Customer Support Bot Example

Build a production-ready customer support chatbot with comprehensive guardrails

This example demonstrates a complete customer support bot implementation using NeMo Guardrails, featuring RAG, multi-layer safety, and conversation management.

Overview

This production-ready customer support bot includes:

• Knowledge base integration for accurate information retrieval
• Multi-layer safety guardrails for input/output validation
• Topic control to keep conversations on-track
• Fact-checking to ensure accurate responses
• PII protection to safeguard customer data
• Conversation flows for common support scenarios

Complete Configuration

1. Main configuration

   config.yml

   colang_version: "2.x"
   
   # Bot instructions and personality
   instructions:
     - type: general
       content: |
         Below is a conversation between a customer and a support bot.
         The bot helps customers with product information, troubleshooting, and account questions.
         The bot is helpful, professional, and accurate.
         If the bot doesn't know the answer, it offers to escalate to a human agent.
   
   # Sample conversation to guide the bot's behavior
   sample_conversation: |
     user "Hi, I need help with my account"
       express greeting and request assistance
     bot express greeting and offer help
       "Hello! I'm here to help you with your account. What can I assist you with today?"
     user "I forgot my password"
       request password reset
     bot provide password reset instructions
       "I can help you reset your password. Please check your email for a password reset link, or visit our website and click 'Forgot Password'. The reset link will be valid for 24 hours."
   
   # Model configuration
   models:
     # Main conversation model
     - type: main
       engine: nim
       model: meta/llama-3.3-70b-instruct
     
     # Safety models
     - type: content_safety
       engine: nim
       model: nvidia/llama-3.1-nemoguard-8b-content-safety
     
     - type: topic_control
       engine: nim  
       model: nvidia/llama-3.1-nemoguard-8b-topic-control
   
   # Rails configuration
   rails:
     config:
       jailbreak_detection:
         nim_base_url: "https://ai.api.nvidia.com"
         nim_server_endpoint: "/v1/security/nvidia/nemoguard-jailbreak-detect"
         api_key_env_var: NVIDIA_API_KEY
   
     dialog:
       single_call:
         enabled: False
   
2. Main flow orchestration

   main.co

   import core
   import llm
   
   flow main
     # Activate LLM for natural conversations
     activate llm continuation
     
     # Activate common support flows
     activate greeting flow
     activate password reset flow
     activate product inquiry flow
     activate escalation flow
   
3. Input and output rails

   rails.co

   import guardrails
   import nemoguardrails.library.content_safety
   import nemoguardrails.library.topic_safety
   import nemoguardrails.library.jailbreak_detection
   
   # Comprehensive input validation
   flow input rails $input_text
       # Check content safety
       content safety check input $model="content_safety"
       
       # Check if on-topic
       topic safety check input $model="topic_control"
       
       # Detect jailbreak attempts
       jailbreak detection model
       
       # Check for PII and warn user
       check customer pii $input_text
   
   # Output validation and fact-checking
   flow output rails $output_text
       # Ensure output is safe
       content safety check output $model="content_safety"
       
       # Fact-check if knowledge base was used
       verify facts if applicable
       
       # Mask any sensitive data
       mask sensitive information
   
   # Custom PII protection for customer data
   flow check customer pii $text
     $has_pii = execute detect_customer_pii(text=$text)
     
     if $has_pii
       bot say "For your security, please don't share sensitive information like credit card numbers, SSN, or full account numbers in chat. I can help you with general questions and guide you to secure channels for sensitive operations."
       abort
   
   # Fact verification for knowledge base responses
   flow verify facts if applicable
     if $used_knowledge_base == True
       $accuracy = execute verify_against_kb
       
       if $accuracy < 0.5
         bot say "I'm not completely certain about that information. Let me connect you with a specialist who can provide accurate details."
         execute escalate_to_human
         stop
   
   # Mask sensitive output data
   flow mask sensitive information
     $output_text = execute mask_sensitive_data(text=$output_text)
   
4. Support conversation flows

   support_flows.co

   # Greeting and initial engagement
   flow greeting flow
     user expressed greeting
     bot express greeting
     bot offer assistance
   
   flow user expressed greeting
     user said "hi" 
       or user said "hello" 
       or user said "hey"
       or user said "good morning"
   
   flow bot express greeting
     bot say "Hello! Welcome to customer support."
   
   flow bot offer assistance
     bot say "How can I help you today?"
   
