/Events /AgentCon 2025 - Singapore
AgentCon 2025 - Singapore
This event is part of AgentCon, organized by Global AI Singapore.
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
Registration
Main Track | Building 1, Albert Hong Lecture Theatre · 08:45–09:15Human Agency: Lowering Barriers, Raising the Bar
How might we put human agency back into AI agents? In this session, SUTD will share short case studies of how they have helped people across all age groups and skill levels to make the most of AI to uplift the lives of those around them. These case studies span work resilience, education and training, and creativity and innovation. They show how we can stay grounded in care, kindness, and human values, amidst the accelerating advances in AI.
Welcome to AgentCon Singapore
Dux Raymond Sy
Human in the Loop: Guardrails for AI’s Wild Side
We're on Year 3 of the Generative AI extravaganza and Year 1 of AI Agents. We are starting to discover that while BUILDING the Agent seems kind of straightforward, getting Agents to Actually Work is…not straightforward and definitely not simple.
In this AgentCon keynote, learn how to get your AI Agents to behave themselves but also let's together figure out what makes us uniquely human and what is OUR role in the AI-verse.
Bringing AI Agents to Life with Azure AI Foundry
AI agents are moving beyond text boxes into real-world interactions — combining models, tools, and avatars to deliver human-like experiences. In this session, we’ll explore how to build an end-to-end solution with Azure AI Foundry, weaving together model selection, instruction design, and tool integration into a single workflow. As a live scenario, we’ll create an AI agent that can order a pizza through a connected MCP server — and then bring it to life with a real avatar for natural, conversational interactions. You’ll leave with a clear view of how to turn prompts and models into full-fledged, real-world AI agents.
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.
Agent Activated: The New Era of SharePoint Collaboration
The future of workplace collaboration is here and it's intellligent, adaptive, and powered by AI. In this session, we'll explore how SharePoint Agents are revolutionizing how we interact with SharePoint content, automate tasks and enhance team productivity.
Join us as we unpack real-world scenarios, demonstrate how to activate and configure Agents, and discuss their impact on employee experience and content management.
SharePoint / Power Platform Administrator and a Dual Microsoft MVP in Business Application and Microsoft 365. I am curious about how things work, especially when it comes to technology. Learning and connecting were my great companions. I want to help others by leveraging the value of Microsoft 365's services. I try to help the tech community as much as possible, as I enjoy doing so in any way I can.
Lunch
Main Track | Building 1, Albert Hong Lecture Theatre · 13:20–14:05Multi-Agent Systems in Business
AI agents aren’t sci-fi anymore — they’re already solving real business problems today. In this session, we’ll go beyond theory and show how multi-agent systems can collaborate to extract insights from live business data using the AutoGen framework and ERP (Business Central) API's.
We’ll build a real working agentic system step by step, connect it to business data, and show how agents talk, think, and act — with tools, memory, and knowledge. Then comes the fun part: a live “Agent vs. Human” challenge, where our agent team goes head-to-head with a brave audience member to answer questions using nothing but documentation (and brains).
If you’re building agent-powered enterprise apps or just curious how far we can push the agent stack — join us for an entertaining, technical, and practical tour of what agents can already do today.
Dmitry is a Business Central expert with over 20 years of experience. He has held roles ranging from developer to business owner. Since earning the MVP title in 2018, Dmitry has consistently shared his expertise through blogs, conferences and community contributions. In 2023, he created CentralQ.ai, an AI-powered search built on the knowledge of the Business Central community, quickly becoming a must-have tool for professionals. Known for turning bold ideas into reality, Dmitry continues to push the boundaries of AI in Microsoft Business Central.
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.
Chat with your Data Using Vector Search
Discover the Power of Vector Search with Azure SQL! There's a new way to search — and it's smarter than ever. Join us for an exciting session where we’ll explore how Azure AI Services and LangChain seamlessly integrate with Azure SQL’s vector search capabilities. Learn how to build chat-enabled applications that interact directly with your operational data, unlocking new possibilities for intelligent, real-time insights. Whether you're modernizing existing systems or building from scratch, this session will show you how to bring conversational AI to your data — effortlessly.
Pio Balistoy is a Filipino Microsoft MVP for Data Platform based in Singapore. Currently a Lead Data Platform Consultant at Pythian, he helps businesses drive transformation through data, analytics, and cloud. He frequently organizes and speaks at user groups and conferences in the APAC region.
Break
Main Track | Building 1, Albert Hong Lecture Theatre · 15:30–16:15Playing with Fire: Unethical AI
AI is powerful, accessible, and incredibly easy to misuse. In this talk, I’ll walk through a series of intentionally provocative projects I’ve built, like an app that writes breakup texts using GPT or one that helps people generate fake excuses to skip meetings. These aren’t just jokes, they’re experiments meant to expose how AI can quietly enable unethical behavior.
Through these weird and sometimes uncomfortable tools, I’ll explore the ethical grey zones we often ignore: how small design choices shape user intent, how automation detaches us from responsibility, and how quickly things can spiral when no one’s watching.
