talk-data.com

Hands-On : MCP (Model Context Protocol) Bootcamp Date: 27th September 2025, 9 AM to 12.30 PM Eastern Time Level: Beginners/Intermediate Registration Link: https://www.eventbrite.com/e/hands-on-mcp-model-context-protocol-bootcamp-tickets-1583073859529?aff=oddtdtcreator Who Should Attend? This hands-on workshop is for developers, senior software engineers, IT pros, architects, IT managers, citizen developers, product managers, IT leaders, enterprise architects, chief analytics officers, CIOs, CTOs, and other decision-makers who want to learn how to seamlessly integrate AI applications and agents into Azure AI Foundry and Microsoft Copilot Studio using the Model Context Protocol (MCP). Experience with C#, Python, or JavaScript is helpful but not required—no prior AI knowledge needed. And while this isn’t a data & analytics-focused session, data scientists, data stewards, and tech-savvy data protection officers will also find it super valuable. Description: MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C gives you a universal way to connect devices to different peripherals and accessories, MCP gives AI models a standardized way to connect to data sources and tools. Why MCP?MCP makes it easier to build agents and complex workflows on top of LLMs. Since LLMs often need to integrate with data and tools, MCP provides:

• A growing list of pre-built integrations your LLM can plug into directly
• The flexibility to switch between LLM providers and vendors
• Best practices for keeping your data secure within your infrastructure

In this half-day, hands-on virtual workshop, Microsoft AI and Business Applications MVP and Microsoft Certified Trainer Prashant G Bhoyar will show you how to use MCP with Azure AI Foundry and Copilot Studio to build powerful AI Agents. Here’s what we’ll cover in detail:

• What is the Model Context Protocol (MCP)?
• How to build an MCP server?
• How to integrate AI applications and agents into Azure AI Foundry and Microsoft Copilot Studio using MCP?
• How does MCP connect directly to existing knowledge servers and APIs, so actions and knowledge can be automatically added and updated within your agents?
• How MCP integration simplifies agent building, reduces maintenance, and leverages enterprise-grade security and governance (like Virtual Network integration, Data Loss Prevention policies, and multiple authentication methods)?
• Best practices for real-world use cases

By the end of this bootcamp, you'll be ready to use MCP to create enterprise-grade agents. The labs will feature a mix of Python, C#, and low-code/no-code UI tools—so even if you don't want to write code, you're covered. Workshop Resources: You’ll get access to Microsoft Copilot, Azure, and Azure OpenAI services (a $500 value) for the hands-on labs. If you already have your own Microsoft Copilot or Azure subscription, you can use that instead. Attendee Workstation Requirements Bring your own computer (Windows or Mac) with:

• Camera, speakers, microphone, and a reliable internet connection (tablets won’t work for this workshop)
• A modern browser: Microsoft Edge, Google Chrome, Firefox, or Safari
• Access to www.azure.com and https://copilot.microsoft.com
• Nice to have: the ability to run C# 10 or Python code using Visual Studio 2022, VS Code 1.66+, Visual Studio for Mac, Rider, or a similar IDE.

