---
title: AI Procurement Agent Demo
emoji: 🤖
colorFrom: blue
colorTo: purple
sdk: streamlit
sdk_version: 1.29.0
app_file: app.py
pinned: false
license: mit
---

# 🤖 AI Procurement Agent Demo

An intelligent procurement agent that leverages reinforcement learning (PPO) for optimal supplier selection and allocation decisions.

## Features

🎯 **Smart Supplier Selection**: Uses PPO (Proximal Policy Optimization) to make optimal allocation decisions

📊 **Real-time Market Analysis**: Considers volatility, demand changes, and price fluctuations

🔍 **Multi-criteria Optimization**: Balances cost, quality, delivery performance, financial risk, and ESG factors

🤖 **Autonomous Decision Making**: End-to-end procurement process automation

📈 **Interactive Visualization**: Real-time dashboards and performance metrics

## How It Works

1. **Market Analysis**: Analyzes current market conditions and volatility
2. **Supplier Evaluation**: Assesses suppliers across multiple dimensions
3. **AI Recommendation**: Uses trained PPO model for optimal allocation
4. **PO Generation**: Automatically creates purchase orders
5. **SAP Integration**: (Mocked) Integration with enterprise systems

## Technology Stack

- **Reinforcement Learning**: Stable-Baselines3 PPO
- **Agent Framework**: SmolagentS for tool orchestration
- **Visualization**: Plotly for interactive charts
- **Backend**: Python with NumPy/Pandas
- **Frontend**: Streamlit for web interface

## Usage

1. Adjust market parameters (volatility, demand, pricing)
2. Configure supplier settings
3. Click "Run Procurement Agent"
4. View AI recommendations and generated purchase orders

Perfect for demonstrating AI-driven procurement automation and intelligent supply chain management!