WhatsApp Customer Engagement Workflow

Automated WhatsApp customer engagement with AI-powered intent analysis and response generation

Back

Workflow Information

ID: whatsapp_customer_engagement_workflow

Namespace: default

Version: 1.0

Created: 2025-07-01

Updated: 2025-07-01

Tasks: 17

Quick Actions

Manage Secrets

Inputs

Name	Type	Required	Default
`message_id`	string	Optional	`wamid.HBgLMTIzNDU2Nzg5MDE...`
`sender_phone`	string	Optional	`+1234567890`

Outputs

Name	Type	Source
`escalation_details`	object	Human escalation details if applicable
`message_processing`	object	WhatsApp message processing results
`conversation_record`	object	Complete conversation log and follow-up schedule
`customer_engagement`	object	Customer engagement outcome
`intent_analysis_result`	object	AI intent analysis and classification

Tasks

get_whatsapp_message

script

Retrieve incoming WhatsApp message details

Task Outputs: {'name': 'message_data', 'value': 'WhatsApp message retrieved'}

get_customer_context_from_crm

script

Retrieve customer information and history from CRM

Python Script:

#!/usr/bin/env python3
import json

print("🔍 Retrieving customer context from CRM...")

phone_number = "+1234567890"

# Mock CRM customer context
customer_context = {
    "customer_found": True,
    "customer_id": "CUST_789",
    "customer_name": "John Smith",
    "company": "TechCorp Industries",
    "industry": "Technology",
    "company_size": "500-1000",
    "customer_tier": "enterprise",
    "account_status": "active_prospect",
    "lead_source": "website_form",
    "assigned_officer": "OFF_001",
    "interaction_history": [
        {
            "date": "2025-06-20T14:30:00Z",
            "type": "email",
            "direction": "inbound",
            "subject": "Initial inquiry about CRM solutions",
            "outcome": "information_sent"
        },
        {
            "date": "2025-06-22T10:15:00Z",
            "type": "phone_call",
            "direction": "outbound",
            "duration_minutes": 15,
            "outcome": "voicemail_left"
        }
    ],
    "current_deals": [
        {
            "deal_id": "DEAL_2025_001234",
            "deal_name": "TechCorp CRM Implementation",
            "stage": "qualified",
            "value": 125000.00,
            "probability": 0.65,
            "last_activity": "2025-06-22T10:15:00Z"
        }
    ],
    "preferences": {
        "preferred_contact_method": "whatsapp",
        "contact_time_preference": "business_hours",
        "communication_style": "professional_direct",
        "language": "en"
    },
    "previous_inquiries": [
        {
            "date": "2025-06-20",
            "topic": "CRM pricing for enterprise",
            "status": "pending_follow_up"
        }
    ]
}

print(f"✅ Customer context retrieved for {customer_context['customer_name']}")
print(f"   Company: {customer_context['company']}")
print(f"   Customer tier: {customer_context['customer_tier']}")
print(f"   Active deals: {len(customer_context['current_deals'])}")
print(f"   Previous interactions: {len(customer_context['interaction_history'])}")

print(f"__OUTPUTS__ {json.dumps(customer_context)}")

Task Outputs: {'name': 'customer_context', 'value': 'Customer context retrieved from CRM'}

get_conversation_history

script

Retrieve WhatsApp conversation history for context

Python Script:

#!/usr/bin/env python3
import json
from datetime import datetime
from datetime import timedelta

print("💬 Retrieving conversation history...")

phone_number = "+1234567890"

# Mock conversation history
conversation_history = {
    "conversation_id": "conv_12345",
    "total_messages": 3,
    "conversation_started": "2025-06-20T14:30:00Z",
    "last_activity": "2025-06-25T16:30:00Z",
    "conversation_stage": "initial_inquiry",
    "messages": [
        {
            "id": "msg_001",
            "timestamp": "2025-06-20T14:30:00Z",
            "from": "+1234567890",
            "type": "text",
            "text": "Hello, I'm looking for a CRM solution for our company",
            "direction": "inbound"
        },
        {
            "id": "msg_002",
            "timestamp": "2025-06-20T14:35:00Z",
            "from": "business_number",
            "type": "text",
            "text": "Hi John! Thanks for reaching out. I'd be happy to help you find the right CRM solution. Can you tell me more about your company size and specific needs?",
            "direction": "outbound"
        },
        {
            "id": "msg_003",
            "timestamp": "2025-06-25T16:30:00Z",
            "from": "+1234567890",
            "type": "text",
            "text": "Hi, I'm interested in your CRM solution for my company. We have about 500 employees and need something that can scale with our growth. Can you tell me about pricing and implementation timeline?",
            "direction": "inbound"
        }
    ],
    "conversation_analytics": {
        "customer_messages": 2,
        "business_messages": 1,
        "avg_response_time": "5 minutes",
        "engagement_level": "high",
        "sentiment_progression": ["neutral", "positive", "positive"],
        "topics_discussed": ["company_size", "scalability", "pricing", "implementation"]
    },
    "context_summary": {
        "customer_needs": ["scalable_crm", "enterprise_solution", "implementation_support"],
        "information_provided": ["initial_greeting", "needs_assessment"],
        "next_expected_topics": ["pricing_details", "feature_overview", "demo_scheduling"]
    }
}

