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.
- Business Scenario and Agent Design
- Getting Started (Setup Instructions)
- System Architecture Overview
- Data Sets
- Code of Conduct
- Security Guidelines
- Support
- License
- Design and prototype agent solutions for real-world business scenarios.
- Compare single-agent vs. multi-agent architectures and approaches.
- Develop and contrast agent implementations using different platforms:
- Azure AI Agent Service
- Semantic Kernel
- Autogen
- Configurable LLM Backend: Use the latest Azure OpenAI GPT models (e.g., GPT-4.1, GPT-4o).
- MCP Server Integration: Advanced tools to enhance agent orchestration and capabilities.
- A2A (Agent-to-Agent) Protocol Support: Enables strict cross-domain, black-box multi-agent collaboration using Google's A2A protocol.
- Flexible Agent Architecture:
- Supports single-agent, multi-agent, or reflection-based agents (selectable via
.env
). - Agents can self-loop, collaborate, reflect, or take on dynamic roles as defined in modules.
- Supports single-agent, multi-agent, or reflection-based agents (selectable via
- Session-Based Chat: Persistent conversation history for each session.
- Full-Stack Application:
- FastAPI backend with RESTful endpoints (chat, reset, history, etc.).
- Streamlit frontend for real-time chat, session management, and history viewing.
- Environment-Based Configuration: Easily configure the system using
.env
files.
- Review the Setup Instructions for environment prerequisites and step-by-step installation.
- Explore the Business Scenario and Agent Design to understand the workshop challenge.
- Dive into System Architecture before building and customizing your agent solutions.
- Utilize the Support Guide for troubleshooting and assistance.
This repository now supports a strict cross-domain multi-agent scenario using the A2A protocol, enabling message-driven, black-box collaboration between a customer-service agent and a logistics agent.
A2A Example Included:
See agentic_ai/agents/semantic_kernel/multi_agent/a2a
.
Please review our Code of Conduct and Security Guidelines before contributing.
This project is licensed under the terms described in the LICENSE file.