About us
Whether you want to get started with AI and the latest technology or you're building your career or the next great idea, Microsoft Reactor connects you with the developers and startups that share your goals.
Microsoft Reactors are centers for free technical learning and sharing, where developers and startup professionals can connect with the local community and build new skills to drive innovation.
Virtual events are running around the clock so join us anytime, anywhere!
Are you a Meetup organizer? Contact us to use our space: ReactorSYD@Microsoft.com
Learn more at: https://aka.ms/developer.microsoft/reactor
Many of our virtual workshops are recorded and then uploaded to our YouTube channel:Â Microsoft Reactor - YouTube
Upcoming events
5
Build Secure, Observable, Production-ready Agents with a Control Plane
·OnlineOnlineBrought to you by Microsoft and NVIDIA
Orchestrate, secure and observe agents enabling advanced AI workflows. Reliable agent orchestration requires clear separation between control and execution. In this joint session, Microsoft and NVIDIA present a multi-agent architecture where Foundry Agent Service coordinates GPU-backed agents running on Azure Container Apps.
Using a document processing scenario with multiple open-source models including NVIDIA Nemotron models, we show how agents route requests, apply security controls, and monitor execution across GPU workloads, producing consistent and explainable results suitable for production environments.
đź”” This session will be presented in two time zones. For our earlier stream, click here
14 attendees
Write the Spec, Let the Agents Build: A Practical Playbook
·OnlineOnlineIn this episode of New Breakpoint, Arnauld Lheureux joins host Michelle Sandford for a hands-on guide to shipping with confidence in an agent powered world.
The core idea is simple: treat the spec as the product, and let agents do the heavy lifting, as long as you give them the right constraints.
Arnauld walks through what makes a spec implementable:
• Clear outcomes
• Non-goals
• Edge cases
• Acceptance criteria
• The smallest testable sliceFrom there, we unpack how to translate that spec into high quality agent tasks for implementation, tests, refactors, and documentation, while keeping humans in control of intent and tradeoffs.
You will learn practical prompting patterns, review checkpoints, and how to avoid the common failure modes like scope creep, plausible but wrong code, and inconsistent behavior across environments.
We close with an enterprise lens: how teams use GitHub Enterprise to operationalize this approach with governance, security boundaries, and a growing ecosystem of custom and third-party agents.
If you want a repeatable playbook that turns specs into merged pull requests with less toil and fewer surprises, this is the episode.
36 attendees
Microsoft JDConf 2026 (APAC)
·OnlineOnlineJoin us at Microsoft JDConf 2026, a global virtual Java Developer Conference on April 8-9. This year’s JDConf focuses on empowering Java developers to build and scale modern, intelligent, and cloud-native applications. With the rise of large language models (LLMs), agent-oriented architectures, and AI-driven development, JDConf 2026 will showcase how Java remains central to enterprise innovation.
We’ll cover key topics such as:
- AI-Native Java and AI-Assisted Development
- App Modernization and Next-Generation Cloud:
- Tools, Automation, and Responsible AI Operations
- Sustainable, Secure, and Efficient Java
- AI Success Stories and Customer Journeys
## 🌎 Asia-Pacific Stream
Program order to come; please check jdconf.com for the latest details---
1. Bootiful Spring AI
Speaker: Josh Long (Broadcom)
The age of artificial intelligence is nearly at hand, and it's everywhere! But is it in your application? It should be. AI is about integration, and here the Java and Spring communities come second to nobody. In this talk, we'll demystify the concepts of modern-day Artificial Intelligence and look at its integration with the Spring AI project, a framework that builds on the richness of Spring Boot to extend them to the wide world of AI engineering.
---
2. Hidden Requirements for Agentic Coding: Spec-Driven Development with BDD Problem Personas
Speaker: Nils Hyoma (MHP - A Porsche Company)
Agentic coding only works as well as the spec you give it. If your Spec-Driven Development focuses on the happy path, your agent will confidently implement only that behavior.
This interactive session introduces BDD Problem Personas to uncover hidden requirements, edge cases, negative paths, and real-user behavior, and convert them into executable BDD scenarios that guide agentic implementation. You'll see the approach in two forms: an interactive card-based persona round for refinement and a GitHub Copilot Custom Chat Mode in VS Code that applies the same persona lens while you write/refine specs or analyze your existing code for gaps (missing checks, unhandled states, weak tests, risky assumptions).
