AI - LINE | Techlist.io

lineApr 24, 20264 min readCurated summary

ODW #4: From Copilot to Pilot, Automating from Implementation to PR with Agentic Coding

LY Corporation’s Orchestration Development Workshop promotes a shift from using AI as a code suggestion tool to using it as an autonomous development “pilot.” The team combined specification-driven development with Jira/Confluence access through MCP so AI agents could investigate requirements, plan implementations, write code, run checks, create pull requests, and respond to reviews. The approach improved development speed and planning, but still requires humans to review AI-generated code and retain responsibility for product quality. ## From Copilot to Agentic Coding - The team initially used GitHub Copilot for small code-generation tasks but saw limited productivity gains. - Two developments enabled a broader shift: - Existing requirements and design documents supported specification-driven development. - Jira and Confluence became accessible to AI coding tools through the Model Context Protocol (MCP). - Agentic coding gives an AI agent a high-level goal, which it decomposes into tasks and executes iteratively. - Unlike autocomplete tools, an agent can analyze the broader codebase, run commands and tests, fix lint errors, and continue until the requested feature is complete. ## Workshop Goals and Human–AI Responsibilities - The workshop focused on automating the process from implementation through pull-request creation. - Humans remained responsible for: - Defining requirements and writing specifications - Final testing, review, and release decisions - AI was assigned: - Implementation planning - Code implementation - Pull-request creation - Initial review and review-response work - This division preserved the existing development process while giving participants practical experience with agentic workflows. ## Stage 1: Research and Implementation Planning - Participants supplied a Jira ticket URL to a custom slash command. - The AI agent: - Retrieved Jira data through the Jira MCP tool - Followed Epic links and collected related tickets - Retrieved Confluence documentation through the Confluence MCP tool - Explored the codebase, using an Explore Agent where available - Wrote a detailed implementation plan to `specs/{ticket-or-topic}/plan.md` - The plan included requirements, affected components, technical analysis, implementation tasks, risks, testing considerations, and a checklist. - Saving the plan to a file made it available for human review, future sessions, and later PR generation. - The team emphasized planning early because vague instructions can lead to incorrect implementations and costly rework. ## Stage 2: Implementation and Pull-Request Creation - The reviewed plan was passed to an implementation command. - The AI was instructed to: - Understand the plan and implementation scope - Modify the code - Add or update tests - Run the test suite - Run linting and build commands - Fix any resulting problems - Explicitly listing these steps encouraged the coding agent to maintain a task checklist and complete the full development cycle. - A separate PR command generated the pull request using the team’s template. - Information gathered during the planning stage could be reused in the PR description, reducing administrative work. ## Stage 3: AI Review and Issue Resolution - An AI screening-review command analyzed the generated PR. - It also read existing comments, including: - The AI’s own prior review comments - Comments from other team members - The agent identified issues requiring changes and explained its assessment of existing comments. - After a human reviewed those conclusions, the AI could implement the necessary fixes, reducing the cost of responding to review feedback. ## Benefits and Risks - **Higher code-generation speed** - Agents can work with less frequent human intervention. - Developers can perform other tasks while agents work. - Multiple agents can potentially run in parallel. - **Earlier risk discovery** - Detailed implementation plans clarify the work before coding begins. - Planning can reveal overlooked tasks, dependencies, and risks. - **Greater review burden** - AI can generate large volumes of code that humans must still inspect. - The unfamiliar workflow may create stress for developers. - **Human accountability remains essential** - Developers are responsible for the quality of AI-generated code. - Poor-quality output increases reviewer workload and can add technical debt. ## Workshop Results - The workshop was delivered twice: - A hands-on practical session requiring prior preparation - An introductory session with more detailed support - Approximately 2,500 people participated. - More than 40% of respondents had already applied, or intended to apply, some aspect of the workshop. - The sessions provided concrete guidance on MCP server usage and effective ways to delegate coding tasks to AI agents. The recommended approach is to introduce agentic coding incrementally: keep human ownership of requirements and final quality decisions, while allowing AI to handle structured planning, implementation, testing, PR creation, and initial review.

Read original

AI Model Context Protocol Github Copilot Agentic Coding+4

lineApr 15, 20264 min readCurated summary

ODW #2: Developing Single/Multi-Agents with ADK and Integrating with Internal Systems

