AI Briefing#kakaopay
The latest AI and developer news about #kakaopay, with the original source and a short summary.
The latest AI and developer news about #kakaopay, with the original source and a short summary.
KakaoPay Insurance safely removed legacy modules in production and laid the groundwork for a Spring Boot upgrade using an AOP-based Shadow comparison strategy.
A KakaoPay developer summarized essential concepts for adopting AI Agents, including the difference between LLMs and Agents, the ReAct pattern, tokens, and context windows.
Toss and Kakaopay shared TAM's role in connecting technology and business, along with its problem-solving approach, at TAM CONNECT 2025.
Multiverse is an in-house platform that lets you spin up virtual devices from a single MacBook to help with app testing and log checking.
A team of non-developers from Kakaopay used **AWS Gen AI** to build a facial recognition-based hyper-personalized kiosk, winning 3rd place at a hackathon.
Kakaopay has developed 'Pageny,' a financial AI concierge that uses a multi-agent architecture based on AWS Bedrock.
Kakao Pay's CreditClan team used AWS Bedrock to develop a personalized AI loan coach service for users.
KakaoPay adopted **MCP** to efficiently connect AI agents with its payment API, and developed a multi-framework **Agent Toolkit**.
The Kakao Pay team used AWS AI services to develop the 'Geum.Yong.Sa.' service, which explains difficult financial terms and recommends related products.
The Kakaopay development team built AIVA, an AI recruiting assistant that analyzes resumes and technical assignments, through a hackathon.
Shares hands-on experience analyzing and resolving CORS errors and Version Skew issues occurring in a Next.js SSR environment.
Kakao Pay shares the process of internalizing its credit core system by applying DDD to efficiently manage its complex credit business.
Kakaopay Securities built a multi and hybrid cluster environment using AWS, IDC, and KakaoCloud to achieve 99.999% service availability.
Kakao Pay implemented a voice consultation chatbot that recommends personalized loan products using AWS AI services.
Using AI, a financial management service was implemented that visualizes transaction history as an image calendar and supports natural language search.
KakaoPay shares the cluster configuration and incident response know-how it gained while operating **Apache Pinot**, a real-time OLAP solution.
KakaoPay held its in-house hackathon '2025 CafeTon' offline, leveraging AWS Generative AI.
This post covers the process of adopting Ktor to fit KakaoPay's development environment and configuring an API server.
Kakao Pay developed a feature flag platform utilizing Redis Pub/Sub and Polling for real-time data synchronization between the admin and serving servers.
Kakao Pay shares the SDK selection criteria and Geocoding optimization methods it encountered while developing location-based services using MapKit.
Kakao Pay analyzed how JPA's @Transactional settings affect DB performance and improved query performance by removing unnecessary transactions.
This covers the practical lessons learned from adopting and then removing Hexagonal Architecture during KakaoPay's Home server overhaul.
KakaoPay's Information Platform Team shares their case and benefits of adopting Spring Cloud Stream for data composition and pipeline processing.
Kakao Pay introduced an adaptive ML model to its FDS that continuously learns and adapts itself to respond to changing fraud patterns.