This session isn’t about solutions, it’s about asking better questions. If you’re building with AI, you need to know just how easy it is to cross the line. Sometimes without realizing it.
Elian Van Cutsem or "ElianCodes" is a full-stack developer, creative technologist, and all-around internet troublemaker based in Belgium. He’s the CTO at Vulpo and works in Developer Relations at React Bricks, focusing on developer experience, documentation, and education. Previously, he was a Software Engineer and core maintainer at Astro. Elian is also a co-organizer of several major JavaScript communities and events, including BeJS, React Paris, React Brussels, and React Africa. Alongside his professional work, he creates provocative and experimental AI projects, designed to challenge our assumptions about ethics, automation, and human behavior. His work blends code and commentary, often in ways that are both hilarious and uncomfortably real. Elian is known for his passion, puns, and offbeat sense of humor. His talks combine technical insight with a strong dose of creative chaos—guaranteed fun on stage.
Closing Remarks
Dux Raymond Sy
Multi‑Agent orchestration in Copilot Studio
Microsoft announced multi-agent capabilities in Copilot Studio in May this year. This allows you to build agents that do not just make use of other tools and systems but also interact with other agents. In this session, we will have a practical look at how you can set up multiple dedicated-purpose agents and have them work together towards a specified goal. You will walk away with practical tips on prompt design, testing, and refining agent orchestration for real-world use cases.
Rene is a Microsoft M365 Apps &Services MVP, working as a Power Platform Tech Lead in Singapore. For more than 15 years, Rene has lived and worked in Europe and Asia Pacific. His main focus currently is the Power Platform, including effective governance and management. In previous roles, he worked extensively with SharePoint and Office 365.
Transforming Contact Centers with Scalable AI: Leveraging AI for Real-Time Voice Intelligence
Contact centers are undergoing rapid evolution by integrating cutting-edge AI technologies to enhance user experiences, reduce operational costs, and enable scalable solutions. In this session, we’ll explore how Azure and NVIDIA are jointly powering next-generation contact center AI systems through advanced speech services, multi-turn retrieval-augmented generation (RAG), and finely-tuned large language models (LLMs) to deliver natural, responsive, and secure voice interactions.
This webinar will offer practical guidance on designing, optimizing, and scaling voice-first AI agent workflows, transitioning from traditional IVR systems to real-time conversational AI. You’ll learn how to incorporate contextual member data for personalization and deploy production-grade AI using Azure & NVIDIA infrastructure
Ashish is a Solution Architect, focusing on cloud infrastructure and AI integration. With a commitment to helping organizations harness the power of cloud technology, he provides tailored solutions for diverse industries. Passionate about community engagement, Ashish shares insights and best practices to guide businesses on their AI journeys. He also mentor aspiring tech professionals and lead workshops, fostering a culture of continuous learning and collaboration in the evolving landscape of AI and cloud solutions.
Building Trustworthy AI Agents
In a world where AI agents are making decisions faster than we can blink, trust isn’t optional, it’s mission critical. This session dives into the architecture of trustworthy AI agents, spotlighting transparency, reliability, governance, ethics, and security.
We’ll unpack the layers that make agents explainable, auditable, and observable and why that matters. From failover strategies and robustness testing to real-time threat detection and the principle of least privilege, we’ll explore how to build agents that don’t just work but also earn trust.
You’ll get practical guidance on operationalizing trust: mapping the trust terrain, designing for observable signals, implementing guardrails, and setting up verification loops.
If you care about building agents that are not just smart but safe, ethical, and resilient—this talk is your blueprint. Let’s build a culture of agent literacy and make trust the default.
I live at the heart of the coding community and help drive awareness and engagement as a developer advocate and technology evangelist. I present at around 50 Conferences and Events around the world each year on AI, Azure, GitHub, Open Source, GameDev and LinkedIn (Including NDC Oslo, London, Copenhagen, Porto, Melbourne; Techorama BE & NL; DDDPerth; GCAP; Google Dev Fest, MS TechReady, MS GeekReady, MS Ignite etc). I judge hackathons and encourage the next generation into technology careers. In 2023 I became the host of the Microsoft ANZ web show - New Breakpoint, which is a show for developers by developers. I am also a co-organiser for the Rust Perth Community Group. I was the #1 Microsoft Social Seller (highest engagement) on LinkedIn for several years and remain #1 SSI rank in team, top 1% in industry and top 1% in network. I run the Microsoft Student Accelerator Program for ANZ encouraging emerging developers to build on Azure.
Scalable AI with Memory: Orleans and Semantic Kernel for Distributed Agents
Learn how to combine Microsoft Orleans and Semantic Kernel to build intelligent, distributed AI agents with memory, tool support, and seamless scalability.
I love automating stuff 😎
Supercharge Your Development with Azure MCP in Visual Studio Code
AI agents are transforming the way developers deploy on Azure, and the Model Context Protocol (MCP) marks the next evolution in simplifying agent deployment.
This session to explore how Azure MCP integrates seamlessly with Visual Studio Code, streamlining and enhancing your development workflow.
