With the popularity of Chat-GPT and Copilots comes the inevitable speculation of where we are on the AI hype cycle. Are we dealing with "glorified statistics", or is there more to this? In this talk we'll look at the wiring under the board, and what really lies behind Large Language Models like GPT-4. After taking a broad look at Artificial Intelligence and Machine Learning, we'll look at principles like transfer learning, and transformer architectures. As well as the theory, we'll see how it's been applied to solving real problems. And we'll also try to get a feel for where the current AI models sit in relation to human intelligence. Finally, we'll look at the broader AI hype cycle, consider the ethical and existential risks in this rapidly moving field, and see how close we are to artificial general intelligence.

Large language models have been a game changer, but they have their limitations. They only know what was generally available up to the point they were trained. They don't have access to recent events, or your own private data. What's worse, if you ask them about something they don't know about, they start making stuff up! That's why we need to build more sophisticated solutions that combine different models, add some prompt engineering and RAG (Retrieval Augmented Generation), as well as some custom code or plugins, and then a few more layers of safety and responsible AI checks. When you want to combine multiple skills and perform tasks to achieve an objective, you can use Microsoft Agent Framework to handle all the low-level details of handling LLMs. Microsoft Agent Framework is an SDK, available in C# and Python. In this talk, we'll focus on the C# version and build enterprise solutions with .NET. You'll see how we can use it to build an "agent", that goes beyond text responses and that actually does something.

Extending Microsoft 365 Copilot is a great way of getting your custom applications in the hands of business users, because you're making it available right where they're working. But there's quite a bit of setup involved in getting up and running - or rather there was. By using the Microsoft 365 Agents Toolkit we can quickly get a Copilot Declarative or Custom Engine Agent built and delivering awesomeness, because the tooling does all the configuration grunt work, leaving us to focus on what we do best - code!

GitHub has significantly enhanced its Copilot offering with the release of agent mode. This feature streamlines and automates code editing workflows, allowing developers to iterate on code changes more efficiently using natural language prompts. Agent mode takes GitHub Copilot even further by enabling Copilot to autonomously plan and execute tasks, including suggesting and running terminal commands, and iterating to resolve issues. These advancements signify a move towards a more "agentic AI" that proactively assists developers throughout the development lifecycle. We'll be mainly using C# and TypeScript languages (not that it matters quite so much when you have an agent to worry about syntax!).

In this intense session I'll show you six ways you can deliver a huge amount of business benefit to almost any organization with a moderate amount of development effort. In a series of quick-fire demos, we'll look at Office Add-ins for Word, Excel, PowerPoint and Outlook, as well as extensions for SharePoint and Teams. We'll also see how we can use the Microsoft Graph and AI to take the intelligence behind the entire Microsoft 365 platform and deliver it where business users spend their working day. Wouldn't you like to be the hero that lets your users work faster, suffer less information overload, and see their families again?