print(f"✅ Conversation history retrieved")
print(f"   Total messages: {conversation_history['total_messages']}")
print(f"   Engagement level: {conversation_history['conversation_analytics']['engagement_level']}")
print(f"   Current stage: {conversation_history['conversation_stage']}")

print(f"__OUTPUTS__ {json.dumps(conversation_history)}")

Task Outputs: {'name': 'conversation_history', 'value': 'Conversation history retrieved'}

get_product_catalog_from_dynamics

script

Retrieve relevant product information from Dynamics 365

Python Script:

#!/usr/bin/env python3
import json

print("📦 Retrieving product catalog from Dynamics...")

# Mock product catalog
product_catalog = {
    "products": [
        {
            "product_id": "CRM_ENT_001",
            "name": "CRM Enterprise Edition",
            "category": "crm_software",
            "description": "Complete CRM solution for enterprise organizations with advanced analytics and customization",
            "target_company_size": "500+",
            "pricing": {
                "base_price": 299.99,
                "currency": "USD",
                "billing_cycle": "monthly",
                "pricing_tiers": [
                    {
                        "tier": "500-1000 users",
                        "price_per_user": 199.99,
                        "setup_fee": 15000.00,
                        "annual_discount": 0.15
                    },
                    {
                        "tier": "1000+ users",
                        "price_per_user": 179.99,
                        "setup_fee": 25000.00,
                        "annual_discount": 0.20
                    }
                ]
            },
            "key_features": [
                "Unlimited users",
                "Advanced analytics and reporting",
                "Custom workflows",
                "API integrations",
                "24/7 enterprise support",
                "Multi-tenant architecture"
            ],
            "implementation": {
                "typical_timeline": "8-12 weeks",
                "implementation_cost": "25% of license cost",
                "training_included": True,
                "data_migration": True
            },
            "competitive_advantages": [
                "Superior scalability",
                "Industry-leading uptime (99.9%)",
                "Advanced AI features",
                "Comprehensive API ecosystem"
            ]
        },
        {
            "product_id": "CRM_PRO_002",
            "name": "CRM Professional",
            "category": "crm_software",
            "description": "Professional CRM solution for growing businesses",
            "target_company_size": "100-500",
            "pricing": {
                "base_price": 149.99,
                "currency": "USD",
                "billing_cycle": "monthly"
            },
            "key_features": [
                "Up to 500 users",
                "Standard reporting",
                "Email integration",
                "Mobile app"
            ]
        }
    ],
    "recommendations": {
        "best_match": "CRM_ENT_001",
        "match_reasons": [
            "Company size (500 employees) fits enterprise tier",
            "Scalability requirements align with enterprise features",
            "Growth trajectory suggests need for advanced capabilities"
        ],
        "alternative_options": ["CRM_PRO_002"],
        "upsell_opportunities": [
            "Advanced Analytics Module",
            "AI Automation Add-on"
        ]
    }
}

recommended_product = product_catalog['recommendations']['best_match']
main_product = next(p for p in product_catalog['products'] if p['product_id'] == recommended_product)

print(f"✅ Product catalog retrieved")
print(f"   Total products: {len(product_catalog['products'])}")
print(f"   Recommended: {main_product['name']}")
print(f"   Target size: {main_product['target_company_size']}")

print(f"__OUTPUTS__ {json.dumps(product_catalog)}")

Task Outputs: {'name': 'product_catalog', 'value': 'Product catalog retrieved from Dynamics'}

analyze_message_intent

script

AI-powered analysis of customer message intent and sentiment

Python Script:

#!/usr/bin/env python3
import json

print("🤖 Analyzing message intent...")

message_content = "Hi, I'm interested in your CRM solution for my company. We have about 500 employees and need something that can scale with our growth. Can you tell me about pricing and implementation timeline?"