AI adoption can improve productivity, but relying on individual developers to create and refine local AI agents leads to knowledge silos, duplicated effort, and uneven results. LY Corporation’s Orchestration Development Workshop addresses this by teaching engineers to build shared single- and multi-agent systems with Google’s Agent Development Kit (ADK). The workshop combines theory with hands-on integration of agents and internal tools such as Jira and Confluence through MCP. ## Organizational Need for AI - Potential applications include pull request reviews, customer support, and internal document search. - Information is difficult to find because company knowledge is distributed across systems such as Jira and Confluence. - LY Corporation aims to double work productivity within three years through AI and continuous innovation. - As tools such as Cline and Claude Code spread, usage remains concentrated among individuals. - This creates: - Productivity gaps between employees - AI knowledge silos - Repeated prompt-development work across teams - Limited awareness of multi-agent approaches - Abandonment of AI when single agents cannot handle complex tasks ## Why a Hands-On Workshop The organizers concluded that organization-wide adoption required practical understanding of three areas: - The strengths and limitations of single-agent and multi-agent systems - A team-based model for building and sharing centralized agents - Integration between AI agents and internal systems through the Model Context Protocol (MCP) Rather than teaching only concepts, the workshop required participants to build working agents with ADK. ## Single-Agent and Multi-Agent Systems - **Single agents** - Use one LLM and are relatively inexpensive and simple to develop. - Work well for straightforward tasks. - Struggle with complex problems requiring multiple specialties. - **Multi-agent systems** - Divide work among multiple specialized LLM-based agents. - Can handle more complex workflows and optimize tasks more effectively. - Require more development effort and token usage. - Must be designed carefully to avoid usage limits and excessive costs. ## Introducing Google ADK - ADK is open-source software for defining agent behavior and building multi-agent systems. - It supports Python, Java, and Go. - Python functions can be exposed as tools that agents invoke. - Teams can build and host shared agents, reducing the need for every employee to independently optimize prompts. ## Building a Single Agent Participants practiced: - Running an ADK web UI and interacting with an agent in a browser - Modifying instructions to change agent behavior - Connecting a prepared Python function as an executable tool The exercises demonstrated that prompts can flexibly control responses and that ordinary Python code can be integrated into an agent with relatively little effort. ## Connecting Agents to Internal Systems with MCP - MCP is an open standard for connecting LLMs to external systems. - It enables agents to actively search sources such as previous inquiries, documentation, Jira, and Confluence. - Participants learned that merely exposing tools is insufficient; the agent also needs clear instructions to use them effectively. - Giving one agent too many tools can enlarge its context, slow responses, and reduce accuracy. - Splitting responsibilities across multiple agents can help isolate context and mitigate these problems. ## Building a Sequential Project Tracker The main exercise created a project-tracking system that analyzes Jira projects and produces translated progress reports. - Four agents execute sequentially: 1. Analyze in-progress tasks 2. Analyze todo or unstarted tasks 3. Generate a consolidated Markdown report 4. Translate the report into the configured language - The first two agents use Jira through MCP. - The report generator synthesizes the preceding analyses. - The translator preserves the report’s formatting and structure. - ADK’s `SequentialAgent` coordinates the workflow and passes results between specialized agents. ## Practical Recommendation Organizations seeking broader AI adoption should move beyond individual experimentation. Shared agents built with ADK, connected to internal systems through MCP, can consolidate expertise, reduce duplicated prompt work, and make multi-agent workflows accessible to entire teams.

Read original

AI Kubernetes Model Context Protocol Python+4

lineApr 10, 20264 min readCurated summary

Clearing Review Bottlenecks with AI - Transforming Review Culture with PR Review Support and Internal Workshops

Orchestration Guild member Fukuyama describes how Yahoo! Places addressed PR review bottlenecks by combining AI assistance with standardized processes and team culture. Reviews had become concentrated among a few engineers, creating delays and forcing a trade-off between speed and quality. The team introduced Claude Code–based screening reviews, then expanded the approach into a broader system for improving PR creation, review accuracy, and continuous improvement. ## PR Review Bottlenecks - In late 2024, review responsibilities were concentrated on the tech lead and one other engineer. - Reviewers were simultaneously implementing features and reviewing code, causing PR queues to grow. - The main problems were: - Authors could not move to their next tasks while waiting for reviews. - Review work consumed most of the day. - Large PRs had to be reviewed quickly, increasing the risk of missed bugs. - This created a single point of failure and exposed the trade-off between thoroughness and development speed. - The launch of a dedicated frontend team in early 2025 provided an opportunity to redesign the review process. ## Introducing AI Screening Reviews - The team first tried having AI summarize PR changes before review. - Although summaries made changes easier to understand, AI did not sufficiently reduce the work of tracing dependencies or identifying hidden problems. - Manually pasting prompts for every review also made the approach inconvenient, so it was abandoned after about two weeks. - The introduction of Claude Code in summer 2025 changed the situation because reusable custom commands eliminated repetitive prompt preparation. - AI screening reviews now perform an initial inspection before a human reviewer makes the final judgment. - This changes the process from “humans inspect everything” to a two-stage model: - AI analyzes the PR, its impact, coding conventions, and possible risks. - A human reviewer validates the analysis and makes the final decision. ## Claude Code Custom Review Commands The custom command requests that Claude Code: - Summarize the PR and its affected areas. - Explain the before-and-after changes for each file. - Check coding and naming conventions. - Investigate dependent files and broader codebase impact. - Identify potential bugs, security issues, performance problems, code smells, and unintended side effects. - Suggest concise, respectful review comments for the author. - Classify comments with labels such as `[must]`, `[want]`, `[imo]`, `[ask]`, `[nits]`, and `[info]`. - Determine whether additional tests are needed based on existing project practices. The command uses GitHub CLI operations such as: - `gh pr view --json title,body,files,url` - `gh pr diff` - `gh pr view --comments` - GitHub API calls for line-level comments - `gh pr checkout` when the relevant branch is not currently checked out The review procedure is deliberately structured: 1. Confirm the review requirements. 2. Understand the PR’s overall purpose and background. 3. Review each changed file in detail. 4. Investigate dependencies across the codebase. 5. Produce a final assessment and suggested comments. The same screening process can help both reviewers and PR authors. Reviewers use it to reduce preparation time and understand impact, while authors can run it before requesting review to fix likely issues in advance. ## Expanding Beyond AI Screening After seeing benefits from screening reviews, the team created a broader improvement framework spanning technology and team culture. It was organized around four connected goals: - Improving efficiency. - Establishing a foundation for review accuracy. - Building review-oriented team culture. - Creating a mechanism for continuous improvement. The approach treats review optimization as an ongoing cycle rather than a one-time tool deployment. ## Automating PR Creation The team also uses AI to reduce the effort required to create PRs. - Git operations such as branch creation, commits, and PR creation are automated. - AI analyzes the commit diff to generate: - A PR title. - A summary of the changes. - Background and motivation. - Other required PR template fields. - Standardized and more complete PR descriptions provide better context for both human reviewers and AI screening. - Improving PR quality at the creation stage also increases the accuracy and consistency of later reviews. ## Practical Recommendation AI should support—not replace—reviewer judgment. Teams should begin by standardizing the review workflow, encode that workflow in reusable AI commands, and measure whether review time, PR waiting time, and review quality improve. Combining AI screening with better PR context, dependency analysis, clear comment conventions, and continuous process refinement offers a more sustainable solution than relying on individual reviewers.