2 Days Hands-On Online Workshop: Azure AI Foundry and Copilot Studio Bootcamp Date: 29-30 May 2025, 9 AM to 5 PM Central Time Level: Beginners/Intermediate Registration Link: https://www.eventbrite.com/e/hands-on-azure-ai-foundry-and-copilot-studio-bootcamp-tickets-1267311596099?aff=oddtdtcreator Who Should Attend? This hands-on workshop is open to developers, senior software engineers, IT pros, architects, IT managers, citizen developers, technology product managers, IT leaders, enterprise architects, chief analytics officers, chief information officers, chief technology officers, and decision-makers interested in learning how AI Agents and Generative AI can help infuse artificial intelligence into next-generation apps and agents. Experience with C#, Python, or JavaScript is helpful but not required. You don't need prior knowledge of AI either. Although this isn't a data & analytics-focused workshop, data scientists, data stewards, and technically-minded data protection officers will also find it very valuable Description: With ChatGPT and other large language models, generative AI has captured the attention of global consumers, enterprises, and C-suite executives. AI has a significant role in the enterprise space and is evolving rapidly. Without understanding the concepts behind these advanced technologies, developers and administrators might find it challenging to assess the true impact of emerging tools and solutions. An AI agent is a powerful companion capable of managing a variety of interactions and tasks—from handling complex conversations to autonomously deciding the best actions based on instructions and context. Agents coordinate language models along with instructions, context, knowledge sources, topics, actions, inputs, and triggers to achieve your desired outcomes. Copilot Studio is a graphical, low-code tool designed for creating agents, including building automations with Power Automate and extending Microsoft 365 Copilot with your own enterprise data and scenarios. One standout feature of Copilot Studio is its ability to connect to other data sources through either prebuilt or custom plugins, as well as integration with Azure AI Foundry. This flexibility allows users to easily build sophisticated logic, ensuring that agent experiences are both powerful and intuitive. Azure AI Foundry is a unified AI platform that includes the Azure AI Foundry portal (formerly Azure AI Studio) and the Azure AI Foundry SDK—a unified SDK featuring pre-built app templates. This SDK gives developers easy access to popular models through a single interface, simplifies the integration of Azure AI into applications, and helps evaluate, debug, and improve application quality and safety throughout development, testing, and production. In this two-day virtual hands-on workshop, Microsoft AI and Business Applications MVP and Microsoft Certified Trainer, Prashant G Bhoyar, will cover these topics in detail:

1. What are multimodal GenAI applications?
2. What are AI agents?
3. What are autonomous agents?
4. What are custom Copilots?
5. Introduction to Copilot Studio: Learn to create agents, build automations with Power Automate, and extend Microsoft 365 Copilot using enterprise data. Discover how to use prebuilt and custom plugins alongside Azure AI Foundry for powerful, intuitive agent experiences.
6. Azure AI Foundry: An in-depth overview of Azure AI Foundry.
7. Azure OpenAI Services: Explore these services, their architecture, and their role in the broader AI ecosystem.
8. Using models from DeepSeek, Llama, Hugging Face, and other open-source models via Azure AI Foundry.
9. Prompt engineering: An in-depth look at creating effective prompts, understanding their importance, and the factors influencing their performance.
10. Use cases and common architectures: Hands-on labs demonstrating real-world implementations.
11. How to evaluate use cases and determine ROI.
12. Azure OpenAI Service embedding models.
13. Customizing Azure OpenAI Services: Configuration to deployment tailored to specific business needs.
14. Deep dive into Azure OpenAI Services: A detailed look at popular models like o1, GPT, Ada, and DALL-E, discussing their unique features and ideal use cases.
15. Using Azure OpenAI Service to access company data.
16. Azure AI Services overview: Language, Speech, and Vision services and their real-world applications.
17. Conversational AI: Design, train, and refine AI capable of human-like interactions.
18. Azure AI Search: Creating advanced search experiences.
19. Document Intelligence Service: Extracting key-value pairs and table data from documents using machine learning.
20. Azure AI Agent Service: Feature-rich managed capabilities combining models, data, tools, and services for automating complex business processes.
21. Semantic Kernel: An open-source SDK for combining AI services (OpenAI, Azure OpenAI, Hugging Face) with programming languages like C# and Python to create advanced AI applications.
22. Model Context Protocol ( MCP )
23. Responsible AI: Ethics and responsible practices in AI use.
24. Enterprise-level applications, Custom Copilots, and AI agents: Learn to develop scalable, multimodal applications using Copilot Studio and Azure AI Foundry, emphasizing industry requirements and best practices.

By the end of the workshop, you'll have practical experience building next-generation multimodal applications, Custom Copilots, and AI Agents using Copilot Studio and Azure AI Foundry. Workshop Resources: Access to Copilot Studio, Azure, and Azure OpenAI services (valued at USD 500) will be provided for hands-on labs, allowing you to build enterprise-grade multimodal applications and agents. However, you're encouraged to use your own Copilot Studio and Azure subscriptions if available. Attendee Workstation Requirements: You must bring your own computer (Windows or Mac) with:

• Camera, speakers, microphone, and a reliable internet connection. Tablets will not work for this workshop.
• A modern browser (Microsoft Edge, Google Chrome, Firefox, or Safari).
• Access to www.azure.com and https://copilotstudio.microsoft.com.
• Nice to have is the ability to run C# 10 or Python code, using Visual Studio 2022, VSCode 1.66+, Visual Studio for Mac, Rider, or similar IDE.

