AI Briefing
AWS Tech Blog (Korea) news
The latest AI and developer news from AWS Tech Blog (Korea), with short summaries.
Visit website →Indexing Knowledge Graphs with the GraphRAG Toolkit
The GraphRAG Toolkit builds a knowledge graph and vector index by extracting sentences, entities, and facts from documents.
Simulating an Expert Team with Agentic AI and Amazon Bedrock AgentCore
AWS implemented a dynamic swarm combining 7 expert agents on top of AgentCore.
Case Study: Transforming an Enterprise IdP Solution into SaaS with AWS SaaS Builder Toolkit
AirCUVE transformed V-FRONT into a multi-tenant SaaS and listed it on AWS Marketplace using SBT in just 3 months.
Deep Insight Through Harness Engineering: A Design Journey from Local Development to Production Operations
Deep Insight isolated agent execution from code execution by separating AgentCore Runtime and Fargate.
A Case Study on Improving Miricanvas's Query Performance through Amazon DocumentDB Index Optimization
Miricanvas shares the index optimization problems and solutions it encountered during its transition to Amazon DocumentDB.
Miricanvas Improves Performance by 50% and Cuts Costs by 30% with Amazon DocumentDB
Miricanvas dropped MongoDB Atlas for DocumentDB, cutting p50 latency in half and reducing costs by 30%.
Eximbay's AX Standardization Journey Based on AWS Kiro
By centering on Kiro and combining three layers—execution, generation, and accumulation—Eximbay standardized organizational AX.
Simplifying AWS resource troubleshooting with Amazon Bedrock Agents and AWS Support Automation Workflows (SAW) Part 2 - A hands-on guide to integrating various runbooks
Attach a new SAW runbook to a Bedrock Agent to automatically diagnose CloudWatch Agent issues.
TOrder's Text2SQL Agent 'TSpoon' Case Study
A Bedrock/Athena-based Text2SQL agent implements natural language queries with dual approval.
GS Retail Innovates Operations Automation with AIOps Agent
AIOps Agent autonomously combines 7+ tools to cut incident analysis time by 93%.
Troubleshooting Amazon EFS NFS I/O Hang: Its Relationship with Security Group Outbound Rules
During EFS maintenance, if the new server's RST is blocked on Outbound, NFS I/O hangs for 1-2 minutes.
Introducing AWS Interconnect Technology from a Distributed Training Perspective - AWS's Interconnect Foundation Technology, ENI
You need to understand AWS's ENI structure and allocation rules to properly unlock EFA performance.
Amazon Aurora PostgreSQL Improves Vector Search Performance and Relevance with pgvector 0.8.0
pgvector 0.8.0 in Aurora PostgreSQL significantly boosts the speed and recall of filtered vector search.
AMOREPACIFIC Applies AI to SAP Development with Kiro IDE
AMOREPACIFIC attached AI to legacy SAP development using Kiro IDE with MCP and Steering.
Analyzing Blueprints Like an Expert Engineer with Agentic Workflow
An AI agent analyzed CAD drawings in 10 minutes, replacing 2-3 days of work.
Efficient Large-Scale Distributed Training of Superb AI's Vision Foundation Model 'ZERO' with Amazon SageMaker HyperPod
SageMaker HyperPod improved ZERO training efficiency by separating low-cost rehearsals from the Training Plan.
Yanolja's Case Study: Building AIOps Agents with Strands SDK and Bedrock AgentCore
Yanolja built 6 AI Agents in 6 weeks, reducing operational work time by more than 50%.
Beyond the Context Window Limit - Practical Context Engineering Techniques Learned from the Deep Insight Development Journey
**Deep Insight** overcomes the **200K Context window** limit through multi-agent design, prompting, and file externalization.
Config Builds a Large-Scale RFM Data Pipeline on Amazon EKS Spot
By moving from SQS+Lambda to an EKS Spot-based setup, they achieved 70-90% cost savings and improved processing speed.