Read original

AI Database Design Web Development Claude Code+4

lineApr 10, 20261 min readCurated summary

List of Articles for ‘Orchestration Development Workshop,’ an Internal Workshop to Enhance AI Utilization Skills

LY Corporation runs the “Orchestration Development Workshop” to help engineers apply AI more effectively in real development work. The workshop focuses on connecting multiple AI tools and agents to amplify creativity through collaborative learning and creation. A related blog series will share workshop topics, beginning with an example of using AI to reduce PR review delays and improve review culture. ## Orchestration Development Workshop - Targets engineers involved in development at LY Corporation. - Emphasizes practical, workplace-oriented AI skills rather than purely theoretical knowledge. - Uses “orchestrating multiple AIs to maximize creativity” as its central theme. - Builds on the idea that organizational learning is essential for successfully adopting AI. ## Blog Series - The series will publish workshop content incrementally. - The article list will be updated as new posts are released. - The listed update date is April 10, 2026. ## AI-Assisted PR Reviews - The first installment addresses bottlenecks and delays in pull-request reviews. - It explains how AI-assisted PR review support can help resolve review stagnation. - It also describes an internal workshop designed to change team review practices and culture. The series presents AI adoption as an organizational and collaborative practice, with PR review automation serving as an initial example of measurable workflow improvement.

Read original

AI Orchestration Team Collaboration Workshop+2

lineApr 8, 20263 min readCurated summary

The Key to AI Utilization Lies in 'Organizational Learning' - The Start of the Orchestration Development Workshop

LY Corporation is moving from simply adopting AI tools to building with AI as a collaborative development partner. Its new Orchestration Development Workshop teaches engineers to coordinate multiple AI systems across coding, testing, reviews, incident analysis, and other workflows. The initiative aims not only to improve efficiency but to free engineers from repetitive work so they can focus on more creative, high-value challenges. ## From AI Adoption to AI Collaboration - AI-assisted development and operations are spreading rapidly across LY Corporation. - Engineers use generative AI for code generation and testing, while combining it with non-generative AI for analysis and operational optimization. - Despite broader adoption, employees differ significantly in how deeply they use AI in their daily work. - The workshop was created to help the organization evolve from “using AI” to “creating alongside AI.” ## Orchestration: Coordinating Multiple AI Systems - “Orchestration” refers to combining multiple AIs, along with human input, to produce a complete outcome. - Example workflows include: - Generating code automatically from a Jira ticket. - Having AI run tests, conduct reviews, and create a pull request. - Analyzing a Slack incident report, estimating the cause, and proposing a fix. - The workshop turns these emerging practices into hands-on learning rather than passive demonstrations. ## A Hands-On, Interactive Learning Model - Participants follow instructors in real time and perform the same tasks themselves. - Zoom conversations and Slack questions create two-way communication during the session. - Instructors and representative participants explore solutions to problems as they arise. - The goal is for attendees to gain skills they can reproduce in their own projects, not merely acquire theoretical knowledge. ## Organization-Wide Support Through Guilds and DevRel - The initiative is designed to avoid depending on individual enthusiasm. - Three complementary functions support continuous growth: - **DevRel:** Drives the program and promotes adoption. - **Guilds:** Contribute practical insights from engineering teams. - **TD:** Helps maintain quality and reproducibility. - This structure supports consistent content quality and enables AI knowledge to spread across the company. ## Beyond Efficiency: Unlocking Engineering Creativity - LY Corporation views AI as more than a way to complete tasks faster. - By delegating repetitive work to AI, engineers can spend more time on creative and strategically valuable activities. - The organization aims to move beyond a model where AI writes code and humans only review it. - Instead, engineers should collaborate with AI from the design stage through implementation. ## Future Direction - LY Corporation plans to share lessons from the workshops through external channels such as its technology blog. - Future topics will include both generative and non-generative AI. - The broader goal is to provide practical guidance for engineers building new workflows with AI. The workshop represents a structured way to turn AI experimentation into repeatable organizational practice, helping engineers coordinate multiple AI tools while preserving human creativity and judgment.

