Monday 9:00 AM - 5:00 PM · Room C

Hands-On: Azure, ChatGPT, DeepSeek, Azure OpenAI For Power Platform Developers Masterclass

Gartner predicts, “by 2026, over 65% of medium to large enterprises will have adopted a Low Code Application Platform as one of their strategic application platforms.” Microsoft Power Platform is a low-code platform for rapidly building customized end-to-end business solutions. It consists of five product areas: Power Apps, Power Automate, Power BI, Copilot Studio, and Power Pages. Each area can be used individually or together. Thanks to native integration with Azure, developers can use their cloud development skills to extend Microsoft Power Platform with different Azure services. With a low-code integrated development approach, business goals can be achieved faster and free up time for the developers.

In this hands-on workshop, Microsoft AI and Business Applications MVP and Microsoft Certified Trainer, Prashant G Bhoyar, will cover these topics in detail:.

1. Microsoft Azure Key Concepts
2. Azure AI Foundry Key Concepts
3. Authentication and Authorization in Azure
4. Azure OpenAI Key Concepts
5. ChatGPT key concepts
6. How can fusion teams take advantage of Azure OpenAI, ChatGPT, Azure AI Foundry, and Microsoft Copilot Studio?
7. Authentication in Microsoft Copilot Studio
8. Azure AI Foundry + Microsoft Copilot Studio
9. Azure AI Foundry + Power Automate
10. Azure AI Foundry + Power Apps
11. Azure AI Foundry + Power BI
12. Azure AI Foundry + Microsoft Fabric
13. Copilot Studio Plugins
14. Copilot Studio Copilot Connectors and Actions
15. How to create multimodal agents and custom copilots?
16. How to create Autonomous agents?
17. Copilot Studio and MCP ( Model Context Protocol)
18. How to use DeepSeek R1 with Azure AI Foundry?
19. How to evaluate a use case and find the ROI?
20. Responsible AI: Delve into the ethics and responsible use of AI.
21. Enterprise-level applications, Custom Copilots, and AI Agents: Learn to develop robust, scalable multimodal applications, Custom Copilots, and AI Agents using Power Platform, Copilot Studio, Azure AI Foundry, and Azure OpenAI, focusing on industry requirements and best practices.

At the end of the workshop, attendees will have a working knowledge of Azure, Azure OpenAI, and how to use it to implement the customizations in the Microsoft Power Platform.

Access to Microsoft Power Platform ( Power Apps, Power Automate, Copilot Studio, and Power BI ), Azure, Azure AI Foundry, DeepSeek, 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 Power Platform, Copilot Studio, and Azure subscriptions if available.

The target audience of this hands-on workshop is Developers, Power Users, and IT Pros who want to get into development.

Please note: Attendees will need to bring their laptops with internet access and modern browsers like Microsoft Edge, Google Chrome, Firefox, and Safari. The tablets will not work.

Tuesday 1:30 PM - 5:00 PM · Room G6

Copilot Studio Deep Dive

With ChatGPT, other large language models and generative AI have caught the attention of global consumers, enterprises, and c-suite. Microsoft's CEO Satya Nadella Says Microsoft is THE Copilot company. With the adoption of Copilots increasing at a rapid space, there is an exponential rise in the demand for custom Agents and Agent Flows ( Custom Copilots).

Microsoft Copilot Studio is a graphical, low-code tool for building agents and agent flows. One of the standout features is its ability to connect to other data sources using either prebuilt or custom plugins. This flexibility enables users to create and orchestrate sophisticated logic, ensuring that their agent experiences are both powerful and intuitive.

In this demo-driven workshop, we will cover advanced topics to create multi-agent systems and autonomous agents using Copilot Studio.

We will cover:

1. Microsoft Copilot Studio Key Concepts
2. Azure AI Foundry Key Concepts
3. What are multi-agent systems and autonomous agents?
4. How can organizations use the Microsoft Copilot Studio and Azure AI Foundry to build multi-agent systems and autonomous agents following industry best practices?

Wednesday 2:00 PM - 3:10 PM · Room 1

Building Intelligent Agents with Azure AI Foundry

In this session, we'll dive deep into the world of intelligent agents and explore how Azure AI Foundry empowers developers to build and deploy sophisticated AI-driven solutions. Learn how to create agents that can reason, learn, and interact with their environment, automating tasks, enhancing decision-making, and delivering personalized experiences.

Key Topics:

Understanding AI Agents: A comprehensive overview of AI agents, their components, and their potential applications.