Global AI Bootcamp taking place in London. If you are an AI enthusiast and love learning more about Azure AI, then this event is perfect for you.

09:30 - 09:45 Welcoming (15 mins)

09:45 - 10:20 Speaker 1 - Opening Keynote - Amy Boyd - Senior Cloud Developer Advocate in AI/ML at Microsoft

Session: To be Confirmed

10:20 - 10:45 Speaker 2 - Nathaniel Okenwa (He/Him) Developer Evangelist @twilio / Wannabe Dev-Rel Superstar / Loves: Coding

Session: Preventing Skynet: Managing Trust with AI Agents

In this talk, we’ll explore the practical dangers of AI agent infrastructure, discuss strategies to safeguard your systems, and provide a comprehensive safety checklist to help you build responsibly. Together, we can prevent the singularity. Remember: The future is not set. There is no fate but what we make for ourselves.

10:45 - 11:10 Speaker 3 - Rahul Basu - Senior Software Engineer at Warner Bros. Discovery

Session: AI, Hollywood, and the Metaverse – A Synergistic Future

Artificial intelligence is set to become the backbone of the metaverse, merging physical and digital realities into immersive experiences. This session explores how AI is transforming storytelling, character creation, and interactive content, revolutionizing the entertainment industry. From generative AI-powered narratives to real-time digital actors, we’ll examine how Hollywood and gaming companies are leveraging AI to redefine engagement. Drawing from his experience architecting Max, Warner Bros. Discovery’s global streaming platform, Rahul Basu will share insights into how AI is being used by top media companies to power next-gen content creation. Attendees will learn about AI-driven MLOps frameworks, synthetic media production, and the tools shaping the future of the entertainment industry. Whether you’re a developer, AI enthusiast, creative, or media executive, this session will provide practical knowledge and real-world use cases on how AI is reshaping the future of entertainment.

11:10 - 11:30 Break (15 mins)

11:30 - 12:15 Speaker 4 - Guy Gregory - Partner Solution Architect@Microsoft specialising in Azure AI.

Session: Introducing Azure AI Agent Service

In this session, we’ll introduce the Azure AI Agent Service, a set of feature-rich, managed capabilities that brings together all the models, data, tools, and services that partners and customers need to automate business processes of any complexity. Here’s what we’ll cover:

• Introducing the Azure AI Agent Service
• How to use the Azure AI Agent Service via SDK and Azure AI Foundry
• How does the Azure AI Agent Service compare to Chat Completions and Assistants API?
• ‘What’s in the box?’ Models, Tools, Actions, and Security
• Creating your Agent Project, and deploying your model
• Creating a basic agent
• Creating an agent with tools
• Advanced agents / Multi-agent examples
• Further reading and training

12:15 - 13:00 Speaker 5 - Manuel Sanchez Rodriguez Director - Azure App Modernisation at NTT DATA \| Microsoft MVP Azure & AI Platform and Sergio Sisternes Senior Director - Head of Cloud Native Solutions at NTT DATA

Session: The Age of Agents: Modernising Your Applications

Join us for an exciting session, "The Age of Agents: Modernising Your Applications" with Azure and Azure OpenAI, where you'll discover how to transform and modernise your applications using the powerful capabilities of Azure and Azure OpenAI. Learn how intelligent agents can enhance performance and user experience, explore practical demonstrations of seamless integration, and get a comprehensive guide on overcoming common challenges. Whether you're a developer, IT professional, or tech enthusiast, this session will equip you with the knowledge and tools to stay ahead in the rapidly evolving tech landscape. Don't miss this opportunity to unlock your applications' full potential with Azure and Azure OpenAI.

13:00 - 14:00 Lunch Break (

14:00 - 14:45 Speaker 6 - Clifford Agius - Freelance Developer that just so happens to fly an Airbus A320 around the Europe.