Read original

AI Database Design PostgreSQL Python+4

lineFeb 23, 20264 min readCurated summary

Sharing the journey of LINE DEV

AI adoption at LY Corporation has moved beyond experimentation toward learning how to use these tools effectively in real work. The LINE DEV AI Reporters program connects scattered individual and team experiences through internal sharing sessions, helping practical lessons spread across the organization. Its central conclusion is that AI productivity depends not only on tools, but also on clear specifications, sound engineering practices, and a culture of continuous sharing. ## Turning Individual Experiments into Organizational Knowledge - AI enthusiasts across LY Corporation were independently experimenting with tools such as ChatGPT and Claude Code. - These experiences often remained limited to individuals or small teams. - AI Reporters brought together members of different roles and seniority who had experience sharing AI-related work. - Their goal was to turn personal trial and error into reusable organizational knowledge. ## Starting with Informal Personal Experiments - Early AI sharing sessions emphasized accessibility rather than polished success stories. - Multimedia Platform Dev’s Choi Jeong-min shared a “one service a day” vibe-coding experiment using Claude Code and Antigravity. - The experiment demonstrated that rapid implementation increases the importance of clearly defining what to build. - Sharing failures and unfinished experiments reduced the pressure to perform and encouraged more employees to try AI themselves. ## Applying AI to Real Development Work - As interest grew, discussions shifted from fun experiments to practical workplace applications. - Data Dev4’s Lee Yun-seong shared more than a month of project experience using Claude Code, project templates, and Vibe Kanban. - Developers spent more time on planning, design, review, and coordination while agents handled implementation. - Because the current codebase becomes the context for future agent work, poor architecture and coding styles can quickly be reproduced and amplified. - Continuous testing, refactoring, documentation, interface management, and architectural cleanup are therefore essential. - Skipping automated tests before commits led to increasing numbers of broken changes during later merges. - Humans remain responsible for ensuring that AI-generated code actually contributes to the project. - The most valuable skills increasingly involve task design, project management, system context, and meta-programming rather than implementation alone. - Developers can work in parallel with agents by planning the next task, researching requirements, and reviewing completed code while agents execute current work. ## Expanding from Teams to Organization-Wide Programs - Fintech Engineering organized a hands-on workshop covering the full path from idea to deployment. - Participants connected ChatGPT, Claude Code, and Stitch AI to plan, design, build, and complete a working service. - The integrated workflow helped participants understand how AI tools can support an entire product-development process, not just prototyping. - The GAI Study Group in the advertising organization broadened discussions to AI strategy, trends, agent behavior, developer workflows, and business applications. - Topics included: - AI agent reliability - Implementing interactions between PyTorch-based LLMs and MCP servers - Senior and junior developers’ vibe-coding workflows - NotebookLM-based RAG using wiki pages and Slack conversations - One session examined MCP internals by implementing JSON-RPC messaging and session-state management directly, revealing complexities hidden by libraries such as FastMCP. - Sessions were opened to participants and presenters from other teams, with some content published online for wider access. ## Building a Culture of Continuous Sharing - The most useful AI knowledge came from real workplace attempts, failures, and revisions—not only from polished documentation or external trends. - AI Reporters made existing but scattered experiences visible and connected them through presentations, Slack discussions, and monthly meetings. - Informal conversations such as “I tried this—how did it work for you?” helped normalize experimentation and learning from mistakes. - AI adoption is treated as an ongoing practice because tools and workflows continue to change. LY Corporation’s experience suggests that organizations should create lightweight, recurring forums where employees can share practical AI experiments. The combination of rapid experimentation, disciplined engineering, and open knowledge exchange allows individual discoveries to become lasting organizational capability.

Read original

AI PostgreSQL Claude Code Chatgpt+4

lineFeb 4, 20264 min readCurated summary

Scaling to Infinity: LY Corporation’s

LY Corporation’s observability team evolved its time-series database to handle rapidly growing infrastructure and Kubernetes workloads. After outgrowing MySQL and OpenTSDB, the team built an engine optimized for high-cardinality metrics, low-latency queries, and seamless API compatibility. Its architecture now combines in-memory, Cassandra, and S3-compatible storage, enabling cost-efficient scaling while supporting trillions of daily metrics. ## Why Time-Series Storage Matters - Metrics record system state as timestamped numerical values. - They support dashboards, threshold-based alerts, and predictive analysis using tools such as ARIMA and Prophet. - Even a small metric record can consume about 280 bytes when timestamps, values, and tags are included. - One CPU metric collected every 15 seconds requires roughly 562 MiB per server annually; across 1,000 servers, this grows to about 548 GiB before adding memory, disk, and network metrics. - High-cardinality cloud environments make both storage cost and query latency critical operational concerns. ## Moving Beyond MySQL and OpenTSDB - MySQL initially became inadequate as the organization moved from SOA to MSA: - Write load increased sharply. - Storage costs and capacity requirements grew. - Query latency worsened for large datasets. - Rigid schemas could not easily represent changing cloud resources. - MySQL sharding provided temporary relief but could not support high-resolution metrics collected at intervals under one minute. - OpenTSDB, introduced in 2016 on Apache HBase, improved write performance but had important limitations: - Tag growth harmed UID-table lookup performance. - Metadata was restricted to a narrow character set. - Large queries required cache warm-up procedures. - These constraints led to the development of an internal database beginning in 2018. ## Building the Internal Time-Series Database - The 2019 engine was designed around: - Flexible protocol support independent of a particular agent. - Linear scalability without downtime. - Low-latency processing of high-resolution metrics. - Strong availability during failures. - Inspired by Meta’s Gorilla research, the team used access patterns in which most queries target recent data. - Frequently accessed metrics were kept in an in-memory database, while colder data was stored in Apache Cassandra. - The new engine enabled metric volumes to grow by more than 200 billion records annually while preserving existing APIs. - Users benefited from the new backend without migration work or code changes. ## Scaling for Kubernetes Workloads - Kubernetes introduced rapidly changing pods, dynamically allocated volumes, and much higher metric churn. - Both major storage layers encountered scaling problems: - IMDB initially required adding identical hardware, limiting expansion options. - Cassandra rebalancing could take tens of hours because of its data volume. - The team improved IMDB with weighted load balancing so nodes with different capacities could be used effectively. - Storage was divided into tiers: - Recent 14-day data remained in Cassandra for high-performance access. - Older data was moved to S3-compatible storage. - This reduced Cassandra dependency, lowered costs, simplified operations, and enabled more flexible hardware and Kubernetes-based deployment. ## Writing and Reading Through S3 - The write path separates data processing from long-term storage: - A Dumper reads metric slots from IMDB. - It converts them into internally defined sub-blocks. - A Block Dumper combines sub-blocks into blocks and writes them to S3. - A Storage Gateway reads the blocks for queries and caches them on local disks. - Disk caching initially caused excessive page-cache use and rapid memory exhaustion. - Direct I/O was considered but withdrawn after the cloud storage team warned that it consumed too much shared bandwidth. - Through cross-team collaboration, the team adopted a B+ tree-based cache that made better use of the kernel page cache without overloading infrastructure. ## Future Direction: From Storage to Intelligence - The team aims to move beyond recording metrics toward prediction and AI-assisted operations. - Achieving this requires consolidating time-series data currently scattered across internal systems. - A key requirement is to perform this integration without imposing migration work or breaking changes on users. - The broader goal is an observability platform that turns unified metrics into predictive and intelligent operational capabilities. The main recommendation is to design time-series platforms around real access patterns, tier storage according to data age, and preserve compatibility while evolving the backend. At extreme scale, careful storage architecture and collaboration across infrastructure teams are as important as raw database performance.