Nicholas Chang is a Senior Platform Engineer at Kainos with a deep passion for Microsoft Azure. With extensive experience in cloud technologies and a focus on Azure, he is the founder of the Microsoft Azure Community User Group, where he fosters knowledge sharing, collaboration, and growth within the tech community. Nicholas is also the creator and host of the Microsoft Community Insights podcast, where he connects with industry leaders and shares valuable insights about Azure and the broader tech ecosystem. As a dedicated community advocate, Nicholas contributes by speaking at events and sharing his expertise through his blog, nicholaschangblog.com. You can connect with him on Twitter: @nick_cloudops or visit his blog to learn more.
NLP, LLM and AI Agents: A great combination
We're diving into an exciting new area of AI where computers don't just understand us, but actually take action. It all begins with Natural Language Processing (NLP), the foundation that taught machines to understand human language. Building on this, Large Language Models (LLMs) like ChatGPT emerged as super-smart brains, capable of generating text, reasoning, and answering complex questions with incredible skill. Then, there are AI Agents: these are programs designed to think, plan, remember, and use tools to achieve specific goals, giving AI the ability to do things.
The real power comes from combining these. The LLM acts as the intelligent "brain" for the AI Agent, helping it understand complex requests and figure out the best steps to take. In turn, the AI Agent provides the "body," executing these plans by using various digital tools, like searching the internet, sending emails, or running code. This collaboration means AI can move beyond just chatting to actually solving multi-step problems in the real (digital) world.
However, a crucial insight is that not every task needs the massive power of an LLM. For many simpler, specific jobs – like finding a name in a text or classifying a simple email – traditional NLP methods are much faster, cheaper, and more accurate. A truly smart AI Agent will intelligently use the LLM for deep thinking and planning, but also rely on these efficient, specialized NLP tools for quick, straightforward tasks. This smart combination of advanced reasoning and efficient execution is what makes these new AI systems so powerful and adaptive.
Highly motivated LLM Scientist with over three years of experience, specializing in advancing the reasoning, planning, and performance of foundation models. Proven expertise across the model de- velopment lifecycle, including large-scale data synthesis, supervised fine-tuning (SFT), reinforcement learning principles, and developing robust evaluation benchmarks (e.g., VMLU - ACL 2025). Key contributor to developing state-of-the-art Vietnamese Large Language Models (KiLM, VinaLLaMA) and Vision Language Models, significantly improving performance on complex language understanding, generation, and multi-modal reasoning tasks.
Building a Conversational AI Agent with Google ADK (A Hands-On POC)
This session is a hands-on walkthrough of building a real conversational AI agent using the Google Agent Development Kit (ADK). We’ll explore how to create a news discovery assistant that can understand user preferences, fetch relevant articles in real time, summarize content, and engage in intelligent conversation all powered by LLMs like Gemini and augmented with external tools. The talk demonstrates how ADK simplifies agent development and equips developers to build useful, extensible AI applications with clean architecture and production-readiness in mind.
I am a software engineer with years of professional experience developing, testing, deploying, and maintaining robust software applications. I excel in creating innovative solutions and seamless user experiences. Beyond my technical skills, I am passionate about physical wellness and enjoy regular workouts to maintain a healthy and active lifestyle.
From Zero to PizzaBot: Building AI Agents with Azure AI Foundry
You will need a laptop for this workshop
In this hands-on workshop, you’ll learn how to build intelligent, domain-specific AI agents using Azure AI Foundry Agent Service. Starting from a simple “hello world” agent, you’ll progressively enhance it with system prompts, custom instructions, and external knowledge via RAG (Retrieval-Augmented Generation). You’ll then extend your agent with tool calling, enabling it to run custom functions like a pizza calculator, and finally integrate with external services through the Model Context Protocol (MCP) for live menu and order management. By the end of the workshop, you’ll have a fully functional Contoso PizzaBot—an AI assistant that can answer questions, recommend pizzas, manage orders, and stay grounded in real business data.
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.
Build your first agent with Azure AI Agent Service
You will need a laptop for this workshop
Imagine you are a sales manager at Contoso, a multinational retail company that sells outdoor equipment. You need to analyze sales data to find trends, understand customer preferences, and make informed business decisions. To help you, Contoso has developed a conversational agent that can answer questions about your sales data.
Goloknath Mishra is working as Senior IT Architect in NCS Pte Ltd. having more than 15 Years of Techno Functional Expertise in architecting and managing digital transformation projects with Microsoft Dynamics 365/Power Platform as technology enabler. Tech Community evangelist, Author, speaker, Youtuber, Microsoft Most Valuable Professional (MVP) & Microsoft Certified Trainer (MCT), Udemy Instructor, Speaker, Blogger, Youtuber, Microsoft Dynamics 365, Power Platform & Azure Enthusiast. He is running Microsoft User Group in Singapore and Odisha focusing on Microsoft Dynamics 365 and Power Platform.
This is how it looked
Made possible by
Made possible by:
Explore AgentCon
AI Agents Developer Conference
AgentCon made possible by:
