MUSINSA used its campaign meta-engine to automatically optimize over half of the hundreds of millions of messages sent monthly.
MUSINSA has developed the DeciML and NeXA platforms to handle decision-making and discovery beyond prediction.
A Mushinseok developer identified three judgment limits when working in parallel with AI agents.
The introduction of a shared queue reduced iOS run time from 25 minutes to 12 minutes.
Resolved check-in failures caused by indoor GPS errors by customizing coordinates and radii per store.
Resolved a connection pool exhaustion outage caused by stdout buffer saturation using a custom Appender, achieving both asynchronous logging and trace_id preservation.
Musinsa's Retail Platform QA team reduced regression testing time from one day to 30 minutes by introducing Playwright and an AI-based test case generator.
Musinsa improved CTR by 21.3% by applying knowledge graph-based unified embeddings to personalized push notifications.
We validated a method for sharing domain knowledge among AI agents using a two-layer semantic layer composed of a standards-based Core and an organization-specific Overlay.
MUSINSA announced that it has redesigned the entire development process from planning to deployment by adopting AI.
Musinsa's MATCH Console and AI assistant MAI integrate operator workflows from data exploration to execution into a single flow.
This introduces MATCH, the decision-making engine Musinsa built to go beyond simply accumulating data and drive actual business outcomes.
Musinsa introduced Prompt Caching and cut LLM API costs by 64% while achieving a 98% cache hit rate.
MUSINSA used **Geometric Prior** instead of a VLM to boost clothing detail shot generation speed by **25x**.
Musinsa automated everything from slow query analysis to PR reflection with query-engineer.
Musinsa integrated four retail tech systems into Megastore Seongsu, keeping them hidden behind the experience.
Beyond AI scores and guides, human judgment in interviews was what truly separated real understanding.
By harnessing an AI agent, a system was built and refined to automatically grade submissions from over 400 people.
By splitting documents and rules into smaller injections, Gemini-based TC automation became a practical part of daily work.
To reduce wait times, Self-POS was designed by rebuilding state management, validation, and hardware from the ground up.
Musinsa's iOS team used AI to mass-generate tests, raising coverage from 9.82% to 79%.
Field research and AI-driven design together solved payment speed, membership conversion, and global support.
Musinsa introduced an AI review summary feature based on an open-source model to efficiently deliver its vast volume of product reviews to customers.
Musinsa selected 66 rookies through its AI-native new hire recruitment.
AI Briefing