Microsoft AI Agentic Workshop Repository

Welcome to the official repository for the Microsoft AI Agentic Workshop! This repository provides all the resources, code, and documentation you need to explore, prototype, and compare various agent-based AI solutions using Microsoft's leading AI technologies.

---

Quick Links

• Business Scenario and Agent Design
• Getting Started (Setup Instructions)
• System Architecture Overview
• Data Sets
• APIM + MCP Security (Optional)
• Code of Conduct
• Security Guidelines
• Support
• License

---

What You Can Do With This Repo

• Design and prototype AI agent solutions for real-world business scenarios
• Explore single-agent and multi-agent architectures with different orchestration patterns
• Build with Microsoft Agent Framework - advanced multi-agent orchestration, handoffs, and checkpointing
• Build end-to-end agentic AI systems - Complete architecture from backend database, MCP tools server, agent orchestration, application backend, to React/Streamlit frontend
• Deploy to Azure with enterprise security - VNet, private endpoints, managed identity, and CI/CD automation

---

Key Features

• Microsoft Agent Framework Integration - Single-agent, multi-agent Magentic orchestration, and handoff-based domain routing with MCP tools. Pattern guide →
• Workflow Orchestration - Hybrid Workflow + Durable Task architecture with fan-out/fan-in topology, human-in-the-loop, and real-time observability. Fraud Detection Demo →
• Observability with Application Insights - Full tracing of agent executions, tool calls, and LLM invocations with pre-built Grafana dashboards. Setup Guide →
• Advanced UI Options - React frontend with interactive workflow visualization and step-by-step tool call details
• MCP Server Integration - Model Context Protocol for enhanced agent tool capabilities with advanced features: authentication, RBAC, and APIM integration
• Agent Evaluations - Evaluate agent performance with custom metrics and test datasets
• Agent State & History Persistence - In-memory or CosmosDB backend for conversation history and agent state
• Enterprise-Ready Reference Architecture - Production-grade deployment with VNet integration, private endpoints, managed identity, and Terraform/Bicep IaC
• CI/CD Pipeline - Automated dev-to-production promotion with per-developer environments, OIDC auth, agent evaluation gates, and doc-change filtering

---

Getting Started

1. Review the Setup Instructions for environment prerequisites and step-by-step installation.
2. Explore the Business Scenario and Agent Design to understand the workshop challenge.
3. Check out the Agent Framework Implementation Patterns to choose the right multi-agent approach (single-agent, Magentic orchestration, or handoff pattern).
4. Try the Durable Fraud Detection Workflow to see hybrid Workflow + Durable Task orchestration with human-in-the-loop.
5. Dive into System Architecture before building and customizing your agent solutions.
6. Utilize the Support Guide for troubleshooting and assistance.

---

Deploy to Azure

For enterprise-ready deployment with VNet integration, private endpoints, managed identity, and CI/CD automation, see the Deployment Guide.

Deployment Method	Description	Guide
🚀 Azure Developer CLI	Single-command quick start	azd Quick Start
🔧 Manual Deployment	PowerShell with Terraform/Bicep	Manual Steps
🔒 Enterprise Security	VNet, Private Endpoints, Managed Identity	Security Profiles
🚀 CI/CD Automation	GitHub Actions with OIDC	GitHub Actions Setup

---

Contributing

Please review our Code of Conduct and Security Guidelines before contributing.

---

License

This project is licensed under the terms described in the LICENSE file.