Read original

AI Database Design Kubernetes Observability+4

lineJan 14, 2026Original article

Building an Enterprise LLM (opens in new tab)

LY Corporation’s engineering team developed an AI assistant for their private cloud platform, Flava, by prioritizing "context engineering" over traditional prompt engineering. To manage a complex environment of 260 APIs and hundreds of technical documents, they implemented a strategy of progressive disclosure to ensure the LLM receives only the most relevant information for any given query. This approach allows the assistant to move beyond simple RAG-based document summarization to perform active diagnostics and resource management based on real-time API data. ### Performance Limitations of Long Contexts * Research indicates that LLM performance can drop by 13.9% to 85% as context length increases, even if the model technically supports a large token window. * The phenomenon of "context rot" occurs when low-quality or irrelevant information is mixed into the input, causing the model to generate confident but incorrect answers. * Because LLMs are stateless, maintaining conversation history and processing dense JSON responses from multiple APIs quickly exhausts context windows and degrades reasoning quality. ### Progressive Disclosure and Tool Selection * The system avoids loading all 260+ API definitions at once; instead, it analyzes the user's intent to select only the necessary tools, such as loading only Redis-related APIs when a user asks about a cluster. * Specific product usage hints, such as the distinction between private and CDN settings for Object Storage, are injected only when those specific services are invoked. * This phased approach significantly reduces token consumption and prevents the model from being overwhelmed by irrelevant technical specifications. ### Response Guidelines and the "Mock Tool Message" Strategy * The team distinguished between "System Prompts" (global rules) and "Response Guidelines" (situational instructions), such as directing users to a console UI before suggesting CLI commands. * Injecting specific guidelines into the system prompt often caused "instruction conflict," where the LLM might hallucinate information to satisfy a guideline while ignoring core requirements like using search tools. * To resolve these conflicts, the team utilized "ToolMessages" to inject guidelines; by formatting instructions as if they were results from a tool execution, the LLM treats the information as factual context rather than a command that might override the system prompt. To build a robust enterprise LLM service, developers should focus on dynamic context management rather than static prompt optimization. Treating operational guidelines as external data via mock tool messages, rather than system instructions, provides a scalable way to reduce hallucinations and maintain high performance across hundreds of integrated services.

AI Large Language Models Prompt Engineering RAG+4

lineDec 30, 2025Original article

A Business Trip to Japan After Only One (opens in new tab)

Joining the Developer Relations (DevRel) team at LINE Plus, a new employee was immediately thrust into a high-stakes business trip to Japan just one week after onboarding to support major global tech events. This immersive experience allowed the recruit to rapidly grasp the company’s engineering culture by facilitating cross-border collaboration and managing large-scale technical conferences. Ultimately, the journey highlights how a proactive onboarding strategy and a culture of creative freedom enable DevRel professionals to bridge the gap between complex engineering feats and community engagement. ### Global Collaboration at Tech Week * The trip centered on participating in **Tech-Verse**, a global conference featuring simultaneous interpretation in Korean, English, and Japanese, where the focus was on maintaining operational detail across diverse technical sessions. * Operational support was provided for **Hack Day**, an in-house hackathon that brought together engineers from various countries to collaborate on rapid prototyping and technical problem-solving. * The experience facilitated direct coordination with DevRel teams from Japan, Thailand, Taiwan, and Vietnam, establishing a unified approach to technical branding and regional community support. * Post-event responsibilities included translating live experiences into digital assets, such as "Shorts" video content and technical blog recaps, to maintain engagement after the physical event concluded. ### Modernizing Internal Technical Sharing * The **Tech Talk** series, a long-standing tradition with over 78 sessions, was used as a platform to experiment with "B-grade" humorous marketing—including quirky posters and cup holders—to drive offline participation in a remote-friendly work environment. * To address engineer feedback, the format shifted from passive lectures to **hands-on practical sessions** focusing on AI implementation. * Specific technical workshops demonstrated how to use tools like **Claude Code** and **ChatGPT** to automate workflows, such as generating weekly reports by integrating **Jira tickets with internal Wikis**. * Preparation for these sessions involved creating detailed environment setup guides and troubleshooting protocols to ensure a seamless experience for participating developers. ### Scaling AI Literacy via AI Campus Day * The **AI Campus Day** was a large-scale event designed for over 3,000 participants, aimed at lowering the barrier to entry for AI adoption across all departments. * The "Event & Operation" role involved creating interactive AI photo zones using **Gemini** to familiarize employees with new internal AI tools in a low-pressure setting. * Event production utilized AI-driven assets, including AI-generated voices and icons, to demonstrate the practical utility of these tools within standard business communication and video guides. * The success of the event relied on "participation design," ensuring that even non-technical staff could engage with AI concepts through hands-on play and peer mentoring. For organizations looking to strengthen their technical culture, this experience suggests that integrating new hires into high-impact global projects immediately can be a powerful onboarding tool. Providing DevRel teams the psychological safety to experiment with unconventional marketing and hands-on technical workshops is essential for maintaining developer engagement in a hybrid work era.