# Mock AI intent analysis
intent_analysis = {
    "primary_intent": "product_inquiry",
    "confidence_score": 0.94,
    "intent_hierarchy": [
        {"intent": "product_inquiry", "confidence": 0.94},
        {"intent": "pricing_request", "confidence": 0.87},
        {"intent": "implementation_question", "confidence": 0.76},
        {"intent": "scalability_concern", "confidence": 0.69}
    ],
    "sentiment_analysis": {
        "overall_sentiment": "positive",
        "sentiment_score": 0.78,
        "emotional_indicators": ["interest", "professional", "forward_thinking"],
        "tone_analysis": "business_focused",
        "urgency_level": "medium"
    },
    "entity_extraction": {
        "company_size": "500 employees",
        "solution_type": "CRM solution",
        "key_requirements": ["scalability", "growth_support"],
        "information_needs": ["pricing", "implementation_timeline"],
        "decision_stage": "evaluation",
        "budget_indicators": ["established_company", "500_employees"]
    },
    "buying_signals": {
        "signals_detected": [
            "specific_company_size_mentioned",
            "scalability_requirements_defined",
            "implementation_timeline_inquiry",
            "pricing_information_requested"
        ],
        "buying_stage": "consideration",
        "urgency_score": 0.65,
        "decision_authority": "likely_influencer",
        "budget_probability": "high"
    },
    "conversation_context": {
        "follow_up_to_previous": True,
        "information_gap": ["detailed_pricing", "implementation_process"],
        "customer_education_level": "informed",
        "technical_sophistication": "medium"
    }
}

print(f"✅ Intent analysis completed")
print(f"   Primary intent: {intent_analysis['primary_intent']} ({intent_analysis['confidence_score']:.2f})")
print(f"   Sentiment: {intent_analysis['sentiment_analysis']['overall_sentiment']} ({intent_analysis['sentiment_analysis']['sentiment_score']:.2f})")
print(f"   Buying stage: {intent_analysis['buying_signals']['buying_stage']}")
print(f"   Buying signals: {len(intent_analysis['buying_signals']['signals_detected'])}")

print(f"__OUTPUTS__ {json.dumps(intent_analysis)}")

Task Outputs: {'name': 'intent_analysis', 'value': 'Message intent analyzed'}

get_product_info

script

Retrieve specific product information for inquiry intent

Python Script:

#!/usr/bin/env python3
import json

print("📋 Retrieving product information for inquiry...")

# Mock detailed product info for response
product_info = {
    "product_focus": "CRM Enterprise Edition",
    "relevant_features": [
        {
            "feature": "Unlimited Users",
            "benefit": "Perfect for your 500+ employee company with room to grow",
            "relevance": "high"
        },
        {
            "feature": "Advanced Scalability",
            "benefit": "Built to handle enterprise growth without performance impact",
            "relevance": "high"
        },
        {
            "feature": "Custom Workflows",
            "benefit": "Adapt the system to your unique business processes",
            "relevance": "medium"
        }
    ],
    "pricing_summary": {
        "recommended_tier": "500-1000 users",
        "price_per_user": 199.99,
        "estimated_monthly_cost": 99995.00,
        "setup_fee": 15000.00,
        "annual_savings": "15% discount available",
        "roi_estimate": "Typically 300% ROI within 18 months"
    },
    "implementation_details": {
        "timeline": "8-12 weeks for full implementation",
        "phases": [
            "Planning and setup (2 weeks)",
            "Data migration (3-4 weeks)",
            "User training (2 weeks)",
            "Go-live and support (1-2 weeks)"
        ],
        "support_included": "Dedicated implementation manager and 24/7 support",
        "training": "Comprehensive user training for all 500 employees"
    },
    "next_steps": [
        "Schedule detailed demo",
        "Provide customized pricing proposal",
        "Connect with implementation specialist"
    ]
}

print(f"✅ Product information compiled")
print(f"   Focus product: {product_info['product_focus']}")
print(f"   Estimated monthly cost: ${product_info['pricing_summary']['estimated_monthly_cost']:,.2f}")
print(f"   Implementation timeline: {product_info['implementation_details']['timeline']}")

print(f"__OUTPUTS__ {json.dumps(product_info)}")

Task Outputs: {'name': 'product_info', 'value': 'Product information retrieved'}

get_support_context

script

Retrieve support context for complaint intent

Task Outputs: {'name': 'support_context', 'value': 'Support context retrieved'}

get_order_details

script

Retrieve order information for order intent

Task Outputs: {'name': 'order_details', 'value': 'Order details retrieved'}

get_troubleshooting

script

Retrieve troubleshooting information for support intent

Task Outputs: {'name': 'troubleshooting_info', 'value': 'Troubleshooting information retrieved'}

generate_response

script

AI-powered response generation based on intent and context

Python Script:

#!/usr/bin/env python3
import json

print("✍️ Generating AI response...")

