Workshop: Learn how to interact with OpenAI models

**Bring your own laptop!**

This lab offers a practical and immersive learning experience in Prompt Engineering. Discover the power of techniques like zero-shot learning and chain of thought. Explore the creative potential of DALL-E for image generation. Learn how to effectively use function calling to unlock the full capabilities of prompt engineering.

Building Intelligent Apps with Semantic Kernel and .NET

Semantic Kernel is a powerful tool that bridges the gap between conventional programming languages and cutting-0edge Large language Models (LLMs) empowering developers to explore AI integration within the .NET ecosystem, making it a valuable tool for building intelligent applications. This session will guide developers through the basics of integrating AI capabilities into their apps using Semantic Kernel. It’s specifically targeted at those who want to integrate AI effectively and understand the underlying concepts behind AI agents.

Building AI Agents with Semantic Kernel and C#

Unlock the Power of AI with .NET and Semantic Kernel!
In this session we dive into the world of AI integration within the .NET ecosystem using Semantic Kernel. This powerful tool bridges the gap between traditional programming and cutting-edge Large Language Models (LLMs), making it an essential asset for developers aiming to build intelligent applications.

What You'll Learn:

Semantic Kernel Capabilities: Explore the features and benefits of Semantic Kernel, and how it empowers you to leverage LLMs in your .NET projects.
Practical Integration: Learn step-by-step how to effectively integrate AI into your applications, enhancing their functionality and user experience.
Concepts Behind AI Agents: Gain insights into the underlying principles of AI agents and how they operate.

This session is perfect for developers eager to harness the potential of AI and elevate their .NET applications to the next level.

Accelerating Microservices Development with .NET Aspire and Dapr

In today’s rapidly evolving digital landscape, agility and speed are essential for successful software development. This holds especially true when building microservices, where efficiency across the entire development lifecycle is crucial.

In this session, we look at .NET Aspire, an advanced framework designed to streamline microservices development. Through best practices, resilience, and scalability, it empowers developers to create efficient and cloud-native microservices.

We then look at Dapr and how the Dapr building blocks can be for common microservices patterns, such as state management, pub/sub, service invocation, and more.

While Dapr abstracts underlying cloud platforms, .NET Aspire enhances development by providing opinionated configuration without hiding the underlying technologies. Together, they empower developers to build resilient, scalable, and efficient microservices while maintaining compatibility with existing tools and ecosystems.

The real magic happens when we combine these technologies. Witness the synergy between .NET Aspire and Dapr through practical demos.

Join me on this exciting journey to unlock efficiency, speed, and innovation in microservices development!

Using Azure AI Search to always generate the most relevant results

In this session, we will take a deep dive into how the addition of vector search capabilities to former Azure Cognitve Search enables swift searches on extensive datasets in an enterprise-grade environment ensuring precision and flexibility. Additionally, the new Semantic Ranker leverages advanced language models to improve the relevance and quality of search results. We will see how vector search greatly improves the results but a hybrid retrieval and a reranking step delivers significantly better results - that will only make your app users get the most relevant information at their fingertips, always.

GraphQL - The API for modern apps and how to build GraphQL APIs in .NET

GraphQL is a new API standard that provides a more efficient, powerful and flexible alternative to REST. GraphQL enables declarative data fetching where a client can specify exactly what data it needs from an API. Instead of multiple endpoints that return fixed data structures, a GraphQL server only exposes a single endpoint and responds with precisely the data a client asked for. The single endpoint can forward the queries to downstream APIs, merge the data and return it to the client in a single response. This makes GraphQL a great solution in microservices architecture in which the number of endpoints for clients to render the page can become a rigid approach.

Build your own ChatGPT using Azure Open AI and .Net and interact with your own data

Generative AI has taken over the way we interact with data and also how we let our customers interact with data.
In this session, we will learn how we can create a Azure Open AI ChatBot using the Open AI Large Language Models that power ChatGPT and then add our own data to the mix which will then help us get the most relevant information to our customers. We will also see how we can hook up this chatbot to a .Net Application to bring this curated experience in our custom applications.

Mastering GitHub Copilot: Maximizing Productivity While Navigating Pitfalls

In the rapidly evolving landscape of AI-powered development tools, GitHub Copilot stands out as a revolutionary assistant for developers. This session will dive into the myriad ways GitHub Copilot can enhance your coding experience, from generating code snippets and tests to creating simple applications with ease. However, it's crucial to recognize that, like any AI tool, Copilot has its limitations and can sometimes provide incorrect or repetitive suggestions.