Session: Could a Co-Pilot be an Aircraft Co-Pilot

Welcome aboard, fellow travelers! In this talk, we’re strapping on our metaphorical aviator goggles and diving into the cockpit to explore the fascinating world of AI Co-Pilots and could they and more importantly should they be used in a real world flight deck? Buckle up, because this flight is about to get bumpy—in a purely intellectual turbulence kind of way. Using aircraft incidents and accidents we will see if an AI Co-Pilot would have saved the day... If you have a fear of flying maybe skip this one but I will say before you run out that none of the accidents are fatal so nothing to be scared of.... You don't need to be an AI specialist or even know anything about it, as we are just exploring the decisions pilots have to make in very limited timescales with limited information and throwing in some human factors to spice it up a bit. These are all good skills you can use in any decision making at work. The aim of this session is to hopefully show you that AI can help but should we use it? You will walk away knowing a bit about AI and have some fun geeking out on aviation.

14:45 - 15:10 Speaker 7 - Ayca Bas - Senior Cloud Developer Advocate@Microsoft

Session: RAG and Knowledge Retrieval Fundamentals

In this session, we are going to talk about what is Retrieval Augmented Generation and why It’s a Game Changer. We'll also learn the fundamentals of search indexing and talk about Vector Search 101: Revolutionizing Retrieval with AI.

15:10 - 15:55 Speaker 8 Dieter Gobeyn - Enterprise Integration Architect & Azure Cloud Solutions Architect

Session: Azure OpenAI Unplugged: Real-World Lessons from My Latest GenAI Project

Thinking of using Azure OpenAI in production? In this session, I’ll share detailed hard-earned lessons from my latest GenAI project, where I combined Azure OpenAI GPT-4 with data integration workflows. As both a solution architect and hands-on developer, I’ll walk you through what worked, what flopped, and what I wish I knew earlier. We’ll dive into managing costs, securing data, reducing hallucinations, fine-tuning prompts, and keeping token usage in check. Whether you’re exploring AI or scaling it, this session is packed with tips to help you avoid pitfalls and build smarter, more efficient AI solutions.

16:00pm - Closing Keynote Lee Stott - Principal Cloud Advocate Manager@Microsoft

Session: Device Intelligence with SLM: A Path to Edge Deployment and Cloud Integration

In today’s fast-paced tech landscape, many organisations aim to enhance device intelligence and responsiveness. This presentation highlights the crucial role of Small Language Models (SLM) in solving business problems and improving device capabilities. By fine-tuning SLM, you can achieve optimal performance and adaptability. We will compare SLM with Large Language Models (LLM), showing why SLM is better suited for organisation’s needs. The importance of customization in fine-tuning these models will be emphasized. A key focus will be on deploying these models on edge devices for real-time processing and decision-making, boosting device intelligence and positioning your organisation as an innovation leader. The presentation will provide a roadmap for implementation, from cloud development to deployment across platforms. Using Azure, organisations can ensure seamless integration and IP ownership, gaining a competitive edge.

Discover how your organisation can leverage SLM to revolutionize its devices and lead in intelligent technology.

By registering for this in person event you are agreeing to have your e-mail shared with building security for building access. Your privacy is important to us. This privacy statement explains the personal data Microsoft processes, how Microsoft processes it, and for what purposes. You can view our full privacy statement here: https://privacy.microsoft.com/privacystatement

Please join us on 12th February, 2025 to listen to the topic: Let's talk about Data Governance and how Microsoft Fabric brings it to a next level with Wolfgang Strasser

What \~ Toronto Data Professionals Community (Virtual) When \~ Wednesday, 12th February, 2025

Agenda:

• 12:00 PM Networking and Introduction
• 12:05 PM Topic: Let's talk about Data Governance and how Microsoft Fabric brings it to a next level with Wolfgang Strasser
• 1:00 PM End

Where: Online via Microsoft team

Session Details: Data Lakes, Lakehouses, Data Warehouses, Data Integration pipelines, notebooks and much more. Data is transformed, stored and reported using more and more technologies. For us as data professionials it is not easy to gain an overview about your data (analytics) landscape. With Microsoft Purview data catalog, we got a tool to do the inventory of your data landscape, classify data and track lineage. With Microsoft Fabric, we got an integrated SaaS analytics platform that contains (almost) everything: Data integration, data storage, data lake houses and warehouses and integrated Power BI reporting. How does this approach change in context of data cataloguing? How can we benefit from the integrated approach to get a better understanding of what happens to our data? Join this session to learn more about the concepts of a data catalog, how Microsoft Purview implements this and how Data Governance and Microsoft Fabric work better together.

