AI BriefingLINE news
The latest AI and developer news from LINE, with short summaries.
Visit website →NEWiOS App Size Optimization: Measuring, Diagnosing, and Reducing Bundle Footprint
A technical guide covering four key size metrics, measurement workflows using App Thinning reports, and specific strategies for reducing binary and asset bloat.
LY Corporation developing Service Connect to simplify service-to-service connectivity in Flava private cloud
LY Corporation is developing Service Connect, an internal platform that simplifies service-to-service connectivity in its Flava private cloud by shifting network control from IP addresses to service identities.
LINE Ads engineers build AI agent to automate advertising analytics reports
The system separates LLM interpretation from code-based calculation to ensure accurate daily reports for LINE OA and Display Ads.
LINE Plus Security R&D details SAGE AI platform for human-in-the-loop security operations
The platform uses a three-stage adoption process to reduce response time and consistency variance in security consultations and operations.
LINE Improves iOS Large-Scale Configuration System by Adopting AttributedString Architecture
LINE has released an iOS configuration system that adopts the AttributedString architecture to resolve circular dependency and thread safety issues.
Development of Harmful Content Detection Model Based on Open Chat Titles and Descriptions
LINE built a monitoring system using the Granite Guardian 3.1 2B model to detect harmful content in Open Chats.
Building a Group Video Call Service in the LINE App Using AI Without Web Engineers
This introduces how to use LINE Developers and LIFF to implement an AI-based group video call service without web engineers.
The More Verification, the Faster the Speed: How Flava API Gateway Uses Agents
LY Corporation presented three key practices for maintaining agent code quality during the development of Flava API Gateway.
Make AI Agents Debate: Redesigning the Development Process Through Multi-Agent Collaboration
By splitting AI agents into Proposer and Challenger roles to debate, this approach reduces the human coordination cost that bottlenecks the development process.
Connecting HDFS Clusters at 1EB+ Scale with Different Histories: Challenges and Design Decisions
This covers the operational and design challenges LY Corporation faced while integrating 1EB-scale HDFS clusters with different architectures.
The Evolution of Prompt Engineering: Automated Optimization and Speedup via Genetic Algorithms
Using GEPA, a genetic-algorithm-based approach, prompt tuning work that used to take days has been reduced to just one hour.
In the GenAI Era, Analyzing How Work and Roles Are Changing, Combined with AI Agents
LY Corporation has integrated the fragmented processes of data analysis through its AI agent 'PJ One Piece,' dramatically cutting analysis speed.
From IaC to AI: Adopting OpenTofu and ChatOps
The LINE Plus SRE team shares how they built a GitOps system by adopting OpenTofu and Terragrunt to improve infrastructure management efficiency.
ID-JAG The Hard Way: Learning AI Agent Authorization Through Failure
Learn the ID-JAG authorization approach that helps AI agents securely access APIs on behalf of users through hands-on practice.
Introducing SLI/SLO to Improve Service Reliability - Part 3: Service Application Cases
LINE has summarized how it operates reliability for its messaging, channel, and authentication services using SLI/SLO.
The Future of AI Agent Security, ID-JAG
ID-JAG is a new authorization approach that controls AI agents' API access centered on the IdP.
From Athenz to Kubestronaut: From Necessity to Expertise
Kubernetes learning that started from the need to operate Athenz eventually led to becoming a Kubestronaut.
Using SLI/SLO to Improve Reliability - Part 1: Building an SLI/SLO Framework and Developing LINE Status
LINE presents how it systematically manages organizational service reliability using an SLI/SLO framework and LINE Status.
Visualizing LINE's Android App Critical Path with AI
Using comment tags and AI, the critical path and bottlenecks in Android were quickly visualized.
LY Corporation's Cloud Infrastructure Transition: The Architecture of Flava, a Next-Generation Platform Unifying Two Massive Clouds
**Flava**, which unifies Verda and YNW, has been redesigned around a single pool, VPC by default, and upstream alignment.