DEFAULT. The feature is available in all Regions where Aurora DSQL is offered.

🔐 Amazon Cognito introduces an admin API operation to reset a user's time-based one-time password (TOTP) multi-factor authentication configuration. Administrators can remove the TOTP device association for users who lose access to their authenticator, enabling users to enroll a new device on next sign-in. This avoids recreating accounts to recover locked-out users and preserves enforced MFA policies. The feature is available in all AWS Regions and is accessible via the AdminDeleteSoftwareToken API through the AWS CLI, SDKs, or APIs; see the developer guide for details.

🛠️ Managers can now record unplanned shrinkage directly in Amazon Connect Customer agent schedules, capturing unscheduled absences like late logins or sudden sick leave. Uploaded assumptions update scheduling metrics instantly, showing adjusted scheduled headcount, net staffing, and projected service level. This allows teams to see, for example, how a 10% unavailability at 8 AM reduces projected service level from 90% to 85%, helping workforce managers proactively address staffing gaps.

🛡️ This recap highlights AWS Security blog posts, new capabilities, code samples, and guidance published in July 2026. Topics include AI agent security, data protection, network and infrastructure protections, threat detection enhancements, compliance guidance, and 21 security bulletins addressing vulnerabilities. Vendors and practitioners can use the code samples and workshops to implement recommended controls and apply patches promptly.

🧩 Mountpoint for Amazon S3 now supports configurable memory usage limits, either set manually or determined automatically based on the runtime environment. This change lets Mountpoint coexist with memory‑intensive workloads such as machine learning training or analytics by reserving memory for applications and slowing operations under memory pressure. The feature detects container budgets in environments like Amazon EKS and is available in all AWS Regions. Upgrade details and configuration guidance are available in the Mountpoint GitHub repository.

🔍 This post explains how correlating signals across AWS services and your business context reveals multi-stage attacks that single alerts miss. It outlines five attack phases and the three primary log sources—CloudTrail, VPC Flow Logs, and Route 53 Resolver logs—used to surface each phase. The guide emphasizes enabling and tuning AWS detection services such as Amazon GuardDuty, then layering custom queries that encode your environment-specific knowledge. It includes CloudWatch Logs Insights queries and operational guidance for thresholds, multi-account setups, and automating detection pipelines.