/Events /AgentCon - Seoul
AgentCon - Seoul
About
Join us for the AI Agents World Tour, a global series of one-day conferences designed exclusively for developers building the future with AI agents.
From San Francisco to Singapore, we’re bringing together leading engineers, researchers, and creators to explore the cutting edge of AI agent design, deployment, and integration. Whether you’re building intelligent assistants, autonomous systems, or next-gen developer tools, this event is your fast track to practical knowledge, hands-on demos, and real-world insights.
What to Expect:
- Deep-Dive Talks from AI pioneers and industry leaders
- Technical Workshops on building, deploying, and scaling agents
- Live Demos of powerful open-source frameworks and tools
- Networking with a global community of builders and innovators
This isn't just another AI event — it’s where developers meet to talk about real code.
Ready to build the future?
Sessions & tracks
When AI Becomes a Team: How Agentic AI Redefines Work and Leadership
Many organizations are experimenting with AI agents, but turning those experiments into real business impact remains a challenge. In this keynote, drawing on Microsoft’s experiences working with customers and partners, we will share a practical, real‑world approach to moving beyond isolated PoCs—scaling agent initiatives into an enterprise‑wide agentic architecture, while addressing security, governance, and operational readiness from day one. This session is designed to ensure that AgentCon participants leave with clear, actionable insights on what they can start changing.
Juhyeon Song is a seasoned technology and business leader with over 25 years of experience spanning the tech industry, consulting, partner ecosystems, business strategy, sales, and account management. She has consistently demonstrated a strong track record of building and leading high performing teams that deliver measurable impact. She joined Microsoft as Korea SME&C Lead in April 2025 and then expanded her scope to lead Cloud and AI ASEAN including Korea as of July 2025, being responsible for driving growth and innovation across ASEAN customers and partner landscape. Prior to joining Microsoft, she spent nearly nine years at Amazon Web Services. She began her AWS journey in 2016 as Head of Enterprise Support and built the team from the ground up and led the sales org of Digital Native, Gaming, and ISV. Her earlier career was shaped at HP Korea, where she held various roles over 16 years. As a Partner Program Lead, she led renewal transitions and strategic planning with key channel partners. As a Global Support Delivery Manager, she launched multilingual centers in Hanoi and Dalian, managing over 100 engineers. She holds a bachelor’s degree in computer science and engineering from Korea University and a Master of Laws (LL.M) in Intellectual Property from Yonsei University Law School.
개발자를 넘어 임팩트로: Tech as a Gift for Everyone
이제 누구나 만들고, 누구나 도전하는 AI Agent의 시대가 열렸습니다. 상상이 곧바로 현실이 되는 매일은 분명 흥미롭고 흥분되지만, 동시에 하나의 질문을 던집니다.
“모두가 만드는 시대에, 나만의 영향력은 어떻게 만들어야 하는가?”
이 질문에 대해, “컴퓨터는 선물이다”라고 말하는 이상묵 서울대학교 교수님을 직접 초청하여 깊은 울림이 있는 메시지를 듣습니다. 교수님은 지구과학자로서 학생들과 탐구 여행을 떠났던 그는, 그 여정 중 사고로 죽음의 문턱까지 가며 목 아래를 전혀 움직일 수 없는 중증 장애를 갖게 되었습니다.
이상묵 교수님은 좌절 대신 기술을 선택했습니다. 컴퓨터와 보조 기술을 익히며, 그는 사고 이전보다 더 많은 연구를 이어가고, 더 많은 학생을 가르치며, 더 넓은 사회적 영향력을 만들어가고 있습니다. 그의 경험은 기술이 단순한 도구를 넘어, 누군가의 가능성을 확장하는 ‘선물’이 될 수 있음을 증명합니다.
이 키노트에서는 개발자로서 기술을 ‘만드는 것’을 넘어, 기술을 통해 어떤 임팩트를 남길 것인가, 그리고 AI와 컴퓨터가 모두에게 어떤 선물이 될 수 있는가에 대해 함께 생각해 봅니다. 개발자의 다음 단계는 더 많은 코드가 아니라 더 큰 임팩트일 수 있습니다.
