AI Briefing
AWS Tech Blog (Korea) news
The latest AI and developer news from AWS Tech Blog (Korea), with short summaries.
Visit website →Real-Time Contextual Advertising Solution Using AWS Elemental Inference
Combining AWS Elemental Inference and Amazon Bedrock to build an architecture that analyzes the context of live broadcasts and places customized ads in real time.
Sajo Systems' Journey to Building Agentic AI Based on In-House ERP Data – Using the Strands Agents SDK and Kiro
Sajo Systems built an Agentic AI that analyzes ERP data and provides insights using the Strands Agents SDK and Kiro.
Miricanvas Improves Search Performance with Amazon OpenSearch 3.3 Upgrade
Miricanvas resolved the stored fields bottleneck and optimized search performance by upgrading to Amazon OpenSearch 3.3.
Miricanvas Introduces Dual Vector Search and Performance Optimization Using Amazon OpenSearch Service
Miricanvas introduced dual vector search based on Amazon OpenSearch Service for 40 million design resources and optimized performance.
PickTurning POSCO DX's Engineering Tacit Knowledge into AI-Usable Knowledge Assets
POSCO DX defined senior engineers' experiential tacit knowledge as UDK that AI has not learned, and verified a method to structure it into a knowledge graph to implement design automation.
How Hanatour Built a Travel Product Planning Agent Using Amazon Neptune and Amazon Bedrock AgentCore
Hanatour used Amazon Neptune and Amazon Bedrock AgentCore to cut travel product planning time from days to minutes.
Building AgentOps with Amazon Bedrock AgentCore (2): Observability, Evaluation, and the AgentOps Lifecycle
This covers AgentOps operations centered on observability, evaluation, and optimization to ensure the quality and safety of agentic AI.
AgentOps Built with Amazon Bedrock AgentCore (2): Observability, Evaluation, and the AgentOps Lifecycle
Covers observability, evaluation, optimization, and the AgentOps lifecycle for ensuring the quality and safety of agentic AI.
Building AgentOps with Amazon Bedrock AgentCore (1): Foundation and Gateway
This article covers the AgentOps architecture and foundation elements for reliably operating agentic AI in production environments.
MEGA MGC Coffee's DB Modernization Case: Migrating Mobile Ordering Service from Amazon RDS for MySQL to Amazon Aurora Serverless v2
MEGA MGC Coffee migrated its DB to Amazon Aurora Serverless v2 to ensure stability and cost efficiency for its mobile ordering service, which experiences highly variable traffic.
Solving Clients' Pain Points with AI: Building a Contest Briefing Agent Using the Strands SDK at Loud Sourcing
Loud Sourcing built an AI agent using Amazon Bedrock and the Strands SDK to help clients write contest briefings.
Analyzing Performance Test Results with AWS DevOps Agent
This introduces how AWS DevOps Agent automates bottleneck identification and report writing after performance testing.
Single LLM Gateway Architecture: Managing Claude Code and Codex in One Place via Amazon Bedrock
A single LLM Gateway architecture makes it possible to unify cost, security, and observability management across various AI coding agents.
Dongwon F&B's Journey to Innovate Shopping Experiences with an AI Shopping Assistant Based on Amazon Bedrock AgentCore
Dongwon F&B leveraged Amazon Bedrock to build an AI agent that goes beyond a simple chatbot to deliver personalized shopping experiences.
Amazon S3 Files, 3 Key Considerations Before Adoption
This analyzes the minimum billing unit and performance characteristics that undermine cost efficiency when adopting Amazon S3 Files.
Building an MCP-Based Cloud Policy Agent with Amazon MWAA and Bedrock AgentCore
This proposes an automated cloud policy management agent architecture based on the MCP standard, leveraging Amazon MWAA and Bedrock AgentCore.
8Percent's Kiro CLI-based Amazon ECS Modernization Journey
8Percent leveraged Kiro CLI and an AI prompt set to rapidly migrate its legacy EC2 environment to Amazon ECS Fargate, cutting operational costs by 76%.
Deep Insight Chatbot Through Inner Loop Engineering – 4 Design Decisions for a Conversational Analytics Chatbot
This covers four core design strategies for building a high-performance conversational analytics chatbot that analysts can use every day.
Building a Pesticide Product Image Recognition System Using Amazon Bedrock Vision LLM and Amazon OpenSearch Service
Kyung Nong built a visual search system that finds pesticide product information from just a photo, using Vision LLM and Amazon OpenSearch.
Using Codex and Claude Code Together on Amazon Bedrock: Implementation via Harness Engineering
This presents an experimental methodology for maximizing development efficiency by combining Codex and Claude Code within the Amazon Bedrock environment.