# Mock AI response generation based on product inquiry intent
generated_response = {
    "response_type": "product_inquiry_response",
    "tone": "professional_helpful",
    "personalization_level": "high",
    "message_text": "Hi John! Great to hear from you again. For TechCorp with 500 employees, our CRM Enterprise Edition would be perfect - it's designed specifically for companies your size with unlimited users and advanced scalability features.\n\nHere's what you're looking at:\n💰 Pricing: $199.99/user/month (about $100K/month for 500 users)\n⏱️ Implementation: 8-12 weeks with full training included\n📈 ROI: Most clients see 300% ROI within 18 months\n\nThe system grows with you - no performance issues as you scale beyond 500 employees. Would you like me to schedule a personalized demo to show you exactly how it would work for TechCorp?",
    "key_elements": [
        "Personal greeting using name and company",
        "Specific product recommendation with reasoning",
        "Clear pricing information",
        "Implementation timeline",
        "ROI value proposition",
        "Scalability assurance",
        "Clear call-to-action"
    ],
    "call_to_action": {
        "primary": "Schedule personalized demo",
        "secondary": "Request detailed pricing proposal",
        "urgency": "medium"
    },
    "follow_up_suggestions": [
        "Demo scheduling",
        "Detailed proposal preparation",
        "Implementation timeline discussion"
    ],
    "estimated_response_effectiveness": 0.87,
    "expected_customer_actions": [
        "Request demo",
        "Ask follow-up questions",
        "Request proposal"
    ]
}

print(f"✅ Response generated")
print(f"   Response type: {generated_response['response_type']}")
print(f"   Tone: {generated_response['tone']}")
print(f"   Effectiveness estimate: {generated_response['estimated_response_effectiveness']:.2f}")
print(f"   Message length: {len(generated_response['message_text'])} characters")

print(f"__OUTPUTS__ {json.dumps(generated_response)}")

Task Outputs: {'name': 'generated_response', 'value': 'AI response generated'}

determine_escalation_need

script

Assess if human escalation is needed

Python Script:

#!/usr/bin/env python3
import json

print("🎯 Determining escalation need...")

# Mock escalation assessment
escalation_assessment = {
    "needs_human_escalation": False,
    "escalation_confidence": 0.85,
    "assessment_factors": [
        {
            "factor": "message_complexity",
            "score": 0.3,
            "threshold": 0.7,
            "status": "below_threshold"
        },
        {
            "factor": "customer_sentiment",
            "score": 0.78,
            "threshold": 0.3,
            "status": "positive"
        },
        {
            "factor": "technical_complexity",
            "score": 0.2,
            "threshold": 0.6,
            "status": "low_complexity"
        },
        {
            "factor": "deal_value",
            "score": 0.8,
            "threshold": 0.7,
            "status": "high_value"
        },
        {
            "factor": "conversation_duration",
            "score": 0.2,
            "threshold": 0.8,
            "status": "short_conversation"
        }
    ],
    "escalation_triggers": {
        "high_value_deal": True,
        "enterprise_customer": True,
        "complex_technical_query": False,
        "customer_frustration": False,
        "pricing_negotiation": False
    },
    "ai_capability_assessment": {
        "can_handle_query": True,
        "information_complete": True,
        "response_quality_sufficient": True,
        "follow_up_manageable": True
    },
    "recommendation": "ai_handled",
    "escalation_reason": None,
    "monitoring_required": True,
    "escalation_threshold_met": False
}

escalation_needed = escalation_assessment["needs_human_escalation"]

if escalation_needed:
    print(f"🚨 Human escalation required")
    print(f"   Reason: {escalation_assessment.get('escalation_reason', 'Multiple factors')}")
else:
    print(f"✅ AI can handle this query")
    print(f"   Confidence: {escalation_assessment['escalation_confidence']:.2f}")

print(f"   High value deal detected: {escalation_assessment['escalation_triggers']['high_value_deal']}")
print(f"   Monitoring required: {escalation_assessment['monitoring_required']}")

print(f"__OUTPUTS__ {json.dumps(escalation_assessment)}")

Task Outputs: {'name': 'escalation_assessment', 'value': 'Escalation need determined'}

send_whatsapp_response

script

Send AI-generated response via WhatsApp

Python Script:

#!/usr/bin/env python3
import json
from datetime import datetime

print("📤 Sending WhatsApp response...")

recipient_phone = "+1234567890"
message_content = "Hi John! Great to hear from you again. For TechCorp with 500 employees, our CRM Enterprise Edition would be perfect - it's designed specifically for companies your size with unlimited users and advanced scalability features.\n\nHere's what you're looking at:\n💰 Pricing: $199.99/user/month (about $100K/month for 500 users)\n⏱️ Implementation: 8-12 weeks with full training included\n📈 ROI: Most clients see 300% ROI within 18 months\n\nThe system grows with you - no performance issues as you scale beyond 500 employees. Would you like me to schedule a personalized demo to show you exactly how it would work for TechCorp?"