Speaker Bio: Wolfgang Strasser, an experienced data consultant at ACP CUBIDO in Austria, specializes in leveraging the Microsoft Data Platform to drive analytics and data strategy transformations. With extensive experience in SQL Server, Azure Data Services, Power BI, and Microsoft Fabric, Wolfgang has established himself as a key resource for businesses aiming to optimize their data processes.

As a Microsoft Data Platform MVP, Wolfgang has a proven track record of excellence in data architecture, analytics, and data governance. He first was awarded in 2015 and since then rewarded every year.

Wolfgang's commitment to the data community is evident through his active participation in national and international conferences, workshops, and online platforms, where he shares insights, best practices, and technical knowledge. He is one of the organizers of Data Community Austria Day (Data Saturday Vienna).

About the Event:

Join us for a 2-day virtual conference on March 6 & 7 to discover the latest services and features in Azure designed specifically for JavaScript developers. You'll hear directly from the experts behind the most sought-after cloud services for developers to learn cutting-edge cloud development techniques that can save you time and money, while providing your customers with the best experience possible.

Join us for our Cloud Skills Challenge at https://aka.ms/AzureJSDay-Challenge.

Who Should Attend:

This event is for everyone interested in learning about JavaScript in Azure and all the opportunities you can unlock, regardless of your level of experience with Azure or JavaScript!

Agenda:

DAY 1: BUILDING AN INTELLIGENT APP WITH JS: DEV TOOLS AND AI

9:00 - 9:10 Introduction and Setup (10m) - Natalia Venditto, Principal Product Owner JavaScript E2E DevEx; Dina Berry, Senior Content Developer Azure JavaScript DevEx

Welcome to the start of the day where we will go over the agenda and then get set up with forking the repo we will use for this event.

9:10 - 9:40 GitHub Copilot Can Do That? (30 m) - Burke Holland, Principal Cloud Advocate VS Code

It’s hard to go even a single day anymore without hearing the word “Copilot”. GitHub Copilot is the original Copilot and the most widely adopted AI tool in history. In this session, we’ll jump into GitHub Copilot and take a look at some of the astonishing things that it can do and how it can make your life as a developer exponentially easier and more enjoyable.

9:40 - 10:25 Building a versatile RAG Pattern chat bot with Azure OpenAI, LangChain (45m) - Wassim Chegham, Senior Software Engineer JavaScript Developer Advocacy; Natalia Venditto, Principal Product Owner JavaScript E2E DevEx; Lars Gyrup Brink Nielsen, Microsoft MVP

In this session we will walk you through the code of our popular JavaScript Azure OpenAI sample, from the backend services, to the frontend application, and even the schema that connects them seamlessly together: the Chat Application Protocol. Lars will also present the most cutting edge new features of Angular in its version 17, a favorite to build enterprise scale applications with!

10:25 - 10:45 LangChain.js + Azure: A Generative AI App Journey (20m) - Yohan Lasorsa, Senior JavaScript Developer Advocate

Discover the journey of building a generative AI application using LangChain.js and Azure. This talk will explore the development process from idea to production, focusing on a RAG-based approach for a Q&A system using YouTube video transcripts. We'll demonstrate how we built a local prototype using open-source models and Ollama, and its transition to Azure for production.

10:45 - 11:10 Extending Copilot for Microsoft 365 using JavaScript and TypeScript (25m) - Bob German, Principal Cloud Advocate Microsoft 365

You may have heard that Microsoft 365 now has an AI Copilot to help users do more within Microsoft 365. What you might not know is that you can extend Copilot to work with your business data and external content. In this session you’ll learn how to extend Copilot with plugins and Graph connectors written in JavaScript and TypeScript. We’ll examine the architecture, relevant Azure resources, and of course the code. All code will be made available so you can try it yourself. It’s easy – please join the session to get started!

11:10 – 11:30 Have a safe coffee chat with your documentation using Azure AI Services (20m) - Maya Shavin, Senior Software Engineer

Building a custom documentation assistant using AI has become achievable with the help of GPT, LangChain and other AI tools. But how can we control the content quality of the coffee chat made to our document assistant, from the user to the assistant’s response? What options do we have to enhance the content safety in our question-and-answer flow, while scaling our project to handle further scenarios? Join my talk and let’s find out.

