SAP-samples/btp-sourcing-decision-board

Sourcing Decision Board

Description

AI-Powered Strategic Sourcing Decision Support System

The Sourcing Decision Board is a procurement decision support system implementing parallel, heterogeneous agentic loop strategies for sourcing award optimization. Instead of relying on a single AI approach, it runs multiple independent AI strategies simultaneously and cross-validates their recommendations before presenting results to procurement professionals.

Key Features

• 🤖 Dual-Strategy AI Execution: Cooperative (Iterative Refinement) and Adversarial (Debate/Challenge) approaches
• ✅ Automated Cross-Validation: Compare results from different strategies for higher confidence
• 📊 Real-Time Decision Board: Live execution monitoring with streaming updates
• 💾 Complete Persistence: SQLite database with full decision history
• 🔍 Decision History: Browse, search, and filter previous RFQ decisions
• 🎯 Intelligent Dual-Sourcing: Automated optimization of supplier splits
• 📈 Strategy Comparison Dashboard: Side-by-side analysis of AI recommendations
• 🔐 Human-in-the-Loop: Structured governance framework for final decisions

Technology Stack

• Backend: Python 3.11+ / Flask
• Frontend: React + SAPUI5
• AI/ML: SAP AI Core + SAP Generative AI Hub
• Database: SQLite (with full audit trail)
• Deployment: SAP BTP Cloud Foundry ready

API Endpoints

Requirements

• Python 3.11 or higher
• SAP BTP account with AI Core enabled
• SAP Generative AI Hub access
• Node.js 18+ (for React frontend build)

Download and Installation

Quick Start

# Clone repository
git clone https://github.com/SAP-samples/btp-sourcing-decision-board.git
cd btp-sourcing-decision-board

# Install Python dependencies
pip install -r requirements.txt

# Configure environment
cp .env.example .env
# Edit .env with your SAP AI Core credentials

# Build React frontend
cd react-app
npm install
npm run build
cd ..

# Run locally
python server.py

Visit http://localhost:5000 to access the application.

Environment Variables

# SAP AI Core Configuration
SAP_AI_CLIENT_ID=your-client-id
SAP_AI_CLIENT_SECRET=your-client-secret
SAP_AI_AUTH_URL=https://your-subdomain.authentication.eu10.hana.ondemand.com
SAP_AI_API_URL=https://api.ai.prod.eu-central-1.aws.ml.hana.ondemand.com
SAP_AI_DEPLOYMENT_ID=your-deployment-id

# Application Settings
ENABLE_AI_AGENTS=true
PORT=5000
DB_PATH=decisions.db

Usage

1. Create a Decision — POST supplier/RFQ data to /api/decision
2. Select Strategy — Choose Single or Dual (recommended) strategy execution
3. Review Results — View AI recommendations in the Comparison Dashboard
4. View History — Browse all previous decisions with search and filtering

Deployment to SAP BTP Cloud Foundry

# Login to Cloud Foundry
cf login

# Deploy application
cf push

See TESTING_GUIDE.md for detailed testing and deployment instructions.

Known Issues

No known issues.

How to obtain support

Create an issue in this repository if you find a bug or have questions about the content.

For additional support, ask a question in SAP Community.

Contributing

If you wish to contribute code, offer fixes or improvements, please send a pull request. Due to legal reasons, contributors will be asked to accept a DCO when they create the first pull request to this project. This happens in an automated fashion during the submission process. SAP uses the standard DCO text of the Linux Foundation.

License

Copyright (c) 2026 SAP SE or an SAP affiliate company. All rights reserved. This project is licensed under the Apache Software License, version 2.0 except as noted otherwise in the LICENSE file.