이상묵 교수: 대한민국 서울대학교 해양학 교수입니다. 불의의 사고로 사지마비가 되었으나 역경을 이겨낸 인재로 유명하며, '0.1그램의 희망'이라는 저서가 있습니다. 1981.03~1985.02. 서울대학교 해양학 이학사 1986.09~1995.02. 미국 메사추세츠 공과대학(MIT)/우드홀(Woods Hole) 해양연구소 해양학 이학박사 이소영: 한국 스타트업의 원조인 네오위즈를 거쳐 마이크로소프트에서 22년 동안 다양한 IT 전문 커리어를 개발해 왔습니다. 마이크로소프트가 승승장구하던 때에 입사하여, 시대의 흐름에 뒤쳐져 끝없이 추락을 거듭하던 시절, 최근 성공적인 AI 전환으로 시가총액 1위 기업으로 화려하게 복귀하는 과정을 그 누구보다 생생히 경험했습니다. 그 과정에서 커뮤니티 리더십과 파트너십의 중요성을 깨닫고 현재는 아시아 총괄 리전 매니저로 한국뿐 아니라 전 세계 IT 커뮤니티 리더의 성장과 발전을 돕고 있습니다.
Professor Lee Sang-mook is a leading marine geophysicist in Korea who views the movements and structures of the Earth's surface from a global perspective. He spearheaded numerous ocean expeditions until a traffic accident in 2006 left him completely paralyzed from the neck down. Following the accident, in addition to field exploration, he ventured into the field of computational science, which predicts natural phenomena using mathematics and computers, and also became involved in higher education for people with disabilities. He is currently active in many government committees related to disability issues. Since recently (since 2020), he has served as the Chairman of the International Central Ridge Research Council and, as the Project Manager for Planet A—a project being pursued as part of Seoul National University's 10-10 initiative—is contributing to the creation of a sustainable society by utilizing global data hubs and artificial intelligence algorithms. His testimony during the 2015 National Assembly audit served as a pioneering catalyst that allowed universities and the entire academic community to utilize Korea's representative large-scale ocean research vessels, which had previously been used exclusively by government agencies.
Agents of Tomorrow: Building the Next Generation of Intelligence
We stand at the edge of a profound shift in artificial intelligence. Over the last five years, generative AI has moved from novelty to necessity—transforming how we create, code, and collaborate. Now, a new frontier is emerging: AI agents. Unlike traditional tools that wait for instructions, agents can perceive, decide, and act toward goals—expanding the boundaries of what humans and machines can achieve together.
In this keynote, we’ll explore the evolution from copilots to fully agentic systems, highlight breakthroughs that are reshaping industries, and imagine the future horizons where autonomous agents redefine productivity, creativity, and discovery. Most importantly, we’ll discuss the role of humans in this new era—not as bystanders, but as leaders guiding how agents operate, align with our values, and amplify our potential.
The Agents of Tomorrow are here—and the future will be built by those bold enough to partner with them.
Henk is a Cloud Advocate specializing in Artificial intelligence and Azure with a background in application development. He is currently part of the AI cloud advocate team and based in the Netherlands. Before joining Microsoft, he was a Microsoft AI MVP and worked as a software developer and architect building lots of AI powered platforms on Azure.
With over 20 years of business and technology experience, Dux has driven organizational transformations worldwide with his ability to simplify complex ideas and deliver relevant solutions. He serves as the Chief Brand Officer of AvePoint who has authored the LinkedIn Learning course How to Build Your Personal Brand, the book SharePoint for Project Management, as well as numerous whitepapers and articles. As a public speaker, Dux has delivered engaging, interactive presentations to more than 25,000 people at leading industry events around the world. He also hosts the modern workplace podcast #ShiftHappens that focuses on how leading organizations navigated their business transformation journey. Dux advocates tirelessly for inclusion, using technology for good, and philanthropic initiatives. Connect with him: http://dux.sy
Software Engineer. Multi-published author (turns out fiction writing is really useful in software!). Owner of the fashion brand Prima Dona studios. Aspiring sommelier at Side Hustle Wines. Dyslexic but Dealing. Believer that tech upskilling is the ultimate equalizer. Always ready to get on a plane.
Enterprise 향 OpenClaw 보안설정 및 MAF A2A 하이브리드 연계
OpenClaw 퍼스널 에이전트의 기업시스템 레벨 확장을 위한 보안 세팅 및 MAF(Microsoft Agent Framework) 기반 Enterprise Agent 와의 Hybrid A2A 연결 방법론을 설명하고, 구현 결과를 시연한다.
