AI Briefing
AWS Tech Blog (Korea) news
The latest AI and developer news from AWS Tech Blog (Korea), with short summaries.
Visit website →Optimizing Claude Code Token Costs: Cache Hit Rates and Session Management Strategies
Since Claude Code charges proportionally to context size, costs should be optimized by improving prompt cache hit rates and appropriately using session management commands such as /clear and /compact.
I'mweb Redesigns Service Network and Optimizes Costs with Amazon VPC Lattice and Kong
I'mweb redesigned its service network by introducing VPC Lattice and Kong Gateway to resolve ALB quota issues.
ZEP Enhances Educational Quiz Generation Architecture with LangGraph on Amazon Bedrock AgentCore
ZEP has introduced a step-by-step quiz generation architecture combining LangGraph and Amazon Bedrock AgentCore to overcome the limitations of single-prompt approaches.
Samsung Electronics Migrates LangGraph-Based TV App Data Query Agent to Production with Amazon Bedrock AgentCore
Samsung Electronics migrated its LangGraph-based natural language query agent to Amazon Bedrock AgentCore to resolve production operational challenges.
AWS Lambda Expands to Four Execution Models, Supporting Workflows Up to One Year and Code Sandboxes
AWS Lambda has expanded to a total of four execution models by adding three new options—always-on, long-running workflows, and code sandboxes—alongside the existing per-invocation execution model.
AWS FinOps Agent Automates Investigation from Cost Anomaly Alerts to Root Cause
AWS FinOps Agent automatically identifies root causes and responsible parties by correlating cost anomaly alerts with CloudTrail.
AWS DevOps Agent's Release Management Autonomously Validates Pre-Deployment Risks
AWS DevOps Agent's Release Management autonomously validates pre-deployment risks to prevent incidents.
AWS Security Agent: On-Demand Security Validation via Context-Aware Multi-Stage Penetration Testing
AWS Security Agent validates security changes in daily-deployed applications in real time through multi-stage penetration testing based on source code analysis.
Forward Deployment of Amazon QuickSight Analytics in Air-Gapped Environments
It presents a method for forward deployment of QuickSight analytics from RND to PRD in air-gapped environments within the financial sector.
LG CNS Case Study: Designing and Automating APQR Systems with Agentic AI
LG CNS reduced APQR report creation time from 12 hours to 1 hour by leveraging Agentic AI.
Guide to Deploying Edge AI Environments Using DEEPX DX-M1 NPU and AWS IoT
This guide demonstrates how to consistently deploy AI models to edge devices by combining the DEEPX DX-M1 NPU with AWS IoT.
Demand Patterns Choose Demand Models: Agentic Demand Forecasting with Amazon Connect Decisions
Amazon Connect Decisions introduces an agentic demand forecasting approach that automates everything from SKU-level pattern diagnosis to model orchestration.
Using Codex on Amazon Bedrock
This guide explains the architecture and security configuration for supporting GPT-5.6 via Bedrock Mantle in Codex.
PolicyGuard on Amazon Bedrock: A Pre-Model Semantic DLP Framework for Coding Assistants
Introducing PolicyGuard, a Pre-Model DLP framework that prevents sensitive information leakage in coding assistant prompts.
Deploying a Data Analysis Agent Built with Claude Code to Production Using Amazon Bedrock AgentCore
This article introduces the process of deploying an agent developed with Claude Code to production using Amazon Bedrock AgentCore.
GS Neotek's Adoption of Claude Code on Amazon Bedrock: Lightweight User Control Without an LLM Gateway
GS Neotek proposed a lightweight architecture that controls per-user costs using Amazon Bedrock logs without an LLM Gateway.
Boost Team Productivity with New Team Member Kiro Crew
This article introduces how to onboard AWS's open-source Kiro Crew to your team to automate issue triage and PR reviews.
Automating Live Streaming Ad Operations with AI-Based SCTE-35 Auto-Insertion
AWS presents an architecture that automates SCTE-35 ad signal insertion in live streams using AI screen recognition technology.
Building an Internal Knowledge MCP Gateway at Silicon2
Silicon2 built an MCP-based knowledge gateway to allow AI to safely utilize distributed internal knowledge.
Resolving Two Blind Spots in Amazon Bedrock LLM Gateways: Caller Identification and Model Governance
This article presents solutions for resolving caller identification and model governance blind spots caused by LLM gateways when adopting Amazon Bedrock.