This covers a strategy for managing domain knowledge as a graph-structured asset so that AI doesn't create duplicate features.
Socar's Modu-ui-Jucharjang built a LangGraph-based AI agent system that automatically recovers from discount-application failures across 50+ external equipment vendor websites.
This covers cache policies and fallback strategies to prevent ChunkLoadError when deploying SPAs using S3 and CloudFront.
They rolled out the system by separating UI and logic, using rollup tree-shaking, and running AGENTS.md and llms.txt.
By combining Figma integration with operational processes, the design system was turned into a repeatable framework.
Starting from 0% test coverage, they safely improved 6 years of legacy by changing code, ERDs, and documentation.
When PID 1, the Node event loop, and K8s termination policy overlap, shutdown hooks alone aren't enough.
Socar simplified in-app vehicle control using BluetoothHost and BluetoothRemote abstractions.
Socar standardized development rules with Socarframe to boost both speed and stability.
Matrix parallelization and pre-checking cache status reduced monorepo CI time by up to 84%.
QA API automation was built in 1 month using GitHub Actions instead of Jenkins.
The S3+GCS batch pipeline was transformed into a near-real-time structure based on MSK and Protobuf.
By combining precipitation forecasts with vehicle location data, unnecessary car wash requests were reduced.
AI Briefing