AI Briefing#amazon-eks
The latest AI and developer news about #amazon-eks, with the original source and a short summary.
The latest AI and developer news about #amazon-eks, with the original source and a short summary.
Built an integrated agent platform where the process from saving settings to making an agent callable takes approximately 2 minutes and 10 seconds.
In 526 investigations over 7 weeks, 77% of root causes were identified, reducing engineers' MTTR.
In the GitOps-based AgentCore deployment demo, all 94 requests succeeded.
Ablely managed the lifecycle of AI agent workloads using Amazon EKS and Agent Sandbox.
Search OS achieved over 2x growth in Ringtey's organic search purchase revenue and a 4.5x increase in GS SHOP AI purchases using its AWS-based SEO/GEO solution.
Global model accuracy improved by 26 percentage points over local models in asymmetric data environments
Amazon EKS has launched a feature allowing customers to directly configure five control plane parameters, including those for kube-scheduler.
This article introduces vLLM optimization strategies to maximize Gemma 4's SLO-compliant throughput through NVFP4 precision and the separation of interactive and batch pools.
By leveraging Run:ai Streamer and cache optimizations for serving Gemma 4 with vLLM on Amazon EKS, cold start times were reduced from 428 seconds to 226 seconds.
Karrot leveraged AWS CloudHSM to design a security architecture with three layers of access control across the network, application, and HSM internals.
Adopting ARM64-based AWS Graviton instances in EKS can cut costs by up to 40% compared to x86.
Amazon EKS has launched a rollback feature that allows reverting to a previous version within 7 days if issues occur after an upgrade.
This introduces a reference architecture for efficiently operating Physical AI workflows on Amazon EKS using NVIDIA OSMO.
DelightRoom migrated 5 clusters to EKS Auto Mode, significantly reducing operational burden.
Automated Agentic AI operations using Amazon EKS Auto Mode, Bifrost, and Langfuse.
By moving from SQS+Lambda to an EKS Spot-based setup, they achieved 70-90% cost savings and improved processing speed.
A roundup of AWS's latest releases across Bedrock, Redshift, Lambda, EKS, and more.
re:Invent 2025 showcased operations, security, and cost optimization strategies built on AI as a default premise.
A missing libdcgm.so on Bottlerocket GPU nodes was causing Karpenter to repeatedly replace them.
Shares the on-site atmosphere, key sessions, and technology experiences from AWS re:Invent 2022 held in Las Vegas.