AI Briefing
AWS Tech Blog (Korea) news
The latest AI and developer news from AWS Tech Blog (Korea), with short summaries.
Visit website →Defending Against Prompt Injection: Multi-Layer Security Design Patterns Based on AgentCore
The security boundary of an LLM agent must be built outside the system, not inside the model.
Sim-to-Real and Real-to-Sim: The Core Engines Enabling Capable Physical AI
Sim-to-Real and Real-to-Sim technologies that narrow the gap between simulation and reality are the core drivers of Physical AI advancement.
PickShinhan Card Builds a Highly Efficient AI Chatbot Using Ontology and Small Language Models
Shinhan Card partnered with AWS to build a next-generation AI chatbot solution leveraging ontology and sLLMs.
Blocking Fraudulent E-commerce Returns with AI: Building an Industry-Specific Guardrail with Amazon Nova Fine-tuning
By fine-tuning Amazon Nova 2 Lite, a Custom Guardrail was built that detects fraudulent return intent in fashion e-commerce with 94.6% accuracy.
Building Building Inspection Intelligence with AWS Spatial Data
Proposes an architecture that uses AWS Spatial Data Management (SDMA) to give inspection data spatial context and improve analysis efficiency.
Running Quantum-Classical Hybrid Algorithms with Amazon Braket (Part 1)
This introduces two ways to run quantum-classical algorithms using Amazon Braket's Hybrid Jobs feature.
Accelerating Physical AI with AWS and NVIDIA: Building Production Applications through Simulation and Real-World Learning
AWS and NVIDIA accelerate Physical AI application development through a dual-path approach combining simulation and real-world learning.
GloZ's Case Study on Building a Natural Language Resume Search System Based on Amazon OpenSearch Service — Part 2: Hybrid Search and Natural Language Query Transformation
This case study covers how GloZ uses Amazon OpenSearch and Claude Haiku to transform natural language queries into search DSL and optimize hybrid search.
Operating NVIDIA OSMO-based Physical AI Workflows on Amazon EKS
This introduces a reference architecture for efficiently operating Physical AI workflows on Amazon EKS using NVIDIA OSMO.
AWS Unified Operations: Building Resilient Operations for Critical Workloads
AWS Unified Operations uses AI and dedicated experts to proactively prevent failures in critical workloads and speed up incident response.
AWS Unified Operations: Building Resilient Operations for Critical Workloads
AWS Unified Operations enhances operational resilience for critical workloads and proactively prevents failures through AI-powered support.
Amazon GameLift Servers Protects Players at All Times with New DDoS Protection Feature
Amazon GameLift Servers has launched a proactive DDoS protection feature optimized for UDP traffic.
Validating a Cross-Account Amazon Redshift Data Sharing Governance Pattern with Amazon SageMaker Unified Studio
This presents the optimal governance pattern for securely sharing cross-account Redshift data in SageMaker Unified Studio while isolating source compute.
HYBE Builds Automated Incident Investigation System Using AWS DevOps Agent and Custom MCP Server
HYBE combined AWS DevOps Agent with Custom MCP to automate the workflow from incident investigation to Jira issue creation.
Reeman Korea Builds a Natural Language-Based Product Search System Using Amazon Bedrock Knowledge Bases
Reeman Korea built a natural language-based product search system using Amazon Bedrock Knowledge Bases, achieving 95% search accuracy.
AWS Interconnect Technology for Distributed Training: An Introduction to High-Speed GPU-to-GPU Communication
This covers the evolution of high-speed GPU-to-GPU communication technology that progressively eliminates CPU intervention to improve distributed training efficiency.
Building Agentic AI for Amazon RDS for SQL Server with Strands and AgentCore
It introduces how to transform existing T-SQL scripts into autonomous database management AI agents using Strands and AgentCore.
Part 3: Automating RDS/Aurora Failure Analysis with Kiro — Receive Daily Automated Reports
With Kiro Database Analyzer (KIDA), you can receive RDS and Aurora failure analysis reports automatically every day.
Part 2: Automating RDS/Aurora Incident Analysis with Kiro — Analysis in the Terminal Environment
Covers how to automate incident analysis for RDS and Aurora in the terminal environment using Kiro Database Analyzer (KIDA).
Part 1: Automating RDS/Aurora Incident Analysis with Kiro — Analyzing in the IDE
Leverage Kiro and MCP to automate incident analysis for Amazon RDS and Aurora within the IDE environment.