   # Password reset flow
   flow password reset flow
     user requested password reset
     bot provide password reset steps
     bot ask if resolved
   
   flow user requested password reset
     user said "I forgot my password"
       or user said "reset password"
       or user said "can't login"
   
   flow bot provide password reset steps
     bot say "I can help you reset your password. Here's what to do:"
     bot say "1. Go to our login page"
     bot say "2. Click 'Forgot Password'"
     bot say "3. Enter your email address"
     bot say "4. Check your email for the reset link (valid for 24 hours)"
   
   # Product inquiry with RAG
   flow product inquiry flow
     user asked product question
     $answer = execute retrieve_product_info
     $used_knowledge_base = True
     bot $answer
   
   flow user asked product question
     user said something about "product"
       or user said something about "feature"
       or user said something about "pricing"
       or user said something about "specifications"
   
   # Escalation to human agent
   flow escalation flow
     user requested human agent
       or user expressed frustration
     bot acknowledge escalation
     execute escalate_to_human
   
   flow user requested human agent
     user said "speak to a person"
       or user said "talk to human"
       or user said "transfer to agent"
   
   flow user expressed frustration
     user said "this isn't helping"
       or user said "you're not helpful"
       or user said "I want to speak to someone else"
   
   flow bot acknowledge escalation
     bot say "I understand. Let me connect you with one of our support specialists who can better assist you."
   
5. Topic control and boundaries

   topics.co

   # Define allowed topics
   define user ask about product
     "What features does the product have?"
     "How much does it cost?"
     "What are the specifications?"
   
   define user ask about account
     "How do I reset my password?"
     "How do I update my billing information?"
     "How do I close my account?"
   
   define user ask about support
     "What are your support hours?"
     "How do I contact support?"
     "Do you have phone support?"
   
   # Define disallowed topics
   define user ask off topic question
     "What's the weather?"
     "Tell me a joke"
     "What stocks should I buy?"
     "How do I cook pasta?"
   
   define user ask for competitor info
     "How do you compare to [competitor]?"
     "Should I use your product or [competitor]?"
   
   # Refusal responses
   define bot refuse off topic
     "I'm here to help with product and account questions. I can't assist with that topic."
   
   define bot redirect competitor question
     "I can tell you about our products and features. I'd be happy to explain what makes our solution valuable for your needs."
   
   # Flows for topic control
   define flow
     user ask off topic question
     bot refuse off topic
   
   define flow
     user ask for competitor info
     bot redirect competitor question
   
6. Custom actions for support operations

   config.py

   from nemoguardrails import LLMRails
   from nemoguardrails.actions.actions import ActionResult
   from nemoguardrails.kb.kb import KnowledgeBase
   from langchain_core.prompts import PromptTemplate
   import re
   import logging
   
   logger = logging.getLogger(__name__)
   
   async def retrieve_product_info(context: dict, kb: KnowledgeBase) -> ActionResult:
       """Retrieve product information from knowledge base."""
       user_message = context.get("last_user_message")
       
       # Search knowledge base
       chunks = await kb.search_relevant_chunks(user_message)
       
       if not chunks:
           return ActionResult(
               return_value="I don't have that information in my knowledge base. Let me connect you with a specialist.",
               context_updates={"should_escalate": True}
           )
       
       # Format context
       context_text = "\n".join([chunk["body"] for chunk in chunks])
       
       # Prepare response with fact-checking context
       return ActionResult(
           return_value=context_text,
           context_updates={
               "knowledge_base_chunks": context_text,
               "used_knowledge_base": True
           }
       )
   
   async def detect_customer_pii(context: dict, text: str) -> ActionResult:
       """Detect customer PII in input."""
       pii_patterns = {
           'credit_card': r'\b\d{4}[\s-]?\d{4}[\s-]?\d{4}[\s-]?\d{4}\b',
           'ssn': r'\b\d{3}-\d{2}-\d{4}\b',
           'email': r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b',
           'phone': r'\b\d{3}[-.]?\d{3}[-.]?\d{4}\b',
           'account_number': r'\b[Aa]ccount\s*#?\s*\d{6,}\b'
       }
       
       for pii_type, pattern in pii_patterns.items():
           if re.search(pattern, text):
               logger.warning(f"PII detected: {pii_type}")
               return ActionResult(
                   return_value=True,
                   context_updates={"pii_detected": pii_type}
               )
       
       return ActionResult(return_value=False)
   
   async def mask_sensitive_data(context: dict, text: str) -> ActionResult:
       """Mask sensitive data in bot output."""
       # Mask credit cards
       text = re.sub(
           r'\b\d{4}[\s-]?\d{4}[\s-]?\d{4}[\s-]?(\d{4})\b',
           r'****-****-****-\1',
           text
       )
       
       # Mask account numbers (keep last 4 digits)
       text = re.sub(
           r'\b([Aa]ccount\s*#?\s*)\d+?(\d{4})\b',
           r'\1****\2',
           text
       )
       
