Built 37 screens in 25 weeks by reusing the flight team's foundation
Strengthening One-Team culture through a retro-themed competition featuring 8 teams and futsal
Accuracy improved by 3–9%p through LLM-as-a-judge and MCP specification optimization, applied to three internal services.
Yeogi-eottae combined LightRAG, based on GraphRAG, with Navigator, which reflects document hierarchy, to improve internal document search accuracy to 84%.
Yeogi-eottae's Exhibition Development Team built a shadowing verification dashboard using Grafana and Prometheus, reducing verification resources during API migration through common libraryization.
To address AI non-determinism, we developed an MCP-based ERD tool where AI handles design and the tool handles rendering.
Sharing a case study on improving internal observability and fostering contributions by leveraging existing infrastructure and AI agents.
To address the surge in outputs and 'intent debt' caused by AI adoption, the article proposes elevating decision-making processes into guides and sharing context through team reviews.
Yeogi-eottae Company has built an internal deployment platform called 'Vibedog' for non-developers, which is currently being used by 58 teams across the company.
Yeogi-eottae used an AI agent to process 280 QA tickets for its overseas tour service, increasing the same-day resolution rate to 56% compared to previous projects and shortening lead times.
The aviation frontend team shared how they manage file impact scope using folder name prefix symbol rules instead of adopting FSD.
A case study on managing state using React Query and URL state without adopting global state libraries when building an airline frontend.
We built an authentication architecture that unifies disparate token ingestion paths from web and app webviews into httpOnly cookies, resolving timing issues.
By applying the immutable source principle and MOC structure to a personal LLM wiki, AI context-linking errors were reduced and the reliability of work memory was improved.
This article summarizes the rendering, query, and incremental lookup optimization process encountered while implementing a 100k-point scatter plot using a custom Grafana plugin.
Yeogi-eottae built an APM scatter chart by integrating OpenTelemetry and ClickHouse to visualize the distribution of individual requests.
The Yeogi-eottae QA team shared how their verification methods and perspectives changed when transitioning from exhibition QA to reservation and settlement QA.
The Yeogi-eottae design team developed a builder that automates the introduction creation process by combining AI with existing SOPs.
Yeogi-eottae achieved an increase in purchase conversion rate through an A/B test involving approximately 1 million users by improving home screen seller cards based on the JTBD framework.
Yeogi-eottae conducted a project to address low click-through rates on its home screen by redefining module roles rather than product card formats and validating new navigation experiences through A/B testing.
The Service Web Development Team combined ATDD and AI agents to preemptively block 1,717 defects before QA began.
The periodic memory spikes occurring after the EKS migration were confirmed to be caused by log compression and page cache.
The SRE team at Yeogi-eottae Company built Alert Adviser, which uses AI to analyze Grafana alerts and automatically trace incident root causes and impact scopes.
The Yeogi Eottae SRE team combined AI and code to automate infrastructure cost estimation and EKS node scaling predictions.
AI Briefing