AI Generative AI Gemini Claude Code+5

lineDec 19, 2025Original article

We held AI Campus Day to improve (opens in new tab)

LY Corporation recently hosted "AI Campus Day," a large-scale internal event designed to bridge the gap between AI theory and practical workplace application for over 3,000 employees. By transforming their office into a learning campus, the company successfully fostered a culture of "AI Transformation" through peer-led mentorship and task-specific experimentation. The event demonstrated that internal context and hands-on participation are far more effective than traditional external lectures for driving meaningful AI literacy and productivity gains. ## Hands-on Experience and Technical Support * The curriculum featured 10 specialized sessions across three tracks—Common, Creative, and Engineering—to ensure relevance for every job function. * Sessions ranged from foundational prompt engineering for non-developers to advanced technical topics like building Model Context Protocol (MCP) servers for engineers. * To ensure smooth execution, the organizers provided comprehensive "Session Guides" containing pre-configured account settings and specific prompt templates. * The event utilized a high support ratio, with 26 teaching assistants (TAs) available to troubleshoot technical hurdles in real-time and dedicated Slack channels for sharing live AI outputs. ## Peer-Led Mentorship and Internal Context * Instead of hiring external consultants, the program featured 10 internal "AI Mentors" who shared how they integrated AI into their actual daily workflows at LY Corporation. * Training focused exclusively on company-approved tools, including ChatGPT Enterprise, Gemini, and Claude Code, ensuring all demonstrations complied with internal security protocols. * Internal mentors were able to provide specific "company context" that external lecturers lack, such as integrating AI with existing proprietary systems and data. * A rigorous three-stage quality control process—initial flow review, final end-to-end dry run, and technical rehearsal—was implemented to ensure the educational quality of mentor-led sessions. ## Gamification and Cultural Engagement * The event was framed as a "festival" rather than a mandatory training, using campus-themed motifs like "enrollment" and "school attendance" to reduce psychological barriers. * A "Stamp Rally" system encouraged participation by offering tiered rewards, including welcome kits, refreshments, and subscriptions to premium AI tools. * Interactive exhibition booths allowed employees to experience AI utility firsthand, such as an AI photo zone using Gemini to generate "campus-style" portraits and an AI Agent Contest booth. * Strong executive support played a crucial role, with leadership encouraging staff to pause routine tasks for the day to focus entirely on AI experimentation and "playing" with new technologies. To effectively scale AI literacy within a large organization, it is recommended to move away from passive, one-size-fits-all lectures. Success lies in leveraging internal experts who understand the specific security and operational constraints of the business, and creating a low-pressure environment where employees can experiment with hands-on tasks relevant to their specific roles.

AI Generative AI Model Context Protocol Gemini+5

lineDec 17, 2025Original article

Safety is a Given, Cost (opens in new tab)

AI developers often rely on system prompts to enforce safety rules, but this integrated approach frequently leads to "over-refusal" and unpredictable shifts in model performance. To ensure both security and operational efficiency, it is increasingly necessary to decouple safety mechanisms into separate guardrail systems that operate independently of the primary model's logic. ## Negative Impact on Model Utility * Integrating safety instructions directly into system prompts often leads to a high False Positive Rate (FPR), where the model rejects harmless requests alongside harmful ones. * Technical analysis using Principal Component Analysis (PCA) reveals that guardrail prompts shift the model's embedding results in a consistent direction toward refusal, regardless of the input's actual intent. * Studies show that aggressive safety prompting can cause models to refuse benign technical queries—such as "how to kill a Python process"—because the model adopts an overly conservative decision boundary. ## Positional Bias and Context Neglect * Research on the "Lost in the Middle" phenomenon indicates that LLMs are most sensitive to information at the beginning and end of a prompt, while accuracy drops significantly for information placed in the center. * The "Constraint Difficulty Distribution Index" (CDDI) demonstrates that the order of instructions matters; models generally follow instructions better when difficult constraints are placed at the beginning of the prompt. * In complex system prompts where safety rules are buried in the middle, the model may fail to prioritize these guardrails, leading to inconsistent safety enforcement depending on the prompt's structure. ## The Butterfly Effect of Prompt Alterations * Small, seemingly insignificant changes to a system prompt—such as adding a single whitespace, a "Thank you" note, or changing the output format to JSON—can alter more than 10% of a model's predictions. * Modifying safety-related lines within a unified system prompt can cause "catastrophic performance collapse," where the model's internal reasoning path is diverted, affecting unrelated tasks. * Because LLMs treat every part of the prompt as a signal that moves their decision boundaries, managing safety and task logic in a single string makes the system brittle and difficult to iterate upon. To build robust and high-performing AI applications, developers should move away from bloated system prompts and instead implement external guardrails. This modular approach allows for precise security filtering without compromising the model's creative or logical capabilities.