현) KT AX Delivery 본부 본부장/상무 현) Microsoft AI MVP 및 RD
Agents Gone Wild: Governance Challenges Every AI Builder Must Anticipate
Agentic AI is changing how software behaves — agents don’t just respond, they act, decide, and operate autonomously across systems and data. That shift introduces a new class of risks that traditional security, compliance, and governance models were never designed to handle. This session focuses on the real-world challenges that emerge when AI agents become active participants in the enterprise — from data overexposure and hallucinations to agent sprawl, unclear accountability, and governance blind spots. Rather than diving into code or promoting a specific platform, we’ll examine common failure patterns, lessons learned from early deployments, and the guardrails agent builders need to think about from day one. Attendees will leave with a clearer understanding of:
Why every AI agent is effectively a new endpoint Where governance breaks down as agents scale What responsible agent design looks like in practice How builders can balance autonomy, trust, and control without slowing innovation
This session is designed for AI builders, architects, and platform teams who want to move fast — without breaking trust.
With over 20 years of business and technology experience, Dux has driven organizational transformations worldwide with his ability to simplify complex ideas and deliver relevant solutions. He serves as the Chief Brand Officer of AvePoint who has authored the LinkedIn Learning course How to Build Your Personal Brand, the book SharePoint for Project Management, as well as numerous whitepapers and articles. As a public speaker, Dux has delivered engaging, interactive presentations to more than 25,000 people at leading industry events around the world. He also hosts the modern workplace podcast #ShiftHappens that focuses on how leading organizations navigated their business transformation journey. Dux advocates tirelessly for inclusion, using technology for good, and philanthropic initiatives. Connect with him: http://dux.sy
Tech Team Lead at AvePoint (5 years) | Microsoft 365 Migration & Data Protection | Enterprise Solution Architecture | B.S. Computer Science
Agentic AI Stack deep dive - Agentic Design patterns
AI is evolving fast, and the way we design solutions is changing with it. In this session, we’ll explore the Agentic AI Stack and break down when and why to use each component. We’ll dive into Microsoft 365 Copilot, Copilot Studio, Microsoft Fabric and Azure AI Foundry, showing how these tools work together to deliver intelligent, context-aware experiences.
You’ll learn through practical demonstrations and live design:
- How agentic design patterns shape modern AI solutions
- Where each tool fits in the stack and the scenarios they’re best suited for
- Practical examples of integrating these technologies for real business impact
If you’re looking to move beyond buzzwords and understand how to architect AI solutions that actually deliver value, this session is for you.
Hi there, I’m Chris! I'm a seasoned tech leader, keynote speaker, and technology consultant with expertise across the full tech stack, from enterprise architecture and data platforms to advanced AI (including Agentic AI and Responsible AI / Trustworthy AI). I’ve led large-scale, high-value enterprise projects and initiatives across industries (with a strong focus on government), helping organizations harness emerging technology responsibly to solve real-world challenges - I try to remove the fluff and cut to solving the real problem. My style is bold, straight-talking, and deeply authentic. I'm a natural connector who brings people together to spark collaboration and creativity. A lifelong tinkerer and excessively curious, I thrive on exploring new ideas and building communities around innovation. I encourage teams to think differently, color outside the lines, and always remember to stay human in a tech-driven world. As an international keynote speaker, I've energized audiences with talks on AI, Ethics in Tech, data strategy, and true concepts around digital transformation, infusing humor and real-talk into every session. Whether I'm advising C-suite leaders on AI strategy or coaching teams on the latest tech, my goal is to inspire innovation, enable people to do awesome things and drive positive change. If you're on the verge of the next big breakthrough and need a dynamic speaker or consultant, let's connect. I'm all about helping to #BuildAwesomeThings and making sure we all #StayExtraHuman along the way.
End-to-End Agentic AI with Red Hat AI
This session explores the evolution of artificial intelligence from simple chat interfaces to production-ready Agentic AI using Red Hat AI. We will move beyond the hype to examine how to build a standardized "Enterprise AI Factory" that integrates models into real workflows while maintaining strict control over data and security.
Attendees will gain practical knowledge on:
- Architecting Agentic Workflows: Leveraging the Llama Stack to provide agents with inference, memory, rag, and tool calling capabilities.
