Human Language is the New UI. How this is possible.

Do you recall the first time you posed a question to ChatGPT and received an answer in clear, understandable English? For many of us it was an eye opener because this language ability was far above anything that had been possible before. This breakthrough in language understanding propelled ChatGPT to an unprecedented 100 million users in just two months, marking the fastest adoption of an application in history. Only a couple of years later, this capability — the Large Language Model (LLM) — is widely available in many forms and is powering more tools and apps every day. This is leading to a fundamental shift in human-computer interaction and is why Microsoft CEO Satya Nadella says “Human language is the new UI layer.”

But how is it this possible? This talk takes a pragmatic look at how LLMs process human language starting with how they break it down and represent it. Our focus will be developing an intuitive understanding that will include a gentle introduction to tokens and embedding models. We will look at illustrative examples in multiple languages and audience participation here will be welcome. There will be no math. 🤓

We’ll close by briefly connecting the dots to other popular AI and AI-adjacent technologies like semantic search, vector databases, retrieval augmented generation (RAG), coding assistants, and even the humble chatbot. Don’t worry if any of these terms are unfamiliar. We won’t go deep, but rather we’ll zoom in on how the language understanding piece is relevant. This can help you appreciate when these other technologies might be useful.

The target audience for this talk is business leaders, developers, product managers, and anyone curious about how AI really works behind the scenes. If you’ve used ChatGPT (or similar), you’re ready for this talk; no other technical background required.

You’ll walk away with an intuitive understanding of how LLMs process language that you can apply when evaluating AI tools, building AI features, or just demystifying the tech for your team.

Let's Build a Goal-Oriented AI Agent Using Semantic Kernel

Imagine an AI not limited to answering individual questions or chatting, but actively working towards a goal you've assigned to it.

In this session, we'll explore the building of an AI Agent – an autonomous actor that can execute tasks and achieve objectives on your behalf.

Along the way we will demystify:

1. 🧠 LLMs - What is a Large Language Model (LLM)
2. 📚 Tokens - What is a token and what are its roles
3. 💡 Embeddings - What are embedding models and vectors and what can they do for us
4. 🎯 Prompts - Beyond the basics
5. ⚙️ Tools - How can these be created and accessed using Semantic Kernel
6. 🤖 Agents - Let's put all these concepts to work!

The end result will be the core (or perhaps 'kernel' 😉) of an AI Agent - your virtual coworker willing to handle tasks on your behalf without. It will be built in C# using the open source, cross-platform Semantic Kernel library.

This talk assumes user-level familiarity with LLMs like ChatGPT or Microsoft Copilot and basic prompting. Anything else will be explained.

This talk does NOT use the Semantic Kernel Agent Framework which is still pre-release.

Designed as a 60- to 90-minute presentation. Target audience is developers and other technical roles. While C# code will be used to illustrate some of the concepts, it is not necessary to be a C# developer to understand this talk.

Empowering AI Agents with Tools using MCP

AI chatbots respond to prompts, but AI agents are much more interesting because they can take meaningful action on your behalf when you empower them with tools. In this talk we explain the concept of a tool and show how to allow an AI agent tool access through the emerging Model Context Protocol (MCP) standard. We will also survey the growing marketplace of MCP servers and how you can integrate them. Finally, we will consider how you can expose your own functionality through the MCP server standard.

By the end of this talk you should understand what tools are, why AI agents benefit from them, what role MCP plays, what problems it solves, when to use it, and how to create your own MCP-compatible tool.