Nashua CLOUD .NET User Group

Agenda:
6:00 PM - 7:30 PM - Guardrails in Action: Ensuring Safe AI with Azure AI Content Safety

Abstract:
AI can be powerful and helpful, but it also needs to be safe and kind. In this session, we’ll explore how Microsoft’s tools—like Azure AI Content Safety, Azure AI Foundry Guardrails, and the Responsible AI Toolkit—work together to keep AI trustworthy and respectful. You’ll learn how developers create custom blocklists to stop harmful or inappropriate words, and use severity thresholds to decide what content is safe to share. We’ll see how these guardrails act like digital seatbelts, helping AI make good choices, follow safety rules, and protect everyone who uses it. By the end, you’ll understand how we can teach AI to be responsible, friendly, and safe for all.

Tired of API limits and rising inference costs? Take control of your AI infrastructure! In this session, we’ll explore how to run open-source Large Language Models like LLaMA 3, Mistral, and more using Ollama—a tool to run LLMs locally—and Azure Container Apps for scalable, secure deployments.

You’ll learn how to:

• Build and deploy Ollama in a containerized environment
• Integrate local LLM inference into your own apps
• Secure, scale (Scale down to zero when not in use!), and monitor AI workloads the cloud-native way
• Watch a live demo of an end-to-end LLM deployment on Azure

Whether you’re creating private copilots, intelligent assistants, or exploring AI self-hosting, this session will show you how to own your AI stack—from model to deployment.

🎯 Who Should Attend:
Developers, cloud engineers, architects, and AI enthusiasts ready to experiment with open-source LLMs in the cloud.

🧰 Tech Stack:
Azure Container Apps | Ollama | Docker | LLaMA 3 | Mistral | Open-Source AI

Bring your curiosity, your beverage of choice, and your sense of adventure—we’ll make the cloud talk back! 🚀

Agenda:
6:00 PM - 8:00 PM - Building Action-Oriented AI Agents with Azure AI Foundry and the Agent Framework

Prerequisites:

• Valid Azure Subscription
• A laptop capable of using RDP (Remote Desktop Protocol) -- pre-configured machines will be provided to ensure a smooth hands-on experience.

Abstract:
In this hands-on workshop, you’ll learn how to build and extend intelligent AI agents using Microsoft’s new Agent Framework in Azure AI Foundry. We’ll begin by creating an agent through the Foundry portal, configuring prompt orchestration, tool usage, and multi-turn planning. You’ll then explore how to connect your custom data sources, enable secure context passing, and design multi-step task flows that make your agents adaptive and goal-oriented. The session concludes with a live demo integrating an embedding data source to create a functional agent capable of retrieving, reasoning, and acting—all supported by a starter repository to help you build your own production-grade agent experiences.