Microsoft Reactor San Francisco

In this session we will make the agent production-ready. We will add job scheduling as a background service, integrate Azure OpenAI and Azure AI Foundry as cloud model providers, build monitoring dashboards, and write unit tests that verify the entire stack.

At the end we will have a complete, tested, cloud-ready agent platform with production-grade error handling, multiple AI model providers, scheduled automation, and observability dashboards. Deploy it to Azure Container Apps, App Service, or run it on-premises with Ollama.

Key Topics & Technologies:

• BackgroundService for long-running jobs
• Azure OpenAI integration and model selection
• Azure AI Foundry (inference, deployments, evaluation)
• Unit testing patterns for agents and tools
• Health checks and system diagnostics
• Job queuing and status tracking
• Configuration for multi-environment deployments (local, staging, production)

Pre-requisites:

• Experience: Intermediate C# and ASP.NET Core knowledge (not a .NET 101)
• Environment: .NET 10 SDK, VS Code + GitHub Copilot (or Visual Studio), Docker (for Ollama)
• Optional: Azure subscription (for Sessions 3–4, but local development works fine throughout)
• Mindset: Curiosity about AI agents, willingness to follow along live and ask questions

Esta sesión de Azure sobre Landing Zone se centra en cómo crear una base sólida para la adopción de la nube mediante la implementación de un entorno inicial estructurado y seguro. Una Landing Zone proporciona un conjunto de políticas, controles de seguridad y arquitecturas recomendadas que facilitan la migración y expansión de las cargas de trabajo en Azure.

Don’t just react—stay ahead.

Discover how to monitor, detect, and respond to AI-specific security threats using Defender for Cloud AI Foundry’s powerful capabilities.

What you’ll learn:

• Define access boundaries using Microsoft Entra ID and role-based access control (RBAC)
• Manage project-level permissions within shared environments
• Secure secrets with Key Vault and managed identities
• Isolate workloads with managed virtual networks and Private Link
• Enable diagnostic logging for centralized visibility and investigation

Who should attend:
Developers, Security Engineers, and technical professionals who want to learn how to configure policies and alerts that keep AI workloads safe and compliant, giving you full control over your cloud environment.

📍 https://aka.ms/SecureMSFTFoundryEnvironments