# Mock WhatsApp response sending
response_result = {
    "message_id": "wamid.HBgLMTIzNDU2Nzg5MDE_response...",
    "recipient": recipient_phone,
    "recipient_name": "John Smith",
    "message_status": "sent",
    "sent_at": datetime.now().isoformat(),
    "delivery_status": "delivered",
    "message_type": "text",
    "character_count": len(message_content),
    "estimated_delivery": "immediate",
    "conversation_id": "conv_12345",
    "ai_handled": True,
    "response_time_seconds": 8.5,
    "campaign_tracking": {
        "campaign_type": "ai_customer_engagement",
        "intent_addressed": "product_inquiry",
        "personalization_level": "high",
        "expected_engagement": "high"
    }
}

print(f"✅ WhatsApp response sent to {response_result['recipient_name']}")
print(f"   Message ID: {response_result['message_id']}")
print(f"   Status: {response_result['message_status']}")
print(f"   Response time: {response_result['response_time_seconds']} seconds")
print(f"   Character count: {response_result['character_count']}")

print(f"__OUTPUTS__ {json.dumps(response_result)}")

Task Outputs: {'name': 'whatsapp_response_sent', 'value': 'WhatsApp response sent'}

escalate_to_human

script

Escalate conversation to human agent

Python Script:

#!/usr/bin/env python3
import json
from datetime import datetime

print("🚨 Escalating to human agent...")

# Mock human escalation
escalation_result = {
    "escalation_id": "ESC_2025_WA_001234",
    "customer_phone": "+1234567890",
    "customer_name": "John Smith",
    "escalation_reason": "high_value_enterprise_inquiry",
    "urgency_level": "high",
    "escalated_at": datetime.now().isoformat(),
    "assigned_agent": "AGENT_001",
    "agent_name": "Sarah Johnson",
    "estimated_response_time": "15 minutes",
    "escalation_context": {
        "conversation_summary": "Enterprise customer inquiry about CRM for 500 employees, pricing and implementation questions",
        "customer_tier": "enterprise",
        "deal_potential": 125000.00,
        "previous_interactions": 3,
        "ai_assessment": "high_value_opportunity_requiring_personal_attention"
    },
    "handover_message": "Hi John! I'm connecting you with Sarah Johnson, our enterprise specialist, who can provide detailed pricing and implementation planning for TechCorp. She'll be with you shortly!",
    "agent_briefing": {
        "customer_background": "Existing prospect, 500-employee tech company",
        "current_need": "CRM Enterprise pricing and implementation timeline",
        "recommended_approach": "consultative_sales_focus_on_scalability_and_roi",
        "next_actions": ["detailed_needs_assessment", "custom_proposal_preparation", "demo_scheduling"]
    }
}

print(f"✅ Escalated to {escalation_result['agent_name']}")
print(f"   Escalation ID: {escalation_result['escalation_id']}")
print(f"   Urgency: {escalation_result['urgency_level']}")
print(f"   ETA: {escalation_result['estimated_response_time']}")

print(f"__OUTPUTS__ {json.dumps(escalation_result)}")

Task Outputs: {'name': 'escalation_result', 'value': 'Conversation escalated to human'}

update_conversation_log

script

Log interaction details in CRM system

Python Script:

#!/usr/bin/env python3
import json
from datetime import datetime

print("📝 Updating conversation log...")

# Mock conversation logging
conversation_log = {
    "log_id": "LOG_2025_WA_001234",
    "customer_id": "CUST_789",
    "interaction_type": "whatsapp",
    "interaction_date": datetime.now().isoformat(),
    "direction": "inbound",
    "channel": "whatsapp",
    "duration_seconds": 8.5,
    "ai_handled": True,
    "escalated": False,
    "interaction_summary": {
        "customer_message": "CRM inquiry for 500-employee company, pricing and implementation questions",
        "intent_classified": "product_inquiry",
        "response_provided": "Detailed CRM Enterprise information with pricing, timeline, and demo offer",
        "outcome": "information_provided",
        "next_expected_action": "demo_request_or_follow_up_questions"
    },
    "sentiment_analysis": {
        "customer_sentiment": "positive",
        "satisfaction_predicted": 0.85,
        "engagement_level": "high"
    },
    "business_impact": {
        "lead_score_change": "+5",
        "deal_progression": "information_stage_to_consideration",
        "opportunity_value": 125000.00,
        "conversion_probability": 0.68
    },
    "ai_performance": {
        "response_time": 8.5,
        "intent_accuracy": 0.94,
        "response_quality_score": 0.87,
        "escalation_avoidance": True
    },
    "follow_up_actions": [
        {
            "action": "monitor_for_response",
            "timeline": "24_hours",
            "automated": True
        },
        {
            "action": "prepare_demo_materials",
            "timeline": "if_requested",
            "automated": False
        }
    ]
}

print(f"✅ Conversation logged")
print(f"   Log ID: {conversation_log['log_id']}")
print(f"   AI handled: {conversation_log['ai_handled']}")
print(f"   Customer sentiment: {conversation_log['sentiment_analysis']['customer_sentiment']}")
print(f"   Opportunity value: ${conversation_log['business_impact']['opportunity_value']:,.2f}")

print(f"__OUTPUTS__ {json.dumps(conversation_log)}")