- AI Safety: Implementing a comprehensive approach across the AI lifecycle, including the use of MCP gateway, guardrails, red teaming, and risk metrics to mitigate toxicity and prompt vulnerability.
- Operationalizing with AgentOps: Standardizing "Day 2 Operations", such as monitoring, maintenance, and telemetry. This is to ensure agents are reliable, secured and scalable in mission-critical environments.
- Cloud-Native Integration: Utilizing the Model Context Protocol (MCP) to standardize tool calling and deploying agents as scalable microservices on Red Hat AI across hybrid cloud environments.
Whether you are a developer or a platform engineer, this session provides a roadmap for turning AI prototypes into secure, high-performing enterprise solutions that deliver measurable business value.
Li Ming brings over two decades of technology and engineering experience. As the AI Architect and a member of the AI Specialist team in APAC, he is responsible for leading AI innovation to tackle complex business challenges and improve customer outcomes. His role involves shaping strategic AI initiatives and guiding thought leadership across the region. Previously, he was the Chief Architect for the public sector in Red Hat Singapore, specializing in Cloud, Container, and Automation technologies. Before joining Red Hat, Li Ming has worked in engineering, R&D, and technology leadership roles. He spent the last 20+ years in Open Source out of which 10 years of that time was actively in High Performance Computing (HPC) and Big Data. He has also held numerous technology leadership roles in engineering, R&D, consulting and architecture.
개발자를 위한 AI Agent 관리 체계: Agent 365로 준비하는 에이전트 운영
AI 에이전트는 이제 단순한 실험 대상이 아니라, 실제 서비스와 업무 흐름에서 지속적으로 실행되는 소프트웨어 구성 요소가 되었습니다. 에이전트를 만들 수 있는 개발자는 많아졌지만, 에이전트를 안전하고 책임 있게 운영할 준비가 된 조직과 개발자는 아직 많지 않습니다. 이 세션에서는 AgentCon의 취지에 맞춰, 개발자가 반드시 고려해야 할 AI Agent 관리 체계를 중심으로 Agent 365를 살펴봅니다. Agent 365는 AI 에이전트를 위한 새로운 컨트롤 플레인(Control Plane)으로, 에이전트를 강화하고 보호하기 위한 표준적인 관리 기반을 제공합니다.
이를 위해 Agent 365가 제공하는 다섯 가지 핵심 관리 요소를 개발자 관점에서 설명합니다. 레지스트리(Registry) - 조직 내 모든 AI 에이전트를 식별하고, 관리 대상에 포함시키는 출발점
액세스 제어(Access Control) - 에이전트에 최소한의 권한만 부여하고, 위험한 상황에서는 접근을 제한하는 구조
시각화(Visualization) - 에이전트의 동작, 연결 관계, 영향도를 이해하기 위한 운영 가시성
상호 운용성(Interoperability) - 에이전트가 다양한 애플리케이션과 데이터, 업무 흐름 속에서 자연스럽게 동작하도록 하는 기반
보안(Security) - 에이전트를 대상으로 한 위협을 탐지하고, 에이전트가 사용하는 데이터와 결과를 보호하는 체계
이 세션은Agent를 ‘잘 만드는 방법’이 아니라, ‘계속 안전하게 운영하기 위해 개발자가 무엇을 준비해야 하는지’**에 초점을 둡니다. 에이전트를 실험 단계를 넘어 실제 환경에 배포하려는 개발자라면, 이 세션을 통해 에이전트 시대의 기본 운영 설계도를 가져갈 수 있을 것입니다.