You'll leave with a repeatable and downloadable workflow and examples for development teams: stronger acceptance criteria, better scenario coverage beyond the happy path, and clearer instructions that agents can implement safely.
Resources (chat modes + cards): github.com/nilsbert/bdd-problem-personas
---
3. Orchestrating AI Agents with Java Pattern Matching
Speaker: Haim Michael (Bar-Ilan University)
Modern software systems increasingly rely on agent-based components that reason, invoke tools, and collaborate with other agents. In such systems, the central engineering challenge is orchestration: deciding what happens next based on uncertain, structured, and sometimes incomplete outcomes produced by AI models. Java's modern pattern-matching features provide a natural and highly expressive foundation for implementing this orchestration logic in a safe and maintainable way.
The talk starts with a concise overview of pattern matching support in recent Java versions, including pattern matching for instanceof, records, sealed hierarchies, and switch. It then moves from language features to architectural design, showing how agent outputs can be modeled as explicit result types and how pattern matching enables clear routing, delegation, retries, fallbacks, and termination decisions.
Through practical, code-focused examples, the session demonstrates common orchestration scenarios, illustrating how pattern matching helps turn probabilistic agent behavior into deterministic, auditable control flow.
---
4. Secrets from Microsoft's Agentic DevOps Transformation
Speaker: Jenny Ferries (Microsoft)
Agentic DevOps is shaping the future of software engineering, driving productivity and innovation through automation and intelligent collaboration. Learn how to:
- Use specialized AI agents throughout the development workflow to maximize impact and accelerate individual developer productivity
- Leverage the framework for co-creative partnership with agents
- Scale AI-driven development practices across teams, overcoming common challenges
Gain practical insights and strategies from Microsoft's journey to empower your own DevOps transformation.
---
5. AI-Driven Development: Practical Approaches to Safely Introducing AI into Large Monolithic Systems
Speaker: Yoshio Terada (Microsoft)
AI-driven development has been gaining traction for more than a year, and many developers have begun leveraging it in small projects, greenfield development, or microservices. However, when it comes to large and complex monolithic systems, applying AI "as-is" becomes challenging due to context-size limitations and the inherent complexity of the existing codebase.
Key topics covered:
- AI-driven development is feasible—even with massive legacy systems
- Strategies for overcoming AI's context-size limitations
- Practical techniques for preventing AI from breaking existing specifications or code
- Lessons learned, best practices, and important considerations for real-world adoption
This session is designed for engineers working in organizations with substantial legacy codebases who want to adopt AI-driven development more confidently and effectively.
---
6. AgentScope Java: Effortless Enterprise Agents for Java Developers
Speaker: Heqing Jiang (Alibaba)
This session introduces AgentScope Java, a new framework designed to bridge the gap between AI prototypes and enterprise production. We will explore how Java developers can leverage its advanced ReAct paradigm, safety sandboxes, and high-performance architecture to build stable, autonomous agents ready for real-world business scenarios.
---
7. Deploying to Production with Confidence
Speaker: Andres Almiray (Java Champion)
How many times have we asked ourselves if it is a good idea to release to production on a Friday afternoon? Is the production software sufficiently robust and/or resilient to vulnerabilities? How can we detect and correct security problems in production?
In recent years, the topic of Software Supply Chain Security has taken on greater importance. Concepts like SBOMs, SLSA, Reproducible Builds, and CI/CD Security are widely discussed to answer these questions. In this session we will discover what these concepts are and how you may apply them to your own projects.
---
8. Maintaining Legacy Applications Using AI Tooling
Speaker: Cristian Schuszter (CERN)
This session focuses on building a working knowledge of available AI tooling that can help developers be more productive in their day-to-day work, with a focus on existing applications and their evolution. We'll talk about techniques and methods to refactor and update your applications, while keeping things manageable, readable, and at the level of code quality expected from an enterprise application.
We'll also discuss the MCP protocol and how it can be used to supercharge your developer tooling further—exploring how to use existing resources to obtain better information for design, code implementation, API endpoints, and more. We'll also explore what it takes to build one of these servers in case you need to offer an MCP server to colleagues.
---
10 attendees
Past events
1120
