AI Briefing
AWS Tech Blog (Korea) news
The latest AI and developer news from AWS Tech Blog (Korea), with short summaries.
Visit website →Cost-Efficient LLM Serving Using GPU Tensor Parallelism on Amazon EC2 G5/G6 Instances
This introduces a method for reducing large-scale LLM serving costs by leveraging GPU Tensor Parallelism on Amazon EC2 G5/G6 instances.
Querying Knowledge Graphs Using the GraphRAG Toolkit
This introduces how to efficiently query information from a knowledge graph built using the GraphRAG Toolkit.
How Hyundai AutoEver Built an Incident Response Automation Agent for Its Big Data Cluster on Amazon Bedrock
Hyundai AutoEver built an incident response automation agent using Amazon Bedrock and LangGraph.
Hyundai AutoEver's Multi-Agent AI on Amazon Bedrock: Cutting Incident Response Time to 5 Minutes
Hyundai AutoEver used LangGraph and Claude to cut incident response time from hours to 5 minutes.
Hyundai AutoEver's Productivity-Boosting Hackathon Using GenAI Sandbox: A Success Story of Innovation and Collaboration
Hyundai AutoEver led AI proof-of-concepts by 14 teams through a GenAI Sandbox and a 4-week hackathon.
How Ccimi combined Amazon IVS with in-house infrastructure to achieve 4K, sub-4-second low-latency live streaming
Ccimi split its architecture between Amazon IVS and in-house infrastructure to achieve 4K low-latency live streaming under 4 seconds.
CJ OliveYoung Builds an AI-Collaborative Development Process and Applies AI-DLC in Practice
CJ OliveYoung implemented 5 projects in a 3-day workshop using AWS AI-DLC.
GloZ's Case Study on Building a Natural Language Resume Search System with Amazon OpenSearch Service - Part 1: Data Pipeline and Indexing
GloZ redesigned its search pipeline and indexing for 100,000 resumes using OpenSearch and Bedrock.
Neubility's Case of Expanding Remote Monitoring Based on Amazon Kinesis Video Streams
Neubility reduced its reliance on port forwarding and expanded remote monitoring externally using Kinesis Video Streams WebRTC.
Introducing Claude Platform on AWS: Use Anthropic's Native Claude Platform with Your AWS Account
Anthropic's native Claude Platform is now available directly with just an AWS account.
How GS SHOP Built a Video-Based AI Product Recommendation Platform
GS SHOP connected video understanding to Shortpick product recommendations.
Agentic AI-Based Platforms - Part 3: Building Enterprise Operations with AgentCore Policy, Evaluation, and Observability
AgentCore introduced how to build enterprise operations using Policy, Evaluation, and Observability.
Applying AI-DLC to Team Projects: The ARMIQ Case, Extended with Subagents and Custom Skills
ARMIQ ran AETL and ACMS in parallel using an AI-DLC that combined Subagents and Custom Skills.
Optimizing a Conversational AI Storytelling Platform with CESC on Amazon ElastiCache for Valkey
Viewcomms used CESC on Amazon ElastiCache for Valkey to cut Tadak v2 image response times to under 100ms and lower generation costs by 35%.
Guide to Amazon GameLift Servers Launch Phases for a Successful Game Launch, Part 2
Before launching on GameLift Servers, teams need to prepare limit increases, load testing, and Blue/Green deployment.
Guide to the Pre-Production Stage for a Successful Game Launch with Amazon GameLift Servers - Part 1
This article summarizes server testing, session, and observability standards to review before adopting Amazon GameLift Servers.
DelightRoom's Case Study on Streamlining Multi-Cluster Operations with Amazon EKS Auto Mode
DelightRoom migrated 5 clusters to EKS Auto Mode, significantly reducing operational burden.
Introduction to AWS Interconnect Technology from a Distributed Training Perspective - GPU-to-GPU Communication Using NCCL in AWS Environments
The article explains how NCCL optimizes GPU collective communication on top of AWS EFA.
Self-Managed Agentic AI Platform Operated on Amazon EKS: Achieving Operational Stability Through Infrastructure Automation and Observability
Automated Agentic AI operations using Amazon EKS Auto Mode, Bifrost, and Langfuse.
Optimizing Amazon EC2 Costs with Grafana k6
Compared performance and cost efficiency across 7 EC2 types using Grafana k6 and Monte Carlo simulation.