11:30-11:40 Outro (10m)

DAY 2: BUILDING AN INTELLIGENT APP WITH JS: HOSTING AND INTEGRATIONS

9:00 - 9:10 Introduction (10m) – Natalia Venditto, Principal Product Owner JavaScript E2E DevEx,

Welcome to the start of day two where we will go over today’s agenda and recap yesterday’s event.

9:10 - 9:40 Crafting Future-proof Apps with JavaScript & Azure Cosmos DB (30m) - Sajeetharan Sinnathurai, Principal Product Manager Azure Cosmos DB

In this session, we'll discuss the developer experience of Cosmos DB with JavaScript, covering the latest additions to the SDK. Additionally, we'll explore Vercel integration for seamless deployment of JavaScript-based applications using templates.

9:40 - 10:00 Turn your database into GraphQL APIs with Azure Static Web Apps Database Connections (20m) - Thomas Gavin, Product Manager Azure Static Web Apps; Stacy Cashmore, MVP for Developer Technologies

Skip the boilerplate server code and use Static Web Apps Database Connections to directly access your database contents using a set of provided GraphQL APIs. In this session, we demo how you can quickly go from frontend to full-stack, saving results in a CosmosDB database using Database Connections and deploying to Azure Static Web Apps.

10:00 – 10:25 Build real-time web apps with Socket.IO and let Azure handle scalability, no more adapters (25m) - Ken Chen, Principal Software Eng Manager Azure Web PubSub and Azure SignalR; Kevin Guo, Senior Product manager Azure Web PubSub and Azure SignalR

Socket.IO is a popular open-source library among JavaScript developers for building real-time web apps. In this session, we are going to explore what we mean by “real-time” web apps and how Socket.IO library can help web developers build them. Also, we discuss a common challenge among Socket.IO developers – scaling out to multiple Socket.IO servers. Through a quick demo, we showcase how easy it is to leverage the recently introduced support for Socket.IO on Azure to offload scalability issue to a cloud service.

10:25 - 11:10 Playwright in Action: From Setup to Best Practices (45m) - Max Schmitt, Software Engineer Playwright; Stefan Judis, Playwright Ambassador

Dive into the essentials of end-to-end testing with Playwright in this engaging 45-minute session. A Playwright core contributor will guide you through a hands-on demo, demonstrating how to efficiently set up, execute automated tests and debug them in GitHub Actions. After that a Playwright ambassador will share the best practices and tips to optimize your testing workflow.

11:10 – 11:20 Outro (10m)

** This is a great chance to start or advance your journey towards improving your developer productivity and innovation. Join us for exciting sessions with insights, useful tips, and interactive discussions that will help you unlock your full potential as a JavaScript developer. We can't wait to see you there on March 6 & 7! **

Hi, Data Folks from Hamburg!

After the summer break, we'll jump into your most requested topic, "How to use your data with the OpenAI API?". Topics include function calls, agents, prompt engineering stuff, and more.

This will be an entire evening of content on "Azure OpenAI Service & OpenAI API"!

Attention! We have gained another room sponsor! The Computer Futures! Don't worry; you won't have to figure out a new route for the evening, as the venue is virtually on the opposite street side of Microsoft, in the Axel-Springer-Building.

We will keep our Hanseatic-Mini-Conference concept and have four speakers on the topic.

Afterward, we will have a panel discussion, where you can ask all the experts to present questions. We will also discuss the new products and announcements from OpenAI on Monday (OpenAI DevDay).

In cooperation with JetBrains, we offer you the opportunity to win 1-year licenses for their products.

And as usual, cold drinks will be available again. Thank you, Computer Futures!

• 18:00 Open door and warm up networking round
• 18:15 Intro
• 18:30 Talk 1
• 18:55 Talk 2
• 19:20 Pause 20min
• 19:40 Talk 3
• 20:05 Talk 4
• 20:30 Panel Discussion with all experts
• 21:00 The End...