Certifications & Recognition • Microsoft Certified Trainer (MCT) — 2008 ~ Present • Microsoft Certified Educator (MCE) — 2017 (UNESCO ICT Competency Framework for Teachers 기반) • Microsoft MVP (Most Valuable Professional) — 2006 ~ 2018 • Microsoft Office Specialist (MOS) Master Instructor — 2004 ~ Present • Certified Fundamentals - all - Azure, Microsoft 365, Security, Dynamics 365, Data, AI, Power Platform Project Management & Security Expertise • Cognitive Project Management in AI (CPMAI™) v7 — Plus, +E • Prosci Change Practitioner • PMP (Project Management Professional) • CISSP (Certified Information Systems Security Professional) + SME • ISO 27001 Auditor • ISO 19011 / 27001 / 27017 / 27018 Provisional Auditor Translator & Auditor Activities • ISC2 CISSP Exam Development Volunteer • PMBOK® 5th & 6th Edition ○ Translation Verification Committee (TVC) Member • Technical Translator & Auditor Publications (Co-Translation) • Mastering Windows Server 2012 (공동 번역) ISBN: 978-8956746449 • Security in Computing (공동 번역) ISBN: 979-1161750033 Education & Social Contribution • PMMDR (Project Management Methodology for Post Disaster Reconstruction) • PBL (Project Based Learning) with PMIEF (PMI Educational Foundation) Core Strength Areas (요약) • AI & Agent Governance • Enterprise Security Architecture • AI + Project / Change Management • Developer & IT Education • Global Standard & Certification (ISO, ISC2, PMI) Youtube o KTxMicrosoft AX Week: Evolving the Way We Work - Transforming Organizational Culture with Copilot - 2025 o LG SDC (Software Developer Conference): Judging Shorts Video – LG SW PM Competition 2025 o Microsoft Tech Conference & Experience Event LIVE: Driving Digital Twin Adoption in Manufacturing oMicrosoft Everywhere 2022: Introducing the Development Journey for Mixed Reality (MR) Developers
Don't Trust the LLM to Translate: Deterministic LLM Translation at scale
Most production LLM systems treat prompt engineering as one-size-fits-all. At Mercari, Japan's largest C2C marketplace, we discovered that's impossible when translating across linguistically incompatible target languages. This talks will give insights on how linguistic constraints forced two fundamentally different glossary architectures in our Gemini-powered marketplace translation system.
Gagan is working as engineer with mercari which is the largest C2C marketplace in japan on the cross border expansion efforts across 50+ countries .
Career Advance in the Age of AI
Building AI Is Easy. Changing How People Work Is Hard. Why Change Management Matters in AI Projects
Now managing the GTM programs in Small & Medium Customer Worked as Azure Success Manager, SMB Lead, Solution Specialist... in Microsoft. Worked as Sales in Citrix. Worked as Java Instructor in Sun Microsystems.
Agent Inception: Building bots with the Copilot CLI
Github's Copilot CLI is a sophisticated command-line agent for coding. In this talk, I'll use Copilot CLI to build an AI bot to play an online game.
CopperHead (https://github.com/revodavid/copperhead-server) is a tournament server for a 2-player Snake game that I created entirely using Copilot CLI and Claude Opus. I'll recount the process of building a game from scratch using agent prompting, and offer some tips and tricks I learned along the way for making this process easier, faster, and better aligned with your intentions.
CopperHead is designed to orchestrate multiple bots playing the game in a knockout tournament format. During the talk, I will demonstrate in real time the process of creating a new player bot with the Copilot CLI. I invite attendees to create competitor bots ahead of the talk, which I will include in a live competition for everyone to watch
David Smith is an AI team leader for Microsoft Developer Relations in Australia. A data scientist and Generative AI expert, he is a co-author of "Introduction to R" and a founding board member of the R Consortium. Follow David on social media as @revodavid.
Gemini AI Classroom Assistant: AI Agent Orchestration for Smarter Digital Learning
How can one teacher effectively monitor 75 screens in a computer lab? At HKIIT, we solved this challenge by building the Gemini AI Classroom Assistant, an AI Agent-powered system leveraging Vertex AI Gemini 3.0 and orchestrated with GenKit on Google Cloud. This talk explores how specialized AI Agents collaborate to transform classroom management:
Invigilator Agent: Detects unauthorized apps, AI chat tools, and academic dishonesty in real time. Wellness Coach Agent: Monitors engagement, frustration, and progress to provide proactive support. Analysis Agents: Process multimodal inputs (screenshots, videos) and trigger tools for messaging, irregularity logging, and progress tracking.
We’ll showcase how these AI Agents interact through serverless flows, leveraging Firebase, Cloud Functions, and Firestore for scalable, secure orchestration. Expect a live demo of agent-driven interventions and insights that empower teachers to focus on teaching while AI handles compliance and welfare. Key Takeaways:
Understand how AI Agents redefine classroom monitoring and engagement. Explore agent roles and tool orchestration using GenKit. Learn the architecture behind real-time multimodal analysis at scale. See how AI Agents collaborate to deliver actionable insights for educators.
