What It Demonstrates
This example shows:- ✅ Real-world use case implementation
- ✅ FAQ search tools
- ✅ Ticket management tools
- ✅ Account management tools
- ✅ Structured responses and confirmations
- ✅ Production-like patterns
Prerequisites
- Python 3.8 or higher
- Kuralit SDK installed:
pip install kuralit - API keys:
DEEPGRAM_API_KEY- Deepgram STT API keyGEMINI_API_KEY- Google Gemini LLM API keyKURALIT_API_KEY- Server API key (defaults to “demo-api-key”)
Features
Your customer support AI Voice Agent can:- 🔍 FAQ Search - Search knowledge base for common questions
- 🎫 Ticket Management - Create, view, update, and list support tickets
- 👤 Account Management - Get account and order information
- 💰 Actions - Process refunds (with confirmation), escalate tickets
Step-by-Step Explanation
Step 1: Define Support Tools
Create tools for customer support operations:Step 2: Create Support Toolkits
Step 3: Configure Agent for Support
Full Code Structure
The example includes:- FAQ Database - In-memory knowledge base
- Ticket System - Create, view, update tickets
- Account System - Customer and order information
- Support Tools - FAQ search, ticket management, account lookup
- Agent Configuration - Customer support personality and instructions
How to Run
Expected Output
Example Interactions
- “How do I reset my password?” → Uses
search_faqtool - “I want to return my order” → Uses
search_faqorcreate_tickettool - “What’s the status of ticket 12345?” → Uses
get_ticket_statustool - “I need a refund for order ABC123” → Uses
process_refundtool (with confirmation)
Key Concepts
Structured Responses
Customer support agents need structured responses:Confirmation Patterns
For destructive actions, require confirmation:Professional Instructions
Agent instructions set the tone:Production Considerations
In production, you would:- Connect to real databases - Replace in-memory storage
- Integrate with ticketing systems - Use actual ticket APIs
- Add authentication - Verify customer identity
- Implement confirmation flows - For refunds and other actions
- Add logging and monitoring - Track support interactions
Next Steps
- Voice Assistant → - Multiple toolkits example
- Tools → - Learn about tools
- Agents → - Building AI Voice Agents