Leveraging Azure AI Foundry: Explore the core features and benefits of Azure AI Foundry, including its powerful tools and services.

Building Intelligent Workflows: Design and implement complex workflows that orchestrate multiple AI services to achieve desired outcomes.

Training and Deploying Custom Models: Fine-tune pre-trained models or train your own custom models to tailor your agent's behavior.

Integrating with Real-World Systems: Connect your agent to various systems and data sources to automate tasks and gain valuable insights.

Monitoring and Optimizing Performance: Track your agent's performance and make necessary adjustments to ensure optimal operation.

Through hands-on demonstrations and practical examples, you'll gain the knowledge and skills to build intelligent agents that can revolutionize your business processes and user experiences.

Wednesday 3:50 PM - 5:00 PM · Room B

Copilot in the Loop: Automating End-to-End Workflows with Power Automate, Azure OpenAI & Teams

Manual approval chains and inbox overload slow every organization. This demo-heavy session shows how to drop Copilot directly inside Power Automate to read incoming documents, extract intent, summarize risks, and route decisions—all within Microsoft Teams. We’ll build a flow that uses Azure OpenAI for extraction, GPT function calls for policy checks, Adaptive Cards for human-in-the-loop review, and Dataverse tables for auditable storage. You’ll learn prompt-engineering tricks to keep legal happy, fallback patterns for offline users, and live metrics for cost control. By the final “F5,” attendees will have a blueprint they can retrofit to expenses, contract review, or support tickets.

Key Takeaways

Orchestrate GPT calls in cloud flows without breaking governance

Surface Copilot conversations in Teams with Adaptive Cards & Loop components

Measure and cap token usage with environment variables and Azure Cost Insights

Roll back or re-route if the model or network fails

Thursday 10:50 AM - 12:00 PM · Room 1

From Prompt to Production: Building Responsible Gen-AI Apps with Azure AI Studio

Azure AI Studio, now generally available with access to 1,600+ foundation and open-source models, lets Microsoft 365 and Power Platform professionals go from a clever prompt to an enterprise-ready Copilot in hours, not months. In this demo-heavy session you’ll learn how to:

Design multimodal prompts and chains in Prompt Flow.

Ground large-language models with your SharePoint or Dataverse data using Retrieval-Augmented Generation (RAG).

Govern outputs with built-in Content Safety, evaluations and cost dashboards.

Deploy as an Azure function, a Teams app, or a Power Automate connector—then surface the same logic inside Microsoft 365 Copilot.

We’ll walk through a live scenario that turns an internal policy PDF library into a secure “Ask HR” Copilot, highlighting pitfalls (token limits, latency) and best-practice mitigations. You’ll leave with a GitHub starter repo, a cost estimator sheet, and a checklist for responsible rollout. Microsoft

Key Takeaways

How Azure AI Studio’s Prompt Flow accelerates prototyping and A/B testing

Implementing RAG with Azure AI Search in three steps

Mapping governance features (Content Safety, evaluations) to your compliance needs

Packaging and sharing your Copilot inside Teams, Power Apps, or Outlook

Thursday 1:00 PM - 2:10 PM · Room A

How to Avoid AI Disasters: Copilot, Data Security, and Unintended Consequences

Say your company rushes in the coming months to implement a Copilot over their Intranet. An employee asks the Copilot, "How much does my co-worker make?" How will it answer?

This scenario becomes plausible as Copilot is connected to data sources for Q&A activities. If the data related to pay, layoffs, and other sensitive topics is accessible by the AI, it's possible that an employee could get an answer to their question. You should take great care before connecting it to your own internal data.

Unfortunately hearing GPT, AI and Machine Learning terms thrown about like doubloons at a Mardi Gras parade in the news is giving many organizations FOMO. We'll discuss what you should know before you jump in.

In this session, we'll address:

• What are these technologies and how they will impact you
• How can these technologies be used in your organization
• Data and security considerations
• Preparing for unintended consequences

Join us to learn about this brave new world and how you could apply it in your own work.

Thursday 4:20 PM - 5:30 PM · Room B

Integrating AI Applications with Copilot Studio Using Model Context Protocol (MCP)

Discover how to seamlessly integrate AI applications and agents into Microsoft Copilot Studio using the Model Context Protocol (MCP). In this session, we will explore how MCP enables direct connections to existing knowledge servers and APIs, allowing actions and knowledge to be automatically added and updated within your agents. Learn how this integration simplifies the agent-building process, reduces maintenance efforts, and leverages enterprise security and governance controls such as Virtual Network integration, Data Loss Prevention policies, and multiple authentication methods.

Friday 9:00 AM - 10:10 AM · Room D

Unleashing AI Agents in Your Enterprise: An Introduction to Azure AI Agent Service

The way we build and integrate AI into our business processes is evolving—fast. Microsoft’s new Azure AI Agent Service is changing the game, offering a powerful, orchestrated AI agent framework that simplifies building intelligent, multi-modal applications.

In this interactive session, you’ll get an inside look at how Azure AI Agent Service enables AI agents that plan, reason, and act autonomously—without complex coding. Whether you’re exploring AI-driven copilots, automating business workflows, or building next-gen customer experiences, this service unlocks new possibilities for AI adoption at scale.

What You’ll Learn:

• What Azure AI Agent Service is and why it matters
• How AI agents use tools, memory, and actions to automate tasks
• Real-world use cases and demos showcasing AI-driven automation
• How to get started and integrate this service into your Azure environment

This session is perfect for attendees looking to cut through the hype and get practical with AI agents. Don't miss this opportunity to stay ahead of the curve and discover how Azure AI Agent Service can accelerate AI adoption in your organization!

Friday 10:20 AM - 11:30 AM · Room G2

Intro to Microsoft Visual Studio Code AI Toolkit

Unlock the power of local AI development directly within your favorite editor! This session introduces the Microsoft Visual Studio Code AI Toolkit, a powerful extension designed to simplify running Small Language Models (SLMs) like Phi-3, Mistral, and Llama directly on your Windows machine. Forget complex setups and cloud dependencies for basic AI tasks; learn how this toolkit streamlines the process, enhancing privacy, speed, and developer workflow integration. We'll learn the best parts of running SLMs locally including security, data sensitivity, fine tuning, integration capabilities, and graphics card acceleration.

Friday 10:20 AM - 11:30 AM · Room A

Building Multimodal Apps, Autonomous Agents, Copilots using GenAI(Azure AI Foundry & Copilot Studio)

An agent is a powerful AI companion that can handle a range of interactions and tasks, from resolving issues requiring complex conversations to autonomously determining the best action to take based on its instructions and context. Agents coordinate a collection of language models, along with instructions, context, knowledge sources, topics, actions, inputs, and triggers to accomplish your desired goals.

In this session, Microsoft AI and Business Applications MVP and Microsoft Certified Trainer Prashant G Bhoyar will cover the following topics in detail:

1. What are Multimodal GenAI Applications? 2)What are AI Agents?
2. What are Autonomous Agents?
3. What are Custom Copilots?
4. Azure AI Foundry: An in-depth overview of the Azure AI Foundy.
5. Microsoft Copilot Studio lets you create powerful AI-powered copilots for a range of requests—from providing simple answers to common questions to resolving issues requiring complex conversations. Engage with customers and employees in multiple languages across websites, mobile apps, Facebook, Microsoft Teams, or any channel supported by the Azure Bot Framework.
6. Responsible AI: Delve into the ethics and responsible use of AI.
7. Enterprise-level applications, Custom Copilots, AI Agents: Learn to develop robust, scalable multimodal applications, Custom Copilots, and AI Agents, focusing on industry requirements and best practices.

Friday 12:30 PM - 1:40 PM · Room A

Copilot Studio vs. Azure AI Foundry

AI powered agents feel like they're coming everywhere, but how do you light up your own data in them not just for staff, but also for external guests? How can you incorporate an AI Agent into both scenarios securely?

We'll start the session with a level set on how AI really works, and in particular Retrieval Augmented Generation. A combination of Search and Large Language Models, it lets your chat interface answer questions it hasn't been trained by leveraging search. Built properly it also respects security, and only answers from content the user has access to, which can live in Dataverse, Microsoft 365, or any other search accessible repository.

One approach we'll cover is Copilot Studio, a low-code environment where you can build intelligent chat experiences using ready-made large language models, a dialog manager, and numerous data connectors. These can be published and licensed in a variety of ways, and can enforce security against your enterprise data.

The other approach is more code focused in Azure AI Foundry. If you want you can get into details around search population, chunking, AI models, and UI.

We'll also cover consumption based pricing from Microsoft for both.

Feeling faint of heart with all this tech talk? Don't despair. Yes we'll be showing code, but we'll also go over real-world business cases, and the solution architectures that leverage the Microsoft AI stacks.