Cyrus Wong is an accomplished senior lecturer who oversees the Higher Diploma program in Cloud and Data Centre Administration at the Hong Kong Institute of Information Technology (HKIIT) at IVE(Lee Wai Lee) in Hong Kong. He is a passionate advocate for the adoption of cloud technology across various media and events. With his extensive knowledge and expertise, he has earned prestigious recognitions such as AWS AI Hero, Microsoft MVP - Azure AI, and Google Developer Expert for AI & Google Cloud Platform. 黃俊彥是香港香港資訊科技學院(HKIIT)位於 IVE(李惠利)資訊科技系雲端系統及數據中心管理高級文憑的高級講師，擁有豐富的知識和專業技能。他熱衷於在各種媒體和活動中推廣雲端技術。由於他的專業知識和專業技能，他獲得亞馬遜雲端運算服務AI英雄、微軟Azure AI最有價值專家和Google AI & 雲端平台的Google開發者專家等著名榮譽稱號，是世上唯一能夠獲得IT業界三巨頭同時公認的專家。
May the best bot win: Build a competitive game bot with agents
In this 90-minute workshop, you will use the GitHub Copilot CLI to build an automated bot what will play in a 2-player version of the Snake game. At the conclusion of the workshop, all bots will compete in a knockout tournament on a CopperHead (https://github.com/revodavid/copperhead-server) game server, and the last bot standing will be declared the winner.
Github's Copilot CLI (https://github.com/features/copilot/cli/) is a sophisticated command-line agent for coding, and can be used effectively by anyone with any level of programming experience. You are welcome to use other coding agents as well, but we will provide brief instruction on GitHub Copilot CLI at the beginning of the workshop for newcomers. The rest of the workshop will be spent in small teams coding your bot and competing in the tournament.
David Smith is an AI team leader for Microsoft Developer Relations in Australia. A data scientist and Generative AI expert, he is a co-author of "Introduction to R" and a founding board member of the R Consortium. Follow David on social media as @revodavid.
When/Where should I use Agent Framework? | 에이전트 프레임워크 어디에다 쓰는 거예요?
It's a game changer! Since the successful launch of Semantic Kernel, it has evolved to Microsoft Agent Framework (MAF) by merging AutoGen, and gets more powerful. But developers keep asking me when and where to use it.
Microsoft offers three ways of developing AI agents, and MAF is one of them. Throughout this session, I'm going to discuss why MAF is important for developers to know by comparing to the other two approaches. At the end of this session, audiences will have basic understandings how easy MAF is to build an agentic AI systems.
Semantic Kernel의 성공적인 론치 이후 이는 AutoGen을 흡수하면서 Microsoft Agent Framework(MAF)로 탈바꿈했습니다. 이제 이 생태계에서 완전히 게임체인저로 자리잡게 됐습니다! 하지만 여전히 개발자 커뮤니티에서는 언제 그리고 어떤 상황에서 MAF를 쓰는 것이 좋은지 물어보곤 합니다.
Microsoft는 AI 에이전트를 만드는 세 가지 방법을 제시합니다. MAF는 그 중 하나죠. 이 세션을 통해 MAF가 다른 두 가지 접근방식과 비교해 특히 개발자들에게 있어서 왜 중요한지 다뤄볼 예정입니다. 세션이 끝나고 나면 참가자들은 에이전틱 AI 시스템을 만드는 데 있어서 MAF 사용법이 얼마나 쉬운지에 대한 기본적인 이해를 할 수 있게 될 것입니다.
Justin is a Principal Developer Advocate at Microsoft and was double-awarded Microsoft MVP in both Azure and Developer Technologies in 2015-2019. He always seeks for ways to improve developer velocity and productivity with various tools.
비개발자가 GitHub Copilot으로 팀 전용 AI 비서를 만든 이야기
제조업계 5명 팀을 이끄는 비개발자가 VS Code와 GitHub Copilot만으로 팀 전용 AI 비서를 만들고 운영한 실제 사례입니다. Claude Code도 Cursor도 허용되지 않는 엔터프라이즈 환경에서, copilot-instructions.md와 Skills 기능을 활용해 주간 로그 작성부터 이메일 발송, 특허 조사, 디자인 자동화까지 구현했습니다. 코드가 아닌 마크다운 파일 작성으로 시작해, SharePoint + JSON + Power Automate를 연결한 서버 없는 아키텍처와 구체적인 구현 방법을 공유합니다. "개발자가 아니라서" 망설이는 분들께, 회사에 이미 있는 도구만으로도 충분히 가능하다는 것을 보여드립니다.
