AI Briefing#oliveyoung
The latest AI and developer news about #oliveyoung, with the original source and a short summary.
The latest AI and developer news about #oliveyoung, with the original source and a short summary.
The article shares how PMs use AI to automate repetitive tasks, allowing them to focus on planning and judgment.
Olive Young will host its first tech conference, define:OMNI, for free in Seongsu on November 19.
Achieved 99% consistency in a 10-year-old back-office system by cross-verifying source mismatches with AI classification and decompilers.
Olive Young enabled order cancellations during the 'Preparing for Shipment' stage, reducing customer service inquiries by 90% compared to normal levels.
Olive Young shared the necessity and design philosophy of a transitional architecture that introduced CDC and Kafka to a low-traffic SMS system.
Olive Young unveiled an alignment learning approach that simultaneously improves the naturalness and format compliance of AI Pick recommendation cards by leveraging NLL metrics.
Olive Young's global store development team utilized AI tools and parallel development methods to implement a Cycle Counting feature for LA stores as a PoC in just 3 days and applied it on-site.
Olive Young improved the scalability and performance of complex delivery logic by applying the Strategy Pattern and Composite Pattern.
Olive Young improved customer convenience by changing the cancellation deadline from the logistics task assignment time to the picking completion time.
Olive Young launched a dedicated ChatGPT plugin and revealed a prompt optimization strategy where PMs and developers collaborated to reduce LLM parameter misinterpretation.
Olive Young completely redesigned its existing, complex POS payment structure in order to reduce checkout time.
Oliveyoung shares a case study on building a unified back office in a micro frontend environment that uses various frameworks.
Oliveyoung redesigned its pipeline with an event-driven architecture (EDA) to resolve the delays and inefficiencies in inventory data processing that arose during omnichannel expansion.
Olive Young experimented with AI as a collaboration partner across the entire development process—not just code generation—through an AWS AI-DLC workshop.
By building a system that judges the optimal fulfillment center in real time between OMS and WMS, the company cut delivery lead time by 14 hours.
By using Partitioning, batch processing time was reduced from 13.5 days to 5 minutes, and Serverless v2 cut costs by 40%.
Olive Young optimized its review theme recommendation system by building a Gemma 3-based sLLM in a constrained environment with just one T4 GPU.
It explains how to use TypeScript's generics to preserve type information while improving code reusability.
To solve the data latency problem of its existing ODI-based batch system, Oliveyoung built a hybrid CDC architecture leveraging OGG and Kafka.
Oliveyoung built an environment that allows simultaneous installation of development and production apps on a single device by separating app identifiers.
Olive Young built a serverless on-call system using Amazon SES and Connect instead of an external solution, cutting operating costs by 95%.
Oliveyoung's QA team participated as an official sponsor of the 2025 QA Korea Conference, sharing the team's vision and quality culture.
Oliveyoung's QA team used AI tools to produce a 25-minute video training staff on incident response processes.
This introduces the delivery agency API integration method and failure response strategy for the stable operation of Olive Young's Oneul Dream service.