Boosting LLM Capabilities \| 25min (Sascha Lorenz) There are only two ways to incorporate "data" into working with an LLM - fine-tuning the model or using the prompt. The usage of the prompt is often referred to as prompt engineering, but this is much more complex than a series of hacks and tricks on your favorite social media feed. Sascha will address strategies for prompt design that combine zero-shot theory, chain-of-thought theory, role prompting, and few-shot prompting to create efficient prompts. It will also touch upon "Memory," LangChain, vector & graph stores, agents, and multi-agent systems like AutoGen. All of these methods can be used to enhance LLM capabilities.

ChatGPT as a Team Assistant \| 25min (Martin Stoll) mindworks GmbH is in the process of developing web applications aimed at supporting and enhancing business processes. The company is currently conducting experiments with the ChatGPT API to create an AI assistant capable of independently managing practical, routine tasks encountered in day-to-day work. Martin Stoll provides insights into his concepts and shares the experiences acquired up to this point.

Discover Real-World Projects powered by Azure OpenAI and Integration \| 25min (Ruben Aster) Services Dive into practical applications and journey through projects executed for and in collaboration with our clients. As an integration consultancy positioned closely to our customer's data, we seize numerous opportunities to implement AI. Delve into the Support-Email Assistant, a tool that seamlessly melds with Outlook, harnessing the power of Azure OpenAI to categorize emails and formulate responses, all while tapping into CRM data. Uncover how support-ticket processes are refined using Azure OpenAI alongside Cognitive Search, and gain insights into the strides made in document management with Azure Document Intelligence. This session promises a brisk yet detailed exploration of Azure AI’s capacity to boost operational efficiency.

Unlocking Knowledge: Extracting Q&A from Corporate PDFs using Azure Cognitive Services \| 25min (Sven Sönnichsen) Discover how to transform static company PDF files into dynamic knowledge repositories using Azure Cognitive Services. In this talk, we will walk you through the step-by-step setup of Azure resources, including Azure DevOps (AZD), Blob Storage, and Azure Search Service, to seamlessly extract, process, and generate questions and answers from your documents. Learn how to leverage these powerful tools to enhance accessibility, streamline information retrieval, and foster a more informed and efficient workspace.

Agenda 18:00 - 18:45 - Pizza and networking

18:45 - 19:35

Take Control of your Azure SQL Managed Instance Migration using the Log Replay Service This session covers the Log Replay Service (LRS), a new free of charge Azure service for migrating databases to SQL managed instance. Learn when you would use it over existing migration methods, like the Data Migration Service (DMS), to solve some migration challenges. And I'll show how I used it in a recent customer project to customise the migration of multi-terabyte databases to SQL managed instance using a combination of full, differential and log backups within a strict downtime window.

I'll also introduce you to some features we implemented post-migration, like Intelligent Query Processing and Data Virtualization, that resulted in the huge improvements in batch processing times in SQL managed instance. Rob Carrol Principal Data Platform Consultant, Coeo I've been working with SQL Server for over 20 years, firstly as a DBA and now as a consultant. I joined Coeo as a Consultant in 2021 providing advice and guidance to customers modernising their SQL Server platforms. I previously worked for Microsoft as a Premier Field Engineer (PFE) and as an independent database consultant, working across various sectors including Financial Services, Retail and Defence. When I'm not working with SQL Server, I'm a keen runner and enjoy spending time with my family.

19:35 - 19:45 - Bio Break

19:45 - 20:35

How Can Microsoft Fabric Have an Impact on Your Business?

All this talk about Data-Ware-Lake-Delta-Beach-House-Lakes (or some combination of that) and Data, Yarn, Fabric integration, everything has got a bit… Meshy! Yes, my friends. The beat of the technology drum is certainly relentless. And with no limits cloud scale and huge innovations from the biggest brains. Two years, it seems, has become the benchmark for tools to live and die by. Reach three years and you almost have a mature product. That said, Microsoft Fabric, the latest offering from global software giant is no exception. But what does this mean for the real world. For the data analysts, engineers and scientists that need to continue answering everyday problems to inform business decisions. In this session we will firmly ignore the hype and focus on the reality. With the pragmatic view of an experienced architect. The problem of gaining insights from our data hasn’t changed. So, what does this mean if implemented using Microsoft Fabric. What, why and how is the tooling going to change our daily deliverables in the short term, medium and long term. Join me for these answers and more as we explore the impact of Microsoft Fabric-Server, erm, Power. Resource. Thing!

