The team completed work that would have taken 23 business days manually in 3.5 days, expanding the scope of regression testing.
Built a 5-stage automation pipeline that extends from specification input to defect registration.
Curry has built a daily automated deployment pipeline for recommendation models using Argo Workflows and SageMaker.
Shares the process of building an AI system that efficiently delivers domain knowledge by combining LLM Wiki and RAG.
Kurly has developed an On-device system that compares the similarity of delivery-completion photos to detect mis-deliveries in real time.
By automating repetitive tasks with Claude Code, the structure of the day and the way decisions are made were transformed.
After 148,000 AI conversations, the conclusion is that productivity depends on orchestration, not usage volume.
Parallel-orchestrate AI work with the Obsidian memory system, Task DAG, Branch Hunt, and Ralph Loop.
To overcome the limitations of the Nx 18 and Bun combination, they upgraded to Nx 21.4+ and Bun 1.2.x.
It uses the Outbox pattern and retries to safely synchronize external inbound-schedule information.
A 4-person, 12-MSA team built role separation and Context standardization using Claude AI.
Kitchen was converted into a single ESM package to improve tree-shaking and DX.
This piece organizes how to use Claude Code predictably by compensating for LLM cognitive limits with systems.
Kurly uses Tech Specs to speed up reviews and collaboration, and is experimenting with AI to automate drafting.
Stabilized spike settlement using Kafka Streams windows and a timestamp extractor.
A legacy CMS collapsing under OOM errors was migrated to Vite, dramatically improving both build and development speed.
Kurly introduced a Collaborative Embedding model with Knowledge Distillation applied, achieving approximately 140% ARPU increase on sale pages.
Kurly reduced delivery-completion photo inspection costs by 93% using a YOLOv11-based object detection model.
Kurly's Fintech Group adopted a NestJS and GraphQL-based BFF to boost frontend productivity and block the impact of backend changes.
Kurly developed an AccessBlock system that blocks service maintenance access at the application level without nginx permissions, and improved performance with Redis caching.
This introduces the frontend and backend implementation logic and Redis data management approach for the AccessBlock system, which blocks access during service maintenance using Vue.js routing and Spring AOP.
Kurly introduced the AI assistant Jarvis, which integrates Gemini and MCP, to shorten error response time.
The Delivery Platform Development Team developed its own encryption module, cowcow-enc, to resolve Hibernate 6.x compatibility issues and reduce data size.
Kurly's OMS team secured stable order processing and deployment efficiency with a small workforce through a Shared Cache architecture and MSA separation.
AI Briefing