GenAI Unpacked: Beyond Basicende

This demo-driven session delves into advanced aspects of Generative AI beyond basic prompt engineering. You’ll learn how GenAI works and how to implement use cases like classification, recommendation, and semantic search.

The session begins with core concepts such as tokens, exploring how transformers learn associations, followed by text generation via completions for a deeper understanding of model functionality. Key topics include embedding vectors, cosine similarity, and vector databases to explain semantic modeling.

You’ll also discover techniques like Retrieval Augmented Generation (RAG) to expand and manipulate model knowledge.

Finally, we’ll explore various model types and tools, including OpenAI Playground, Azure AI Studio, and Microsoft’s Semantic Kernel.

This technical session is ideal for those looking to understand and build intelligent applications powered by large language models.

Modern Serverless Applications with Azure Durable Functions, ACI and Dockeren

In the modern world of digital transformation and the increasing popularity of cloud technology, almost every single application becomes part of a more complex distributed system. With the help of Serverless services, some parts of applications can be implemented more easily and efficiently.
In this session, you will learn how to implement and operate long-running applications using Azure Functions. You will learn about developing and monitoring long-running applications useful for integration scenarios.

This deep-dive session demonstrates how durable functions can be used to implement various complex scenarios. You will learn about orchestrations, actor models and durable entities. Moreover, you will also learn how to deploy and monitor long-running processes composed in Docker containers and operated in the Azure Container registry.

This session focuses on software architects and developers with the goal of designing and implementing modern applications with cloud technologies. Demos in this session include lessons learned and best practices from real customer projects.

Coding Workflows beyond limits of Hyperautomation – Best of Azure Durable Functions and Actor Modelende

In the modern world of digital transformation and the increasing popularity of cloud technology, almost every single application becomes part of a more complex distributed system. This fact increasingly demands the use of long-running workflows, state management and integration of systems. In this session you will learn how to use Azure Durable Functions to implement workflows with Actor Programming Model.
This session is aimed at software architects and developers who are designing and developing workflows and integration solutions for Microsoft Azure.
The demos in this session include lessons learned and best practices from real enterprise customer projects.

Best practices: Building Enterprise Applications that leverage GenAIende

The new era of software development brings intelligent applications powered by Large Language Models (LLMs) and Generative AI (GenAI), revolutionizing business processes. While these tools offer immense potential, building AI-powered applications involves challenges beyond prompt optimization or low-code techniques.

In this demo-driven session, you’ll learn to build enterprise applications seamlessly integrating GenAI. We’ll showcase OpenAI, Azure OpenAI, and explore advanced concepts using Microsoft’s Semantic Kernel, an open-source toolkit for creating enterprise-grade AI agents.

Targeted at developers, architects, and technical decision-makers, this session provides valuable insights into GenAI and intelligent application development—even for those without a C# background.

How to build modern backendsen

In the time of microservices, cloud and machine learning, complexity of backend applications increases. It is getting more and more difficult to design robust, reliable, scalable and easy to operate system.
This session is about building advanced and modern backends with help of Actor Programming Model theory and Azure Service Bus. It demonstrates how a lightweight Actor Model framework can be built and used on top of Azure service Bus messaging platform. Attendees will learn first about theory of Actor Programming Model and many powerful messaging patterns. With lot of demos, it will be demonstrated how to implement and use a lightweight Actor Programming Model framework based on Azure Service Bus to build robust, scalable and partitioned services.

Workshop: Deep dive into Azure OpenAI and Semantic Kernel ende

Artificial Intelligence has a tremendous impact on technology and society. Microsoft Azure and .NET have already established themselves as leading cloud, AI, and IoT platforms in this field. With the help of the "Semantic Kernel," professional developers can now harness the incredible capabilities of large language models. This demo-based session will explain how .NET and other developers can use Microsoft Semantic Kernel to leverage Azure OpenAI models for implementing novel intelligent applications. Utilizing this remarkable technology, we will illustrate how custom copilots and task orchestration can be implemented.
You will learn how to create plugins that extend the cognitive capabilities of a Generative AI by incorporating custom code.

This session is designed for software architects, developers, and any other software engineers interested in implementing applications with Generative AI.

Azure best practices - Architecting complex solutions with heavy loadsende

ML and AI are undoubtedly becoming increasingly important. However, integrating ML/AI into software is not an easy task. Most projects in this context are prototyped in Python. However, a real solution has numerous requirements that go beyond the scope of an experimental application. ML.NET is a viable approach that also has its limits.
In this talk, you will learn how to implement real projects using Microsoft Machine Learning .NET frameworks. And not only that. We will show how a proper architecture of such a solution is created step by step. You will first learn how ML.NET works. Next, we show how "heavy workloads" such as ML training process can be implemented why technologies such as Docker can sometimes be surprisingly unhelpful here and how such "limits" can be circumvented using Azure Batch Service. That's not all. The prediction part of such an application can also make your web-hosted web application go haywire.
This is an advanced talk with lots of demos and insights into the world of ML.NET and Microsoft Azure. Even if your topic is not necessarily ML, this talk will teach you how to design and run heavy-load solutions in Azure.