Paul (AKA @mrpaulandrew) is the Founder & CTO of Cloud Formations, a specialist data consultancy based in the UK. With nearly 20 years’ experience designing and delivering Microsoft data architectures, Paul leads a passionate team of engineers, supporting businesses small and large with scalable cloud platforms. Business value delivered through data insights. Over the years, covering a breadth of design patterns and industry leading concepts, including Lambda, Kappa, Delta Lake, Data Mesh and Data Fabric. Paul is also a Microsoft Data Platform MVP, director for the Data Relay conference, East Midlands user group leader, book author and mentor. In addition to the day job(s), Paul is a father of three, husband, foodie, runner, blood donor, geek, Lego, and Star Wars fan! Lastly, Paul confesses to enjoying a Ramstein playlist when given half a chance to do some coding for a customer project.

Summary Data integration from source systems to their downstream destinations is the foundational step for any data product. With the increasing expecation for information to be instantly accessible, it drives the need for reliable change data capture. The team at Fivetran have recently introduced that functionality to power real-time data products. In this episode Mark Van de Wiel explains how they integrated CDC functionality into their existing product, discusses the nuances of different approaches to change data capture from various sources.

Announcements

Hello and welcome to the Data Engineering Podcast, the show about modern data management When you’re ready to build your next pipeline, or want to test out the projects you hear about on the show, you’ll need somewhere to deploy it, so check out our friends at Linode. With their new managed database service you can launch a production ready MySQL, Postgres, or MongoDB cluster in minutes, with automated backups, 40 Gbps connections from your application hosts, and high throughput SSDs. Go to dataengineeringpodcast.com/linode today and get a $100 credit to launch a database, create a Kubernetes cluster, or take advantage of all of their other services. And don’t forget to thank them for their continued support of this show! You wake up to a Slack message from your CEO, who’s upset because the company’s revenue dashboard is broken. You’re told to fix it before this morning’s board meeting, which is just minutes away. Enter Metaplane, the industry’s only self-serve data observability tool. In just a few clicks, you identify the issue’s root cause, conduct an impact analysis⁠—and save the day. Data leaders at Imperfect Foods, Drift, and Vendr love Metaplane because it helps them catch, investigate, and fix data quality issues before their stakeholders ever notice they exist. Setup takes 30 minutes. You can literally get up and running with Metaplane by the end of this podcast. Sign up for a free-forever plan at dataengineeringpodcast.com/metaplane, or try out their most advanced features with a 14-day free trial. Mention the podcast to get a free "In Data We Trust World Tour" t-shirt. RudderStack helps you build a customer data platform on your warehouse or data lake. Instead of trapping data in a black box, they enable you to easily collect customer data from the entire stack and build an identity graph on your warehouse, giving you full visibility and control. Their SDKs make event streaming from any app or website easy, and their state-of-the-art reverse ETL pipelines enable you to send enriched data to any cloud tool. Sign up free… or just get the free t-shirt for being a listener of the Data Engineering Podcast at dataengineeringpodcast.com/rudder. Data teams are increasingly under pressure to deliver. According to a recent survey by Ascend.io, 95% in fact reported being at or over capacity. With 72% of data experts reporting demands on their team going up faster than they can hire, it’s no surprise they are increasingly turning to automation. In fact, while only 3.5% report having current investments in automation, 85% of data teams plan on investing in automation in the next 12 months. 85%!!! That’s where our friends at Ascend.io come in. The Ascend Data Automation Cloud provides a unified platform for data ingestion, transformation, orchestration, and observability. Ascend users love its declarative pipelines, powerful SDK, elegant UI, and extensible plug-in architecture, as well as its support for Python, SQL, Scala, and Java. Ascend automates workloads on Snowflake, Databricks, BigQuery, and open source Spark, and can be deployed in AWS, Azure, or GCP. Go to dataengineeringpodcast.com/ascend and sign up for a free trial. If you’re a data engineering podcast listener, you get credits worth $5,000 when you become a customer. Your host is Tobias Macey and today I’m interviewing Mark Van de Wiel about Fivetran’s implementation of chang