LLM-Automated-Inventory-Management

This is a group final project for 5 final semester computer engineers at USF working with Microsoft.

The project builds an AI-driven, multi-agent customer service system for Contoso that automates quote requests, purchase orders, and inventory management using LLMs, A2A communication, and MCP. It includes email-based customer workflows with onboarding and authorization rules, quote persistence, inventory updates, and an admin conversational interface to monitor outstanding quotes, unavailable items, and system status, all within Azure and compliance/budget constraints.

Setup

Prerequisites

• uv (Python 3.11+ will be managed by uv)

Initial Setup

# Clone the repo
git clone <repo-url>
cd LLM-Automated-Inventory-Management

# Install all dependencies (including dev dependencies)
uv sync

If you plan to contribute, follow the additional developer workflow steps in CONTRIBUTING.md.

Contributing

Please read CONTRIBUTING.md for details on our development workflow, coding standards, and how to submit pull requests.