Youngbin Lee is an engineer with 20 years of experience in the automotive industry, currently leading the Innovation Strategy and Development Team at GM Technical Center Korea. Throughout her career, she has been passionate about work automation and leveraging tools like Office and Power Platform, which naturally led her to explore AI capabilities. Her main challenge: helping a traditionally slow-moving organization adapt to rapid change through innovative approaches.
Implementing 5 multi-agent workflow patterns | 다섯가지 멀티에이전트 패턴 구현해보기
There are five multi-agent workflow patterns commonly used, but it's tricky to implement without fully understanding agent frameworks. Microsoft Agent Framework (MAF) offers built-in ways to implement those workflow patterns.
Throughout this workshop, I'm going to provide hands-on materials to implement those patterns so that participants can easily follow up in their own pace.
At the end of the workshop, participants will have implemented those multi-agent workflow patterns using MAF.
멀티 에이전트 워크플로우를 구축하는데 있어 흔히 쓰이는 다섯 가지 패턴이 있습니다. 하지만, 사용하고자 하는 에이전트 프레임워크에 대한 충분한 이해가 없이는 구현하기가 쉽지 않죠. Microsoft Agent Framework(MAF)는 이러한 패턴을 손쉽게 구축할 수 있는 방법을 이미 내재하고 있습니다.
이 워크샵 시간에는 MAF를 이용해 이러한 패턴을 손쉽게 구현할 수 있는 핸즈온 워크샵 자료를 제공합니다. 참가자들은 자신의 페이스에 맞춰서 자료를 따라 멀티 에이전트 워크플로우 패턴을 직접 구현해 볼 수 있습니다.
워크샵 세션이 끝난 후 참가자들은 MAF를 이용해 적어도 한 번 이상 워크플로우 패턴을 구현하고 이를 실무에 적용시킬 수 있는 인사이트를 얻을 수 있게 됩니다.
Justin is a Principal Developer Advocate at Microsoft and was double-awarded Microsoft MVP in both Azure and Developer Technologies in 2015-2019. He always seeks for ways to improve developer velocity and productivity with various tools.
AI Changes How We Work — In the Vibe Era, from Data Insights to Enterprise Apps
The vibe coding era is here. Tell AI what you need in plain language, and it writes the code, builds the app, and designs the dashboard. It's impressive — but one very real question remains:
"It's easy to make a great demo, but how do I actually apply this to my company's day-to-day work?"
Sam Heo, a Power Platform MVP with over 30 years of hands-on IT experience driving digital transformation for SMBs, combines Power BI with MCP (Model Context Protocol) to show how business users can build production-ready dashboards by simply talking to AI — no DAX formulas, no data modeling expertise required. From analyzing table structures to generating themes and creating measures, AI executes while humans make the decisions.
Then Jaeseok Lee MVP opens the world of Vibe.PowerApps. Using M365 Copilot's App Builder and the Power Apps Vibe Builder, he demonstrates a new development experience where a team of AI agents takes you from requirements definition to full-stack app deployment in one seamless flow. You'll see business apps come to life — without writing code — on top of Dataverse with enterprise-grade security and governance built in.
This session goes beyond knowing the technology. It tackles a concrete challenge: how to take decades of legacy systems and manual processes and innovate 10x faster with AI and Power Platform. There's no magic wand — but there is a platform that empowers the people closest to the process to drive the transformation themselves.
Microsoft Business Applications MVP with 30+ years of IT infrastructure and enterprise systems experience. Specializing in Power Platform (Power Automate, Power BI, Power Apps) consulting and Microsoft Dynamics Business Central ERP implementation. Administrator of the Power Platform Korea User Group (1,000+ members). Passionate about helping SMBs adopt AI and automation without complex coding — delivering innovative, cost-effective digital transformation through hands-on training and real-world use cases.
Microsoft AI, 비즈니스 애플리케이션 MVP 입니다. 파워플랫폼 한국 사용자 그룹에서 에이전트와 노코드 기술에 대해서 재미난 실습으로 커뮤니티 생활을 하고 있습니다.
This is how it looked
Made possible by
Made possible by:
