Nashua CLOUD .NET User Group

Agenda:
6:00 PM - 7:30 PM - Model Context Protocol (MCP): Connecting AI Models to Real Systems

Abstract:
LLMs are powerful, but real impact comes when they can safely and reliably interact with tools, APIs, and enterprise systems. In this session, we’ll explore the Model Context Protocol (MCP)—a standard for connecting AI models to real-world systems securely, governably, and reusably.

We’ll cover what MCP is (and is not), how it differs from function calling and plugins, and how MCP Clients and Servers work together using stdio and SSE transports. The talk includes a live demo showing MCP tool integration in practice.

Who should attend: architects, developers, and anyone building production-grade AI systems beyond simple demos.

Azure Machine Learning (Azure ML) is a powerful platform for building, training, and deploying machine learning models in the cloud. In this session, we’ll take a practical, beginner‑friendly tour of the core concepts you need to get started. This is a brief overview, designed to help you understand what Azure ML offers and how you can begin using it in your own projects.
You’ll get an introduction to:

• What Azure Machine Learning is
• The Azure ML workspace and the basic tools available (Studio, SDK, CLI)
• How compute, data, and models are organized in Azure ML
• The general workflow for training and deploying a model
• Key concepts to help you explore further on your own

This session is meant to give you a solid foundation — not to cover every feature — so you leave with clarity, confidence, and a clear path for continued learning. New to machine learning? See how to make your first step with Azure ML Studio.

In this second session of the Azure Machine Learning series, we’ll move beyond the high‑level overview and dive into one of the most essential parts of any ML workflow: preparing and managing your data. Azure Machine Learning provides powerful tools for ingesting, transforming, and organizing datasets so you can build reliable, repeatable machine learning pipelines.
This session focuses on the practical side of ETL (Extract, Transform, Load) within Azure ML and how to work effectively with datasets in the platform. Whether you’re coming from Step 1 or already familiar with the basics, this meetup will help you understand how data flows through Azure ML and how to set up your environment for successful model training.
You’ll learn:

• How ETL fits into the machine learning lifecycle
• Options for ingesting data into Azure ML (local files, cloud storage, data stores)
• How to create, version, and manage Azure ML Datasets
• Techniques for transforming and preparing data using the Studio UI, SDK, and pipelines
• Best practices for organizing data for reproducibility and collaboration
• How prepared datasets connect to training jobs and experiments

This session is designed to give you the confidence to start building real ML workflows with clean, well‑structured data. If you’re ready to move from “What is Azure ML?” to “How do I actually use it with my data?”, this is your next step.

Agenda:
6:00 PM - 7:30 PM - AI Workflows with Microsoft Agent Framework

Abstract:
AI systems become reliable when workflows—not prompts—define execution.
In this session, we’ll focus on Microsoft Agent Framework Workflows, the core abstraction for building structured, deterministic, and observable AI systems.

You’ll learn how workflows model AI behavior as explicit execution graphs composed of executors, edges, and type-safe messages, enabling planning, tool execution, reflection, human-in-the-loop interventions, and controlled retries. We’ll explore how orchestrations coordinate these workflows, manage state, and control execution paths—bringing predictability and debuggability to multi-step AI processes.

Rather than relying on opaque agent loops, Microsoft Agent Framework workflows make control flow, decision points, human approvals, and system behavior explicit, making them suitable for production, governance, and enterprise integration.

### Key takeaways:

• Why workflows are the foundational concept in Agent Framework
• Core workflow primitives: executors, edges, messages, checkpoints
• How orchestrations manage flow, state, execution paths, and human-in-the-loop steps
• When to use workflows instead of prompt-driven agents
• Designing AI systems that are deterministic, testable, observable, and governable