Task Outputs: {'name': 'conversation_log', 'value': 'Conversation logged in CRM'}

check_new_inquiry

script

Determine if this creates a new inquiry/opportunity

Task Outputs: {'name': 'inquiry_check_result', 'value': 'New inquiry check completed'}

create_crm_inquiry

script

Create new inquiry record in CRM

Python Script:

#!/usr/bin/env python3
import json
from datetime import datetime

print("📋 Creating new CRM inquiry...")

# Mock CRM inquiry creation
crm_inquiry = {
    "inquiry_id": "INQ_2025_005678",
    "customer_id": "CUST_789",
    "customer_phone": "+1234567890",
    "customer_email": "john.smith@techcorp.com",
    "inquiry_type": "product_interest",
    "source": "whatsapp",
    "priority": "high",
    "subject": "CRM Enterprise Solution for 500 Employees",
    "description": "Customer interested in CRM Enterprise Edition for 500-employee technology company. Specific questions about pricing ($199.99/user/month tier) and implementation timeline (8-12 weeks). Company name: TechCorp Industries.",
    "products_of_interest": ["CRM_ENT_001"],
    "customer_context": {
        "company_size": "500",
        "industry": "technology",
        "current_solution": "unknown",
        "scalability_important": True,
        "budget_range": "enterprise_level"
    },
    "ai_analysis": {
        "intent_confidence": 0.94,
        "urgency_score": 0.65,
        "budget_indicators": ["enterprise", "500_employees", "scalability_focus"],
        "buying_stage": "consideration",
        "conversion_probability": 0.68
    },
    "created_at": datetime.now().isoformat(),
    "assigned_to": "TEAM_ENTERPRISE_SALES",
    "estimated_response_time": "2 hours",
    "follow_up_sequence": [
        {
            "step": 1,
            "action": "send_detailed_proposal",
            "scheduled_for": (datetime.now()).isoformat(),
            "owner": "sales_team"
        },
        {
            "step": 2,
            "action": "schedule_demo_call",
            "scheduled_for": "on_customer_request",
            "owner": "demo_specialist"
        }
    ],
    "related_records": {
        "customer_id": "CUST_789",
        "existing_deal": "DEAL_2025_001234",
        "conversation_log": "LOG_2025_WA_001234"
    }
}

print(f"✅ CRM inquiry created")
print(f"   Inquiry ID: {crm_inquiry['inquiry_id']}")
print(f"   Priority: {crm_inquiry['priority']}")
print(f"   Subject: {crm_inquiry['subject']}")
print(f"   Assigned to: {crm_inquiry['assigned_to']}")
print(f"   Conversion probability: {crm_inquiry['ai_analysis']['conversion_probability']:.2f}")

print(f"__OUTPUTS__ {json.dumps(crm_inquiry)}")

Task Outputs: {'name': 'crm_inquiry_created', 'value': 'CRM inquiry created'}

schedule_follow_up

script

Schedule appropriate follow-up actions

Python Script:

#!/usr/bin/env python3
import json
from datetime import datetime
from datetime import timedelta

print("📅 Scheduling follow-up actions...")

# Mock follow-up scheduling
follow_up_schedule = {
    "follow_up_id": "FOLLOWUP_2025_001234",
    "customer_id": "CUST_789",
    "conversation_id": "conv_12345",
    "follow_up_type": "whatsapp_engagement_follow_up",
    "scheduled_actions": [
        {
            "action_id": "ACTION_001",
            "action_type": "response_monitoring",
            "description": "Monitor for customer response to CRM Enterprise information",
            "scheduled_for": datetime.now().isoformat(),
            "duration_hours": 24,
            "automated": True,
            "trigger_condition": "no_customer_response_within_24h"
        },
        {
            "action_id": "ACTION_002",
            "action_type": "proactive_follow_up",
            "description": "Send follow-up message if no response received",
            "scheduled_for": (datetime.now() + timedelta(hours=48)).isoformat(),
            "automated": True,
            "message_template": "demo_offer_follow_up",
            "condition": "no_response_received"
        },
        {
            "action_id": "ACTION_003",
            "action_type": "sales_team_notification",
            "description": "Notify enterprise sales team of high-value opportunity",
            "scheduled_for": (datetime.now() + timedelta(hours=2)).isoformat(),
            "automated": True,
            "recipient": "TEAM_ENTERPRISE_SALES"
        }
    ],
    "escalation_rules": [
        {
            "condition": "no_response_after_72_hours",
            "action": "escalate_to_sales_manager",
            "priority": "medium"
        },
        {
            "condition": "negative_sentiment_detected",
            "action": "immediate_human_intervention",
            "priority": "high"
        }
    ],
    "success_metrics": {
        "target_response_rate": 0.75,
        "target_demo_conversion": 0.40,
        "target_proposal_acceptance": 0.60
    }
}