In this session, we explore the exciting capabilities of GitHub Copilot while also shedding light on its potential pitfalls. We'll discuss how to leverage Copilot effectively, using your coding expertise to identify and mitigate its shortcomings. Through real-world examples and hands-on demonstrations, you'll learn how to integrate GitHub Copilot into your development workflow to significantly boost productivity without compromising code quality.

Key Takeaways:

- Discover the diverse functionalities of GitHub Copilot and how it can streamline your development process.
- Understand the common pitfalls of using AI tools like Copilot how to mitigate them.
- Learn strategies for effectively incorporating Copilot into your coding routine, ensuring it complements rather than hinders your work.
- Participate in live demonstrations and practical exercises to see Copilot in action and practice mitigating its limitations.

This session is designed for developers eager to harness the power of AI tools while maintaining a critical eye on their outputs.

Build a Kubernetes style modern app without complexities of Kubernetes using Azure Container Apps

Kubernetes can be complex. To get started with Kubernetes, developers must first go through an initial, steep learning curve before taking full advantage of all the features offered by Kubernetes. Although Microsoft offers Kubernetes as a fully managed service, you are still responsible for managing, configuring, and hardening the underlying Kubernetes cluster. Azure Container Apps abstracts this a step further and lets you focus on building applications using many of the benefits of Kubernetes without the need for cluster management – using the power of serverless.

In this session we will cover:
-What is Azure Container Apps
-How does it compare to Kubernetes
-Deploy a microservices application to Azure Container Apps
-Demos

Simplify building microservices with DAPR

Moving away from heavily coded monolithic applications to finer, self-contained microservices offers a vast array of benefits but at the same time they also introduce increased complexities in team and product management. To get started, the team must make decisions on picking the right dependencies in addition to the right solution.
It would be much easier to get started if there was a runtime that offered building blocks to implement some common patterns that you need to adopt in your application. This would allow teams to focus on building the right solution without need to choose the tools upfront. Dapr is that runtime.
Dapr or Distributed Application Runtime, is a portable, event-driven runtime that makes it easy for any developer to build resilient, stateless and stateful applications that run on the cloud and edge and embraces the diversity of languages and developer frameworks.

Making sense of all container options in Azure

With the hype around containerization, nearly every organization is trying to start their modernization journey with containers. If you are doing this on a cloud hyperscaler like Azure, your team already has many options to build and deploy cloud native and containerized applications. Should you always use Kubernetes? Or maybe a good old App Service is more suitable to run your website in a container? In this session, we cover which scenarios and use cases are best suited for the different container options available in Azure today.

GraphQL - The API for modern apps and how to build GraphQL APIs in .NET

GraphQL is a new API standard that provides a more efficient, powerful and flexible alternative to REST. GraphQL enables declarative data fetching where a client can specify exactly what data it needs from an API. Instead of multiple endpoints that return fixed data structures, a GraphQL server only exposes a single endpoint and responds with precisely the data a client asked for. The single endpoint can forward the queries to downstream APIs, merge the data and return it to the client in a single response. This makes GraphQL a great solution in microservices architecture in which the number of endpoints for clients to render the page can become a rigid approach.

In this session we will cover:
- What is GraphQL?
- What problem does it solve?
- GraphQL Schema, Operations, Types and Resolvers
- Build your own GraphQL Server with HotChocolate and .NET Core
- Schema stitching by joining multiple APIs to a single endpoint
-Demos

Designing for Sustainability on Azure

When designing for the cloud, the impact and benefits of a cloud hosted application have always been traditionally measured with financial and efficiency metrics. The Well Architected Framework for Azure has been no different.
Right now, organizations around the world are putting a renewed focus on sustainability and are trying to understand how cloud can help organizations reduce their carbon emissions and lessen their environmental footprint to help them achieve their sustainability and environmental goals.
In this session, we will look at how we can design solutions that maximize utilization but reduce waste while still using the Well-Architected Framework as a technical foundation.

