RewardPilot - AI-Powered Credit Card Optimizer
Maximize your credit card rewards with intelligent recommendations
Get AI-powered credit card recommendations that maximize your rewards based on:
- 💰 Reward Rates - Optimal card selection for each purchase
- 📚 Card Benefits - Detailed information from our knowledge base
- ⚠️ Spending Caps - Risk warnings to avoid missing out on bonuses
🤖 Autonomous Agent: ✅ Active (Claude 3.5 Sonnet)
📊 Mode: Dynamic Planning + Reasoning
⚡ Services: Smart Wallet + RAG + Forecast
Transaction Details
Select a user
Select the category first
Select merchant (changes based on category)
💡 Recommendation
✨ Select a category and merchant, then click 'Get Recommendation'
📊 Quick Stats
🔄 Card Comparison
📝 Example Transactions
| User ID | 🏷️ Type of Purchase | 🏪 Merchant Name | 💵 Amount (USD) | Use Custom MCC Code | Custom MCC Code | 📅 Transaction Date (Optional) |
|---|
🎯 Your Rewards Optimization Dashboard
📊 Visual Analytics
📋 Detailed Breakdown
💰 Category Spending Breakdown
| Category | Monthly Spend | Best Card | Rewards | Rate |
|---|---|---|---|---|
| 🛒 Groceries | $450.00 | Amex Gold | $27.00 | 6% |
| 🍽️ Restaurants | $320.00 | Amex Gold | $12.80 | 4% |
| ⛽ Gas | $180.00 | Costco Visa | $7.20 | 4% |
| ✈️ Travel | $850.00 | Sapphire Reserve | $42.50 | 5% |
| 🎬 Entertainment | $125.00 | Freedom Unlimited | $1.88 | 1.5% |
| 🏪 Online Shopping | $280.00 | Amazon Prime | $16.80 | 6% |
| Total | $2,205.00 | - | $108.18 | 4.9% |
📈 Monthly Trends & Insights
🔥 Top Spending Categories:
- ✈️ Travel: $850 (↑ 45% from last month)
- 🛒 Groceries: $450 (↑ 12%)
- 🍽️ Restaurants: $320 (↓ 5%)
💡 Optimization Opportunities:
- ✅ You're using optimal cards 87% of the time
- 🎯 Switch to Chase Freedom for Q4 5% grocery bonus
- ⚠️ Amex Gold dining cap approaching ($2,000 limit)
🏆 Best Performing Card: Chase Sapphire Reserve - $42.50 rewards earned
📊 Year-to-Date:
- Total Rewards: $1,298.16
- Potential if optimized: $1,640.00
- Money left on table: $341.84
🔮 Next Month Forecast
Based on your spending patterns:
- Predicted Spend: $2,350
- Predicted Rewards: $115.25
- Cards to Watch: Amex Gold (dining cap), Freedom (quarterly bonus)
Recommendations:
- 💳 Use Chase Freedom for groceries in Q4 (5% back)
- ⚠️ Monitor Amex Gold dining spend (cap at $2,000)
- 🎯 Book holiday travel with Sapphire Reserve for 5x points
Analytics loaded for u_alice
Chat with RewardPilot AI
Ask questions about credit cards, rewards, and your spending
💡 Try asking:
How the Autonomous Agent Works
RewardPilot uses Claude 3.5 Sonnet as an autonomous agent to provide intelligent card recommendations.
🎯 Phase 1: Planning
The agent analyzes your transaction and decides:
- Which microservices to call (Smart Wallet, RAG, Forecast)
- In what order to call them
- What to optimize for (rewards, caps, benefits)
- Confidence level of the plan
🤔 Phase 2: Execution
The agent dynamically:
- Calls services based on the plan
- Handles failures gracefully
- Adapts if services are unavailable
- Collects all relevant data
🧠 Phase 3: Reasoning
The agent synthesizes results to:
- Explain why this card is best
- Identify potential risks or warnings
- Suggest alternative options
- Calculate annual impact
📚 Phase 4: Learning
The agent improves over time by:
- Storing past decisions
- Learning from user feedback
- Adjusting strategies for similar transactions
- Building a knowledge base
🔑 Key Features
✅ Natural Language Explanations - Understands context like a human
✅ Dynamic Planning - Adapts to your specific situation
✅ Confidence Scoring - Tells you how certain it is
✅ Multi-Service Coordination - Orchestrates 3 microservices
✅ Self-Correction - Learns from mistakes
📊 Example Agent Plan
{
"strategy": "Optimize for grocery rewards with cap monitoring",
"service_calls": [
{"service": "smart_wallet", "priority": 1, "reason": "Get base recommendation"},
{"service": "spend_forecast", "priority": 2, "reason": "Check spending caps"},
{"service": "rewards_rag", "priority": 3, "reason": "Get detailed benefits"}
],
"confidence": 0.92,
"expected_outcome": "Recommend Amex Gold for 4x grocery points"
}
🎓 Powered By
- Model: Claude 3.5 Sonnet (Anthropic)
- Architecture: Autonomous Agent Pattern
- Framework: LangChain + Custom Logic
- Memory: Redis (for learning)
Try it out in the "Get Recommendation" tab! 🚀
About RewardPilot
RewardPilot is an AI-powered credit card recommendation system built using the Model Context Protocol (MCP) architecture.
