AI Briefing
AWS Tech Blog (Korea) news
The latest AI and developer news from AWS Tech Blog (Korea), with short summaries.
Visit website →AWS Lambda Web Functions: Billing Based on Active CPU Time and Support for 128 Concurrent Requests
A cost reduction of approximately 66% compared to existing solutions is confirmed for LLM streaming processing.
Amazon MSK Express Kafka Transaction Bottleneck Analysis and Optimization Guide
Confirmed that the MSK Express Kafka transaction bottleneck lies in the coordinator and presented an optimization sequence.
AWS PCS Provides Zero-Downtime Upgrades and Inter-Queue Node Sharing Compared to ParallelCluster
AWS PCS reduces HPC operational burden through zero-downtime upgrades and inter-queue node sharing.
eagworks migrates LangGraph workflows to AgentCore Runtime, reducing TTFT p95 by 5.5 seconds
Migrated LangGraph workflows without rewriting to mitigate high-concurrency latency.
iAWorks Builds Agentic AI PoC Validation and Evaluation Framework with Amazon Bedrock AgentCore
Validated complex query processing and a 60% reduction in response time by integrating LangGraph supervisor structure with AgentCore tools.
Search OS Doubles Ringtey's Organic Search Purchase Revenue and Boosts GS SHOP AI Purchases by 4.5x with AWS-Based SEO/GEO
Search OS achieved over 2x growth in Ringtey's organic search purchase revenue and a 4.5x increase in GS SHOP AI purchases using its AWS-based SEO/GEO solution.
Solving the Max-Cut Problem with PennyLane-Based QAOA: Amazon Braket Hybrid Jobs Implementation Guide (Part 1)
This article explains the code structure and principles of the maxcut_qaoa module for solving the Max-Cut problem using QAOA, step by step.
PickW Concept Completes Modernization of 1.6 Million Lines of .NET 10 in 7 Weeks Using AWS Transform and Kiro
A hybrid strategy using AWS Transform and Kiro reduced migration effort by 90%.
Configuring Self-Hosted Grafana Webhooks to Trigger Automatic Investigations with AWS DevOps Agent
The Grafana 12.0 Webhook feature sends alerts to the DevOps Agent to trigger automatic investigations.
Uber Achieves 52% Reduction in Per-Session AI Agent Costs Through Cost Structure Analysis and Optimization
This article summarizes Uber's case study on reducing AI agent costs and strategies for measuring and optimizing token costs using Amazon Bedrock.
Guide to Operating Isolated AI Agents on AWS EKS: NetworkPolicy, Warm Pool, and gVisor Performance Analysis
Using a Warm Pool reduces gVisor sandbox startup time to approximately 57ms, eliminating runtime differences.
Break-even Analysis of AWS Direct Connect Flat-rate Pricing: Seoul Region
For the Seoul region, flat-rate pricing becomes cheaper than pay-as-you-go when monthly data transfer out exceeds 114 TB with a port-pair configuration.
SD Biosensor Productionizes Conversational Data Analysis Agent with Amazon Bedrock AgentCore
Transitioned from multi-agent to single-agent architecture to ensure reproducibility and observability.
CJ Olive Young Builds Operational Automation with AI Agents on Amazon Bedrock
Reduced incident analysis time from 1-2 days to approximately 5 minutes and automated daily checks.
PickSocar Modu Parking: Developing a Voice Parking Service in Two Days via AI-DLC Workshop
Socar Modu Parking developed a voice parking MVP in two days using the AI-DLC methodology and launched its beta in September.
Automating VOD Chapter Generation with AWS Elemental MediaConvert and Amazon Bedrock
Combines MediaConvert shot transition data with Bedrock to automatically generate chapters without separate analysis infrastructure.
Lotte Department Store Builds 'AI Biz Center', a Partner Proposal AI Agent Based on Amazon Bedrock
The number of proposal submissions increased by 160% year-over-year, and 25% of customers utilized the AI writing feature.
AWS ParallelCluster and Teamcenter Integration Shortens Simulation Cycles from Days to Hours
Integration of Siemens Teamcenter and AWS ParallelCluster eliminates HPC queue bottlenecks while maintaining data traceability.
Lawfirm Develops 'Minbungi' VoC Automated Investigation AI Agent at AWS-Supported Hackathon
The agent, deployed on the day of the hackathon, aims to reduce VoC tasks that previously took 39 hours per month down to 8 hours.
Hanwha Ocean Adopts AWS-Based AI Translation App OTalk to Bridge Communication Gaps in Shipbuilding Sites
Achieving approximately 96% usage among direct foreign personnel, the app bridges communication gaps with shipbuilding-specific translation.