Build your own ChatGPT using Azure Open AI and interact with it using .NET

Generative AI has taken over the way we interact with data and also how we let our customers interact with data.
In this session, we will learn how we can create a Azure Open AI ChatBot using the Open AI Large Language Models that power ChatGPT and then add our own data to the mix which will then help us get the most relevant information to our customers. We will also see how we can inject a custom tool to further enhance the experience. And all of this from a .NET application to bring this curated experience into our custom applications.

The impact of Gen AI in the life of a developer - Following The journey of a feature

Generative AI is revolutionizing the software development landscape, bringing about significant improvements in various aspects of the development process.
In this session, we will look at how Gen AI is impacting the daily work of a developer. We will follow the journey of a feature across Software Development Lifecycle and see how GenAI can impact the way we work. We will look beyond code generation and look at how GenAI can streamline SDLC across stages like Planning and Analysis, Testing, Deployment and Maintenance.

Generative AI promises to rewrite the way software is built and maintained. For developers, as we embrace this transformative technology, we can expect increased productivity, faster development cycles, and elevated software quality.

Choosing the Right Generative AI Model for Your Needs

Navigate the World of Generative AI with Confidence!

In today's rapidly evolving AI landscape, there are numerous Generative AI models to choose from: Large Language Models (LLMs), Small Language Models (SLMs), proprietary models, open models, cloud-based models, on-device models, text models, code models, image models, and multimodal models. This session is designed to provide you with the guidance you need to select the right model for your specific needs.

What You'll Learn:

Model Selection: Understand the different types of Generative AI models and their unique capabilities.
Evaluation Tools: Discover tools and methodologies to evaluate and compare models based on your specific tasks.
Practical Insights: Gain practical insights into how to effectively integrate these models into your projects.

This session is perfect for developers, data scientists, and AI enthusiasts who want to make informed decisions about which Generative AI models to use and how to leverage them for maximum impact.

A Practitioners Guide to Reducing the Environmental Impact of Generative AI

As generative AI continues to revolutionize various industries, its environmental impact becomes a critical concern. This session delves into sustainable practices for developing and deploying generative AI, guided by Microsoft's Well-Architected Framework (WAF) for sustainable workloads.
We will explore key decision points, including selecting the right models, optimizing fine-tuning processes, leveraging Retrieval Augmented Generation (RAG), and mastering prompt engineering, all through an environmental sustainability lens. By adopting these best practices, practitioners can effectively implement generative AI solutions while minimizing their carbon footprint, energy consumption, and electronic waste.
Join this session to learn how to balance innovation with responsibility and contribute to a greener future.

Empowering AI at the Edge

In an era where real-time data processing and low-latency responses are crucial, running AI models on the edge has emerged as a game-changer. This session delves into the transformative potential of deploying large language models (LLMs) and other AI technologies directly on edge devices. We will explore the technical intricacies and architectural considerations of edge AI with Azure.

Key Takeaways:
- Gain insights into the fundamentals of running AI models on edge devices using Azure services, including hardware requirements, software frameworks, and deployment strategies.
- Learn about the best practices for designing and implementing edge AI solutions with Azure, ensuring optimal performance and scalability.
- Experience live demonstrations of Azure edge AI applications, highlighting the ease of integration and the tangible benefits for end-users.

This session is tailored for developers and architects eager to harness the power of AI at the edge with Azure, offering practical knowledge and inspiration to innovate beyond the cloud.

Demystifying Agent Types within the Semantic Kernel Framework

Artificial intelligence is transforming the way developers create innovative solutions and if you looking to build agentic solutions, then you surely have come across Semantic Kernel and the 3 agent types is supports. This session is designed to empower developers by demystifying three key AI agent types within the Semantic Kernel framework: Chat Completion Agent, OpenAI Assistant Agent, and Azure AI Agent.

Understanding these agent types is crucial for developers aiming to build the right solutions for their projects. By gaining insights into the unique capabilities and applications of each agent, developers can enhance productivity, drive innovation, and optimize their solutions. This knowledge will enable them to automate tasks, streamline workflows, and create cutting-edge applications that interact intelligently with users and data sources. Additionally, mastering these AI agents will deepen their expertise and keep them ahead in the competitive tech landscape.

Join us in this session to explore how these AI agents within the Semantic Kernel framework can transform your development process. Whether you are building conversational AI, automating tasks, or integrating AI into your applications, this session will provide you with the knowledge and tools to succeed.