🏗️ Architecture
- 🎯 Model Context Protocol (MCP) architecture
- 🤖 LLM-powered explanations using Llama 3.2
- 📚 RAG (Retrieval-Augmented Generation) for card benefits
- 📈 ML-based spending forecasts
- 📊 Interactive visualizations
Features
- Smart card recommendations for every purchase
- AI-generated personalized insights
- Visual analytics dashboard
- Conversational AI assistant
- Real-time cap warnings
- Multi-card comparison
The system consists of multiple microservices:
- Smart Wallet - Analyzes transaction context and selects optimal cards
- Rewards-RAG - Retrieves detailed card benefit information using RAG
- Spend-Forecast - Predicts spending patterns and warns about cap risks
- Orchestrator - Coordinates all services for comprehensive recommendations
🎯 How It Works
- Enter Transaction Details - Merchant, amount, category
- AI Analysis - System analyzes your wallet and transaction context
- Get Recommendation - Receive the best card with detailed reasoning
- Maximize Rewards - Earn more points/cashback on every purchase
🔧 Technology Stack
- Backend: FastAPI, Python
- Frontend: Gradio
- AI/ML: RAG (Retrieval-Augmented Generation)
- Architecture: MCP (Model Context Protocol)
- Deployment: Hugging Face Spaces
📚 MCC Categories Supported
- Groceries (5411)
- Restaurants (5812)
- Gas Stations (5541)
- Airlines (3000-3999)
- Hotels (7011)
- Entertainment (7832, 7841)
- And many more...
🎓 Built For
MCP 1st Birthday Hackathon - Celebrating one year of the Model Context Protocol
👨💻 Developer
Built with ❤️ for the MCP community
Version: 1.0.0
Last Updated: November 2025
API Endpoints
Orchestrator API
Base URL: https://mcp-1st-birthday-rewardpilot-orchestrator.hf.space
POST /recommend
Get comprehensive card recommendation.
Request:
{
"user_id": "u_alice",
"merchant": "Whole Foods",
"mcc": "5411",
"amount_usd": 125.50,
"transaction_date": "2025-01-15"
}
Response:
{
"user_id": "u_alice",
"merchant": "Whole Foods",
"amount_usd": 125.5,
"recommended_card": {
"card_id": "c_amex_gold",
"card_name": "American Express Gold Card",
"reward_rate": 4.0,
"reward_amount": 502.0,
"category": "Groceries",
"reasoning": "Earns 4x points on Groceries"
},
"alternative_cards": ["..."],
"rag_insights": { "...": "..." },
"forecast_warning": { "...": "..." },
"services_used": ["smart_wallet", "rewards_rag", "spend_forecast"],
"final_recommendation": "..."
}
Other Services
- Smart Wallet: https://mcp-1st-birthday-rewardpilot-smart-wallet.hf.space
- Rewards-RAG: https://mcp-1st-birthday-rewardpilot-rewards-rag.hf.space
- Spend-Forecast: https://mcp-1st-birthday-rewardpilot-spend-forecast.hf.space
Interactive Docs
Visit /docs on any service for interactive Swagger UI documentation.
cURL Examples
# Get recommendation
curl -X POST https://mcp-1st-birthday-rewardpilot-orchestrator.hf.space/recommend \
-H "Content-Type: application/json" \
-d '{
"user_id": "u_alice",
"merchant": "Whole Foods",
"mcc": "5411",
"amount_usd": 125.50
}'