GitHub Copilot is far more than just an autocomplete tool: it can research and plan work, run in the background, collaborate across sessions, and automate repo maintenance. In this hands-on workshop, we’ll explore agentic engineering on GitHub: starting with research and planning, moving into async handoffs and parallel threads, customizing and steering multiple agents, skills and plugins and GitHub Agentic Workflows. Attendees will learn how to structure work for agents, how to customize and personalize Copilot, preserve context across handoffs, orchestrate multiple agents safely, and keep humans in control while accelerating throughput. Prerequisites: https://gist.github.com/joshjohanning/6078cad11106ff05679ac22741bbbbe3

Step into the future of software architecture with this dynamic, code-driven workshop designed for architects and developers ready to dive deep into the essential patterns and practices of modern distributed applications. From microservices and CQRS to Event Sourcing, GraphQL-driven data access, and real-time notifications, we’ll cover the critical components that power today’s scalable, resilient systems. AI-proofing with LLM integration rounds things off nicely. With a focus on decision-making in complex, real-world scenarios, this workshop guides you through optimizing service communication, token-based security, and implementing robust telemetry, metrics, and logging. A versatile sample application demonstrates both monolithic and fully distributed setups, flexible enough to support multiple languages, including JavaScript and C#. Come ready to explore containerized samples, get hands-on with the code, and walk away with a fully functional, flexible architecture that you can start using immediately! Prerequisites: The workshop is a very detailed presentation with many demos and lots of code samples. There are no specific practice tasks, but the source code of all samples is made available early in the day and many attendees choose to work along with the presentation, or experiment with the samples on the side, or during the breaks. All questions are welcome and we'll answer as much as possible during the day! To run the demo apps, the main requirement is Docker, or a compatible container runtime. A second large demo runs directly on a locally installed Node.js. Of course you may want to use VS Code or an IDE of your choice to check out the source code. Whether you decide to work along or just listen, the day is packed with concepts and content, so you will take loads of ideas with you even if you leave your laptop alone during the day.

Software architecture is all about trade off decisions. Knowing the characteristics of different architectural styles and how they vary is key to making informed decisions about software architecture. In this workshop, you will: - Learn laws and principles of software architecture - Review and extend custom sample apps built with multiple architectural styles - Visualize and understand differences in system component communication mechanisms - Create and leverage decision records for team and AI usage - Identify ways to enforce architectural decisions and detect and prevent drift Students will leave with C# source code for several different working architectural styles as well as slides, notes, and LLM agents and skills they can apply immediately. Prerequisites: Laptop with dotnet 10 sdk and any ide/editor of choice will suffice. And git.

Whether we like it or not, the days when developers write most of the code are over. At the same time, AI-assisted coding has a reputation problem. For many experienced developers, “vibe coding” means spaghetti prompts, hallucinated logic, and unreviewable messes that collapse the moment they hit production. AI To be fair, the people who abuse this term are also the people who probably fall under this category. I prefer “Agentic Programming” instead. I have pushed thousands of lines of code in production using agentic programming. Code that would have taken me months to write myself now takes merely days. In this workshop, we’ll explore agentic programming as a disciplined engineering practice, not a toy. Using Claude Code, I’ll show how to collaborate with AI agents to produce maintainable, reviewable, and production-ready code, without surrendering architectural control, correctness, or performance. We will cover: - What Claude Code, Codex and Cursor are, how they work, and how you should use them - Designing clear agent boundaries and responsibilities. - How to turn vague intent into explicit, testable instructions. - Create plans that can run for hours on end, generating and testing code as they go. - Securing your agentic code - Skills - Plugins for automating repetitive tasks - Much more (workshop contents are constantly updated as new models and tools are released) This is not a “let the AI take the wheel” session. It’s about teaching the AI to work like a senior engineer, while you stay firmly in charge. If you believe AI coding tools are dangerous, flaky, or fundamentally incompatible with serious software engineering, then this workshop is for you. Requirements: - A laptop with your favourite IDE installed - Node and .NET 10 - Git - A GitHub account - Claude Code Access - Codex Access - Cursor Access