print(f"✅ Follow-up actions scheduled")
print(f"   Follow-up ID: {follow_up_schedule['follow_up_id']}")
print(f"   Scheduled actions: {len(follow_up_schedule['scheduled_actions'])}")

for action in follow_up_schedule['scheduled_actions']:
    print(f"   • {action['action_type']}: {action['description']}")

print(f"__OUTPUTS__ {json.dumps(follow_up_schedule)}")

Task Outputs: {'name': 'follow_up_scheduled', 'value': 'Follow-up actions scheduled'}

Triggers

Webhook Trigger: WhatsApp Message Received
POST /webhook/whatsapp-message

Manual Trigger: Manual Message Processing

YAML Source

id: whatsapp_customer_engagement_workflow
name: WhatsApp Customer Engagement Workflow
tasks:
- id: get_whatsapp_message
  name: Get WhatsApp Message
  type: script
  script: "#!/usr/bin/env python3\nimport json\nfrom datetime import datetime\n\n\
    print(\"\U0001F4F1 Retrieving WhatsApp message...\")\n\nmessage_id = \"wamid.HBgLMTIzNDU2Nzg5MDE...\"\
    \nsender_phone = \"+1234567890\"\n\n# Mock WhatsApp message data\nmessage_data\
    \ = {\n    \"message_id\": message_id,\n    \"from\": sender_phone,\n    \"timestamp\"\
    : \"1719331200\",\n    \"type\": \"text\",\n    \"text\": {\n        \"body\"\
    : \"Hi, I'm interested in your CRM solution for my company. We have about 500\
    \ employees and need something that can scale with our growth. Can you tell me\
    \ about pricing and implementation timeline?\"\n    },\n    \"profile\": {\n \
    \       \"name\": \"John Smith\"\n    },\n    \"context\": {\n        \"from\"\
    : sender_phone,\n        \"forwarded\": False,\n        \"frequently_forwarded\"\
    : False\n    },\n    \"message_analysis\": {\n        \"message_length\": 142,\n\
    \        \"language_detected\": \"en\",\n        \"sentiment\": \"positive\",\n\
    \        \"urgency_level\": \"medium\",\n        \"business_context\": {\n   \
    \         \"company_size_mentioned\": \"500 employees\",\n            \"solution_type\"\
    : \"CRM\",\n            \"specific_interests\": [\"pricing\", \"implementation\"\
    , \"scalability\"]\n        }\n    }\n}\n\nprint(f\"\u2705 Message retrieved from\
    \ {message_data['profile']['name']}\")\nprint(f\"   Phone: {message_data['from']}\"\
    )\nprint(f\"   Message: {message_data['text']['body'][:50]}...\")\nprint(f\" \
    \  Sentiment: {message_data['message_analysis']['sentiment']}\")\n\nprint(f\"\
    __OUTPUTS__ {json.dumps(message_data)}\")\n"
  outputs:
  - name: message_data
    value: WhatsApp message retrieved
  packages:
  - json==2.0.9
  - datetime
  description: Retrieve incoming WhatsApp message details
- id: get_customer_context_from_crm
  name: Get Customer Context from CRM
  type: script
  script: "#!/usr/bin/env python3\nimport json\n\nprint(\"\U0001F50D Retrieving customer\
    \ context from CRM...\")\n\nphone_number = \"+1234567890\"\n\n# Mock CRM customer\
    \ context\ncustomer_context = {\n    \"customer_found\": True,\n    \"customer_id\"\
    : \"CUST_789\",\n    \"customer_name\": \"John Smith\",\n    \"company\": \"TechCorp\
    \ Industries\",\n    \"industry\": \"Technology\",\n    \"company_size\": \"500-1000\"\
    ,\n    \"customer_tier\": \"enterprise\",\n    \"account_status\": \"active_prospect\"\
    ,\n    \"lead_source\": \"website_form\",\n    \"assigned_officer\": \"OFF_001\"\
    ,\n    \"interaction_history\": [\n        {\n            \"date\": \"2025-06-20T14:30:00Z\"\
    ,\n            \"type\": \"email\",\n            \"direction\": \"inbound\",\n\
    \            \"subject\": \"Initial inquiry about CRM solutions\",\n         \
    \   \"outcome\": \"information_sent\"\n        },\n        {\n            \"date\"\
    : \"2025-06-22T10:15:00Z\",\n            \"type\": \"phone_call\",\n         \
    \   \"direction\": \"outbound\",\n            \"duration_minutes\": 15,\n    \