       # Mask emails
       text = re.sub(
           r'\b([A-Za-z0-9._%+-]+)@([A-Za-z0-9.-]+\.[A-Z|a-z]{2,})\b',
           r'***@\2',
           text
       )
       
       return ActionResult(return_value=text)
   
   async def verify_against_kb(context: dict) -> ActionResult:
       """Verify response accuracy against knowledge base."""
       # Simple verification - in production, use semantic similarity
       kb_chunks = context.get("knowledge_base_chunks", "")
       bot_response = context.get("bot_message", "")
       
       if not kb_chunks or not bot_response:
           return ActionResult(return_value=0.5)
       
       # Simple overlap check (replace with semantic similarity in production)
       overlap = len(set(bot_response.split()) & set(kb_chunks.split()))
       total = len(set(bot_response.split()))
       accuracy = overlap / total if total > 0 else 0.0
       
       return ActionResult(return_value=accuracy)
   
   async def escalate_to_human(context: dict) -> ActionResult:
       """Escalate conversation to human agent."""
       logger.info("Escalating to human agent")
       
       # In production, integrate with ticketing system
       ticket_id = f"TICKET-{hash(str(context))}"
       
       return ActionResult(
           return_value=ticket_id,
           context_updates={
               "escalated": True,
               "ticket_id": ticket_id
           }
       )
   
   def init(app: LLMRails):
       """Register all custom actions."""
       app.register_action(retrieve_product_info, "retrieve_product_info")
       app.register_action(detect_customer_pii, "detect_customer_pii")
       app.register_action(mask_sensitive_data, "mask_sensitive_data")
       app.register_action(verify_against_kb, "verify_against_kb")
       app.register_action(escalate_to_human, "escalate_to_human")
   
7. Add knowledge base

   Create your product documentation in the kb/ folder:

   kb/product-info.md

   # Product Information
   
   ## Features
   
   Our product offers:
   - Advanced analytics and reporting
   - Real-time collaboration
   - Enterprise-grade security
   - 24/7 customer support
   - API access for integrations
   
   ## Pricing
   
   - Starter Plan: $29/month (up to 5 users)
   - Professional Plan: $99/month (up to 25 users)
   - Enterprise Plan: Custom pricing (unlimited users)
   
   ## Support Hours
   
   - Email Support: 24/7
   - Chat Support: Monday-Friday, 9 AM - 6 PM EST
   - Phone Support: Enterprise customers only
   

Usage

Python API

from nemoguardrails import LLMRails, RailsConfig

config = RailsConfig.from_path("./config")
rails = LLMRails(config)

# Example support conversation
conversation = [
    {"role": "user", "content": "Hi, I need help"},
    {"role": "assistant", "content": "Hello! Welcome to customer support. How can I help you today?"},
    {"role": "user", "content": "What features does your product have?"},
]

response = rails.generate(messages=conversation)
print(response["content"])

Conversation Examples

1. Normal product inquiry

   User: Hi, what features does your product have?
   
   Bot: Hello! Welcome to customer support. Our product offers:
        - Advanced analytics and reporting
        - Real-time collaboration  
        - Enterprise-grade security
        - 24/7 customer support
        - API access for integrations
        
        Would you like to know more about any specific feature?
   
2. Password reset

   User: I forgot my password
   
   Bot: I can help you reset your password. Here's what to do:
        1. Go to our login page
        2. Click 'Forgot Password'
        3. Enter your email address
        4. Check your email for the reset link (valid for 24 hours)
        
        Did this help resolve your issue?
   
3. PII detection

   User: My credit card number is 4532-1234-5678-9010
   
   Bot: For your security, please don't share sensitive information like 
        credit card numbers, SSN, or full account numbers in chat. I can help 
        you with general questions and guide you to secure channels for 
        sensitive operations.
   
4. Escalation

   User: This isn't helping, I want to talk to a person
   
   Bot: I understand. Let me connect you with one of our support specialists 
        who can better assist you.
        
        [Creates ticket TICKET-12345 and initiates handoff]
   

Project Structure

customer-support-bot/
├── config.yml              # Main configuration
├── config.py               # Custom actions
├── main.co                 # Main flow orchestration
├── rails.co                # Input/output rails
├── support_flows.co        # Support conversation flows
├── topics.co               # Topic control
└── kb/                     # Knowledge base
    ├── product-info.md
    ├── troubleshooting.md
    └── faq.md

Production Deployment

For production use:

1. Use NIMs for models: Deploy NeMo Inference Microservices for better performance
2. Enable logging: Track all conversations and rail activations
3. Monitor metrics: Track escalation rates, response times, accuracy
4. A/B testing: Test different prompts and thresholds
5. Human review: Regularly review flagged conversations
6. Update KB: Keep knowledge base current with product changes

Related Examples

• Basic RAG - Knowledge base integration
• Multi-Rail Configuration - Comprehensive safety
• Chatbot Assistant - Conversational flows