AI Large Language Models Prompt Engineering Prompt Injection+4

lineNov 4, 2025Original article

Security Threat Cases and Countermeasures (opens in new tab)

Developing AI products introduces unique security vulnerabilities that extend beyond traditional software risks, ranging from package hallucinations to sophisticated indirect prompt injections. To mitigate these threats, organizations must move away from trusting LLM-generated content and instead implement rigorous validation, automated threat modeling, and input/output guardrails. The following summary details the specific risks and mitigation strategies identified by LY Corporation’s security engineering team. ## Slopsquatting and Package Hallucinations - AI models frequently hallucinate non-existent library or package names when providing coding instructions (e.g., suggesting `huggingface-cli` instead of the correct `huggingface_hub[cli]`). - Attackers exploit this by registering these hallucinated names on public registries to distribute malware to unsuspecting developers. - Mitigation requires developers to manually verify all AI-suggested commands and dependencies before execution in any environment. ## Prompt Injection and Arbitrary Code Execution - As seen in CVE-2024-5565 (Vanna AI), attackers can inject malicious instructions into prompts to force the application to execute arbitrary code. - This vulnerability arises when developers grant LLMs the autonomy to generate and run logic within the application context without sufficient isolation. - Mitigation involves treating LLM outputs as untrusted data, sanitizing user inputs, and strictly limiting the LLM's ability to execute system-level commands. ## Indirect Prompt Injection in Integrated AI - AI assistants integrated into office environments (like Gemini for Workspace) are susceptible to indirect prompt injections hidden within emails or documents. - A malicious email can contain "system-like" instructions that trick the AI into hiding content, redirecting users to phishing sites, or leaking data from other files. - Mitigation requires the implementation of robust guardrails that scan both the input data (the content being processed) and the generated output for instructional anomalies. ## Permission Risks in AI Agents and MCP - The use of Model Context Protocol (MCP) and coding agents creates risks where an agent might overstep its intended scope. - If an agent has broad access to a developer's environment, a malicious prompt in a public repository could trick the agent into accessing or leaking sensitive data (such as salary info or private keys) from a private repository. - Mitigation centers on the principle of least privilege, ensuring AI agents are restricted to specific, scoped directories and repositories. ## Embedding Inversion and Vector Store Vulnerabilities - Attacks targeting the retrieval phase of RAG (Retrieval-Augmented Generation) systems can lead to data leaks. - Embedding Inversion techniques may allow attackers to reconstruct original sensitive text from the vector embeddings stored in a database. - Securing AI products requires protecting the integrity of the vector store and ensuring that retrieved context does not bypass security filters. ## Automated Security Assessment Tools - To scale security, LY Corporation is developing internal tools like "ConA" for automated threat modeling and "LAVA" for automated vulnerability assessment. - These tools aim to identify AI-specific risks during the design and development phases rather than relying solely on manual reviews. Effective AI security requires a shift in mindset: treat every LLM response as a potential security risk. Developers should adopt automated threat modeling and implement strict input/output validation layers to protect both the application infrastructure and user data from evolving AI-based exploits.

AI Large Language Models Model Context Protocol Ai Security+5

lineOct 3, 2025Original article

A month-long project in (opens in new tab)

This blog post explores how LY Corporation reduced a month-long development task to just five days by leveraging "vibe coding" with Generative AI tools like ChatGPT and Cursor. By shifting from traditional, rigid documentation to an iterative, demo-first approach, developers can rapidly validate multiple UI/UX solutions for complex problems like restaurant menu registration. The author concludes that AI's ability to handle frequent re-work makes it more efficient to "build fast and iterate" than to aim for perfection through long-form specifications. ### Strategic Shift to Rapid Prototyping * Traditional development cycles (spec → design → dev → fix) are often too slow to keep up with market trends due to heavy documentation and impact analysis. * The "vibe coding" approach prioritizes creating "working demos" over perfect specifications to find "good enough" answers through rapid feedback loops. * AI reduces the psychological and logistical burden of "starting over," allowing developers to refine the context and quality of outputs through repeated interaction without the friction of manual re-documentation. ### Defining Requirements and Solution Ideation * Initial requirements are kept minimal, focusing only on the core mission, top priorities, and essential data structures (e.g., product name, image, description) to avoid limiting AI creativity. * ChatGPT is used to generate a wide range of solution candidates, which are then filtered into five distinct approaches: Stepper Wizards, Live Previews with Quick Add, Template/Cloning, Chat Input, and OCR-based photo scanning. * This stage emphasizes volume and variety, using AI-generated pros and cons to establish selection criteria and identify potential UX bottlenecks early in the process. ### Detailed Design and Multi-Solution Wireframing * Each of the five chosen solutions is expanded into detailed screen flows and UI elements, such as progress bars, bottom sheets, and validation logic. * Prompt engineering is used iteratively; if an AI-generated result lacks a specific feature like "temporary storage" or "mandatory field validation," the prompt is adjusted to regenerate the design instantly. * The focus remains on defining the "what" (UI elements) and "how" (user flow) through textual descriptions before moving to actual coding. ### Implementation with Cursor and Flutter * Cursor is utilized to generate functional code based on the refined wireframes, using Flutter as the framework to ensure rapid cross-platform development for both iOS and Android. * The development follows a "skeleton-first" approach: first creating a main navigation hub with five entry points, then populating each individual solution module one by one. * Technical architecture decisions, such as using Riverpod for state management or SQLite for data storage, are layered onto the demo post-hoc, reversing the traditional "stack-first" development order to prioritize functional validation. ### Recommendation To maximize efficiency, developers should treat AI as a partner for high-speed iteration rather than a one-shot tool. By focusing on creating functional demos quickly and refining them through direct feedback, teams can bypass the bottlenecks of traditional software requirements and deliver user-centric products in a fraction of the time.

