How DeepL keeps closest-exit routing during maintenance with AWS Cloud WAN
TutoSartup excerpt from this article:
Taking a single AWS Direct Connect link out of service for planned maintenance is a routine task, but in a multi-Region hybrid network it demands care... DeepL connects its AWS Regions to its data centers through Direct Connect and relies on the default closest-exit egress behavior to keep latency low... This post describes how DeepL does this with AWS Cloud WAN and a Direct Connect gateway att...
Taking a single AWS Direct Connect link out of service for planned maintenance is a routine task, but in a multi-Region hybrid network it demands care... DeepL connects its AWS Regions to its data centers through Direct Connect and relies on the default closest-exit egress behavior to keep latency low... This post describes how DeepL does this with AWS Cloud WAN and a Direct Connect gateway att...
Single-shot and agentic retrieval with Amazon Bedrock Managed Knowledge Base
TutoSartup excerpt from this article:
Applications need a way to match retrieval effort to each request without building separate systems for simple and complex questions... Amazon Bedrock Managed Knowledge Base now supports single-shot Retrieval Augmented Generation (RAG) and retrieval-only requests through AgenticRetrieveStream... With retrieval-only requests, the service returns the matching passages without generating an answer,...
Applications need a way to match retrieval effort to each request without building separate systems for simple and complex questions... Amazon Bedrock Managed Knowledge Base now supports single-shot Retrieval Augmented Generation (RAG) and retrieval-only requests through AgenticRetrieveStream... With retrieval-only requests, the service returns the matching passages without generating an answer,...
Introducing Claude Fable 5.2 on AWS
TutoSartup excerpt from this article:
Today, we are announcing the availability of Claude Fable 5...2 and Claude Mythos 5...2 on Amazon Bedrock and Claude Platform on AWS... Claude Fable 5... Claude Mythos 5... Why Claude Fable 5... For authorized work in cyber security and life sciences, Claude Mythos 5... Claude Fable 5... Data retention and Enterprise Frontier Safeguards Anthropic designates Claude Fable 5... Getting starte...
Today, we are announcing the availability of Claude Fable 5...2 and Claude Mythos 5...2 on Amazon Bedrock and Claude Platform on AWS... Claude Fable 5... Claude Mythos 5... Why Claude Fable 5... For authorized work in cyber security and life sciences, Claude Mythos 5... Claude Fable 5... Data retention and Enterprise Frontier Safeguards Anthropic designates Claude Fable 5... Getting starte...
NVIDIA Nemotron 3.5 Super VL is now available in Amazon SageMaker JumpStart
TutoSartup excerpt from this article:
Super VL is the vision-language model (VLM) in the NVIDIA Nemotron 3... The model pairs a 120B-parameter hybrid Mixture-of-Experts (MoE) language backbone with 12B active parameters and a C-RADIO vision encoder... In this post, we walk through the model’s capabilities and the JumpStart deployment configurations...5 Super VL is a 120B-parameter model with 12B active parameters per token... Tr...
Super VL is the vision-language model (VLM) in the NVIDIA Nemotron 3... The model pairs a 120B-parameter hybrid Mixture-of-Experts (MoE) language backbone with 12B active parameters and a C-RADIO vision encoder... In this post, we walk through the model’s capabilities and the JumpStart deployment configurations...5 Super VL is a 120B-parameter model with 12B active parameters per token... Tr...
Help defend against memory poisoning in Amazon Bedrock AgentCore with multi-layer write validation
TutoSartup excerpt from this article:
Amazon Bedrock AgentCore Memory helps AI agents maintain context across sessions through persistent short-term and long-term memory... Because memory content is automatically retrieved and injected into future conversations, the integrity of what gets written to memory directly shapes future agent behavior, which makes the write path a valuable control point to strengthen... AWS Identity and Acces...
Amazon Bedrock AgentCore Memory helps AI agents maintain context across sessions through persistent short-term and long-term memory... Because memory content is automatically retrieved and injected into future conversations, the integrity of what gets written to memory directly shapes future agent behavior, which makes the write path a valuable control point to strengthen... AWS Identity and Acces...
AWS Weekly Roundup: AgentCore Runtime V2, Amazon DynamoDB bulk put items, and more (November 9, 2026)
TutoSartup excerpt from this article:
AWS Lambda now supports queues for Apache Kafka in self-managed Kafka event sources – You can now process records from a single Kafka partition across many parallel AWS Lambda invocations... AWS contributes a large-transaction binary log optimization to MySQL – With binlog on, a huge transaction holds a global commit lock while its events are copied, blocking every other commit... Upcoming...
AWS Lambda now supports queues for Apache Kafka in self-managed Kafka event sources – You can now process records from a single Kafka partition across many parallel AWS Lambda invocations... AWS contributes a large-transaction binary log optimization to MySQL – With binlog on, a huge transaction holds a global commit lock while its events are copied, blocking every other commit... Upcoming...
Simplify cross-partition access with AWS IAM outbound identity federation
TutoSartup excerpt from this article:
You can now use tokens from AWS Identity and Access Management (IAM) outbound federation to assume roles in other Amazon Web Services (AWS) partitions... When your workloads run across AWS partitions such as Commercial, China, GovCloud (US), and European Sovereign Cloud, a workload in one partition might need to access resources or communicate with AWS services in another partition... AWS partiti...
You can now use tokens from AWS Identity and Access Management (IAM) outbound federation to assume roles in other Amazon Web Services (AWS) partitions... When your workloads run across AWS partitions such as Commercial, China, GovCloud (US), and European Sovereign Cloud, a workload in one partition might need to access resources or communicate with AWS services in another partition... AWS partiti...