Einführung in Azure Open-AI und Generative KIde

Azure OpenAI Service bietet Unternehmen und Entwicklern leistungsstarke vortränierte KI-Modelle, die in Produktionsmaßstäben betrieben werden. Diese Session ist eine Einführung in die Welt von Azure OpenAI. Die Teilnehmer lernen über die verschiedenen beindrückende Technologien (Machine Leraning, Deep Learning und Natural Language Processing) und Ansätze, die verwendet werden, um hochmoderne KI-Systeme zu entwickeln.
Insgesamt bietet diese Session eine umfassende Einführung in Welt von OpenAI und ist für Architekten, Entwickler, Forscher und alle KI-Neugirige konzipiert.

Azure Open AI for professional Enterprise Developersen

Artificial Intelligence is rapidly transforming the tech industry and soon society too. Fortunately, Azure and .NET have emerged as leading Cloud, AI and IoT development platforms. As a professional enterprise developer, you can leverage the amazing Azure's Open AI capabilities to build intelligent applications that can help solve new kinds of problems.

In this demo-powered session, we'll demonstrate how .NET developers can use Azure Open AI to build applications that cannot be implemented by using common development approaches. We'll start with an overview of Azure's Open AI capabilities and how they can be used with any programming language, not only. NET. Then, we'll dive into many demos of how to build intelligent applications using Azure cognitive services, such as OpenAI.

This session is designed for Software Architects, Developers and all other software engineers, who build and want to build applications with Large Learning Models.

Building intelligent applications with Large Language Models and Semantic Kernelende

Artificial Intelligence is rapidly transforming the tech industry and soon society too. Azure and .NET have emerged as leading Cloud, AI and IoT development platforms. As a professional enterprise developer, you can leverage the amazing Azure's Open AI capabilities to build intelligent applications that can help solve new kinds of problems.
In this demo-powered session, we'll demonstrate how .NET and any other developers can use Microsoft Semantic-Kernel to leverage Azure OpenAI and build applications that cannot be implemented by using common development approaches. We'll start with an overview of Azure's Open AI capabilities and how they can be used with any programming language, not only. NET. Then, we'll deep dive into Semantic Kernel and demonstrate how to build intelligent applications.

This session is created for Software Architects, Developers and all other software engineers who build and want to build applications with Large Language Models.

Custom Copilots and Task orchestration with Microsoft Semantic Kernel and Gen AIende

Artificial Intelligence has a tremendous impact on technology and society. Microsoft Azure and .NET have already established themselves as leading cloud, AI, and IoT platforms in this field. With the help of the "Semantic Kernel," professional developers can now harness the incredible capabilities of large language models. This demo-based session will explain how .NET and other developers can use Microsoft Semantic Kernel to leverage Azure OpenAI models for implementing novel intelligent applications. We will demonstrate how custom copilots and task orchestration can be implemented by using this amazing technology.

This session is designed for software architects, developers, and any other software engineers interested in implementing applications with Generative AI.

Building Smart Agents and Custom Copilots with GenAI and Semantic Kernelen

GenAI is undoubtedly becoming increasingly important. However, building intelligent applications and integrating AI into software is not an easy task. Real-life solutions have numerous requirements that go beyond the scope of an experimental application built for Data Science purposes or simply playing around with prompts.

In this demo-driven session, you will learn how to build AI agents integrated into applications of any type. You will see many demos in .NET/C# that demonstrate building GenAI applications capable of running almost anywhere and on any OS. Even if C# is not your primary language, feel invited to learn about concepts like Agents and Plugins, which will help you build your custom copilots.

We will start with core topics such as tokens, completions, cosine similarity, embeddings, and different model types and then combine them to build custom copilots using Azure OpenAI, Azure Open AI and Semantic Kernel. Once you understand how everything works, you will be able to teach existing models to perform tasks they usually cannot do.

This session is a technical presentation designed for developers, architects, and technical decision-makers.

Master Class: Design and implementation of Enterprise Applications that leverage GenAIende

As a professional enterprise architect or developer, you are required to build new applications that leverage large language models and Generative AI.
In this one-day master class, we will demystify how Generative AI works. We will start with the basics and then dive deep into important topics such as token generation, vector similarity, embeddings, different model types, and more. Next, we will explore various levels of application for specific use cases. We will begin with simple application types that use prompt engineering and demonstrate how these can be enhanced with techniques like Retrieval-Augmented Generation (RAG).

Finally, we will showcase how plugins can help integrate Generative AI into any software system and explain techniques to reduce or even prevent hallucinations.

Through numerous demos, we will illustrate how .NET developers and developers from other backgrounds can build AI agents that execute intelligent code in any application.

You will also gain insights into Microsoft Azure AI Foundry and the Open Source Semantic Kernel, both used internally at Microsoft. We will demonstrate how these frameworks can be employed to build applications and powerful backends that integrate AI into any software system, whether running in Azure or on-premises.

Most Demos will be in C#/.NET and Visual Studio. However, you are required to have a good technical knowledge of any programming language and any IDE.

Science Fiction or reality: The New Software Era of Custom Co-Pilots. en

Ready for the new wave of innovations? Dive into the fascinating new software world powered by Azure OpenAI and Large Language Models.
In this live-coding futuristic session, you will learn from Damir, a Microsoft MVP and Microsoft Regional Director, how to build software created in a siýmbiose between natural and programming languages.

Whether you’re an architect, developer, or just curious about AI, feel invited to see how to code custom copilots that orchestrate complex processes and possibly replace traditional user interfaces.

Technologies in focus: GenAI, Azure Open AI, .NET/C#, Semantic Kernel.