Agent Innovator Lab

Requirements View it on GitHub

Agent Innovoator Lab

The Agent Innovator Lab is designed to provide a structured learning experience for AI agent development by leveraging Microsoft Azure’s core services (Data & AI, App, and Infra). Each lab focuses on a specific topic, covering areas such as search algorithm optimization, agentic design patterns, and evaluation frameworks. Through this hands-on workshop, participants will gain practical experience in building, optimizing, and evaluating Azure-based AI agents, ultimately driving innovation and enhancing real-world AI system deployment. This repository includes RAG best practices, along with tools and techniques for innovating current architecture.

This hands-on lab is suitable for the following purposes:

  1. 1-day workshop (4-7 hours depending on customer)
  2. Hackathon starter code
  3. Reference guide for RAG/Multi-Agent design patterns

List of workshops

Provided below is a list of currently published modules:

Title Description and Link
Lab 0. Basic RAG Create RAG application with Azure AI Search
Lab 0. Basic Agent Basic Concepts of Agent and Agent toolkits (AutoGen and LangGraph)
Lab 1. Agentic Design Pattern Practice representative patterns of Agentic RAG
Lab 2. Evaluation Design Pattern Practice the Evaluation-Driven RAG patterns
Lab 3. Optimization Design Pattern In Developmet
Lab Intermission. Agentic Workflow Design Lab Design Agentic Workflow before each hands-on session

Requirements

Before starting, you should meet the following requirements:

Please do not forget to modify the .env file to match your account. Rename sample.env to .env or copy and use it

Get started

If you are using your own local

# Create a virtual environment
python -m venv venv

# Activate the virtual environment
# On Windows
venv\Scripts\activate

# On macOS/Linux
source venv/bin/activate

# Set up your environment
git clone https://github.com/Azure/agent-innovator-lab.git

cd agent-innovator-lab 

pip install -r requirements.txt


If you are using Azure ML Compute Instance

conda create -n venv_agentlab python=3.11

# Set up your environment
git clone https://github.com/Azure/agent-innovator-lab.git

cd agent-innovator-lab 

pip install -r requirements.txt

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft’s Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.


Distributed by an MIT license. This hands-on lab was developed by Microsoft AI GBB (Global Black Belt).