AI Large Language Models Generative AI Prompt Engineering+5

lineOct 3, 2025Original article

IUI 202 (opens in new tab)

The IUI 2025 conference highlighted a significant shift in the AI landscape, moving away from a sole focus on model performance toward "human-centered AI" that prioritizes collaboration, ethics, and user agency. The prevailing consensus across key sessions suggests that for AI to be sustainable and trustworthy, it must transcend simple automation to become a tool that augments human perception and decision-making through transparent, interactive, and socially aware design. ## Reality Design and Human Augmentation The concept of "Reality Design" suggests that Human-Computer Interaction (HCI) research must expand beyond screen-based interfaces to design reality itself. As AI, sensors, and wearables become integrated into daily life, technology can be used to directly augment human perception, cognition, and memory. * Memory extension: Systems can record and reconstruct personal experiences, helping users recall details in educational or professional settings. * Sensory augmentation: Technologies like selective hearing or slow-motion visual playback can enhance a user's natural observational powers. * Cognitive balance: While AI can assist with task difficulty (e.g., collaborative Lego building), designers must ensure that automation does not erode the human will to learn or remember, echoing historical warnings about technology-induced "forgetfulness." ## Bridging the Socio-technical Gap in AI Transparency Transparency in AI, particularly for high-risk areas like finance or medicine, should not be limited to showing mathematical model weights. Instead, it must bridge the gap between technical complexity and human understanding by focusing on user goals and social contexts. * Multi-faceted communication: Effective transparency involves model reporting (Model Cards), sharing safety evaluation results, and providing linguistic or visual cues for uncertainty rather than just numerical scores. * Counterfactual explanations: Users gain better trust when they can see how a decision might have changed if specific input conditions were different. * Interaction-based transparency: Transparency must be coupled with control, allowing users to act as "adjusters" who provide feedback that the model then reflects in its future outputs. ## Interactive Machine Learning and Human-in-the-Loop The framework of Interactive Machine Learning (IML) challenges the traditional view of AI as a static black box trained on fixed data. Instead, it proposes an interactive loop where the user and the model grow together through continuous feedback. * User-driven training: Users should be able to inspect model classifications, correct errors, and have those corrections immediately influence the model's learning path. * Beyond automation: This approach reframes AI from a replacement for human labor into a collaborative partner that adapts to specific user behaviors and professional expertise. * Impact on specialized tools: Modern applications include educational platforms where students manipulate data directly and research tools that integrate human intuition into large-scale data analysis. ## Collaborative Systems in Specialized Professional Contexts Practical applications of human-centered AI are being realized in sensitive fields like child counseling, where AI assists experts without replacing the human element. * Counselor-AI transcription: Systems designed for counseling analysis allow AI to handle the heavy lifting of transcription while counselors manage the nuance and contextual editing. * Efficiency through partnership: By focusing on reducing administrative burdens, these systems enable professionals to spend more time on high-level cognitive tasks and emotional support, demonstrating the value of AI as a supportive infrastructure. The future of AI development requires moving beyond isolated technical optimization to embrace the complexity of the human experience. Organizations and developers should focus on creating systems where transparency is a tool for "appropriate trust" and where design is focused on empowering human capabilities rather than simply automating them.

AI Large Language Models Human In The Loop Human Centered Ai+5

lineSep 26, 2025Original article

PD1 AI Hackathon: Into the (opens in new tab)

The PD1 AI Hackathon 2025 served as a strategic initiative by LY Corporation to embed innovative artificial intelligence directly into the LINE messaging ecosystem. Over 60 developers collaborated during an intensive 48-hour session to transition AI from a theoretical concept into practical features for messaging, content, and internal development workflows. The event successfully produced several high-utility prototypes that demonstrate how AI can enhance user safety, creative expression, and technical productivity. ## Transforming Voice Communication through NextVoIP * The "NextVoIP" project utilized Speech-to-Text (STT) technology to convert 1:1 and group call audio into real-time data for AI analysis. * The system was designed to provide life security features by detecting potential emergency situations or accidents through conversation monitoring. * AI acted as a communication assistant by suggesting relevant content and conversation topics to help maintain a seamless flow during calls. * Features were implemented to allow callers to enjoy shared digital content together, enriched by AI-driven recommendations. ## Creative Expression with MELODY LINE * This project focused on the intersection of technology and art by converting chat conversations into unique musical compositions. * The system analyzed the context and emotional sentiment of messages to automatically generate melodies that matched the atmosphere of the chat. * The implementation showcased the potential for generative AI to provide a multi-sensory experience within a standard messaging interface. ## AI-Driven QA and Test Automation * The grand prize-winning project, "IPD," addressed the bottleneck of repetitive manual testing by automating the entire Quality Assurance lifecycle. * AI was utilized to automatically generate and manage complex test cases, significantly reducing the manual effort required for mobile app validation. * The system included automated test execution and a diagnostic feature that identifies the root cause of failures when a test results in an error. * The project was specifically lauded for its immediate "production-ready" status, offering a direct path to improving development speed and software reliability. The results of this hackathon suggest that the most immediate value for AI in large-scale messaging platforms lies in two areas: enhancing user experience through contextual awareness and streamlining internal engineering via automated QA. Organizations should look toward integrating AI-driven testing tools to reduce technical debt while exploring real-time audio and text analysis to provide proactive security and engagement features for users.

AI Generative AI Test Automation Mobile Development+2