    \        \"outcome\": \"voicemail_left\"\n        }\n    ],\n    \"current_deals\"\
    : [\n        {\n            \"deal_id\": \"DEAL_2025_001234\",\n            \"\
    deal_name\": \"TechCorp CRM Implementation\",\n            \"stage\": \"qualified\"\
    ,\n            \"value\": 125000.00,\n            \"probability\": 0.65,\n   \
    \         \"last_activity\": \"2025-06-22T10:15:00Z\"\n        }\n    ],\n   \
    \ \"preferences\": {\n        \"preferred_contact_method\": \"whatsapp\",\n  \
    \      \"contact_time_preference\": \"business_hours\",\n        \"communication_style\"\
    : \"professional_direct\",\n        \"language\": \"en\"\n    },\n    \"previous_inquiries\"\
    : [\n        {\n            \"date\": \"2025-06-20\",\n            \"topic\":\
    \ \"CRM pricing for enterprise\",\n            \"status\": \"pending_follow_up\"\
    \n        }\n    ]\n}\n\nprint(f\"\u2705 Customer context retrieved for {customer_context['customer_name']}\"\
    )\nprint(f\"   Company: {customer_context['company']}\")\nprint(f\"   Customer\
    \ tier: {customer_context['customer_tier']}\")\nprint(f\"   Active deals: {len(customer_context['current_deals'])}\"\
    )\nprint(f\"   Previous interactions: {len(customer_context['interaction_history'])}\"\
    )\n\nprint(f\"__OUTPUTS__ {json.dumps(customer_context)}\")\n"
  outputs:
  - name: customer_context
    value: Customer context retrieved from CRM
  packages:
  - json==2.0.9
  depends_on:
  - get_whatsapp_message
  description: Retrieve customer information and history from CRM
- id: get_conversation_history
  name: Get Conversation History
  type: script
  script: "#!/usr/bin/env python3\nimport json\nfrom datetime import datetime\nfrom\
    \ datetime import timedelta\n\nprint(\"\U0001F4AC Retrieving conversation history...\"\
    )\n\nphone_number = \"+1234567890\"\n\n# Mock conversation history\nconversation_history\
    \ = {\n    \"conversation_id\": \"conv_12345\",\n    \"total_messages\": 3,\n\
    \    \"conversation_started\": \"2025-06-20T14:30:00Z\",\n    \"last_activity\"\
    : \"2025-06-25T16:30:00Z\",\n    \"conversation_stage\": \"initial_inquiry\",\n\
    \    \"messages\": [\n        {\n            \"id\": \"msg_001\",\n          \
    \  \"timestamp\": \"2025-06-20T14:30:00Z\",\n            \"from\": \"+1234567890\"\
    ,\n            \"type\": \"text\",\n            \"text\": \"Hello, I'm looking\
    \ for a CRM solution for our company\",\n            \"direction\": \"inbound\"\
    \n        },\n        {\n            \"id\": \"msg_002\",\n            \"timestamp\"\
    : \"2025-06-20T14:35:00Z\",\n            \"from\": \"business_number\",\n    \
    \        \"type\": \"text\",\n            \"text\": \"Hi John! Thanks for reaching\
    \ out. I'd be happy to help you find the right CRM solution. Can you tell me more\
    \ about your company size and specific needs?\",\n            \"direction\": \"\
    outbound\"\n        },\n        {\n            \"id\": \"msg_003\",\n        \
    \    \"timestamp\": \"2025-06-25T16:30:00Z\",\n            \"from\": \"+1234567890\"\
    ,\n            \"type\": \"text\",\n            \"text\": \"Hi, I'm interested\
    \ in your CRM solution for my company. We have about 500 employees and need something\
    \ that can scale with our growth. Can you tell me about pricing and implementation\
    \ timeline?\",\n            \"direction\": \"inbound\"\n        }\n    ],\n  \
    \  \"conversation_analytics\": {\n        \"customer_messages\": 2,\n        \"\
    business_messages\": 1,\n        \"avg_response_time\": \"5 minutes\",\n     \
    \   \"engagement_level\": \"high\",\n        \"sentiment_progression\": [\"neutral\"\
    , \"positive\", \"positive\"],\n        \"topics_discussed\": [\"company_size\"\
    , \"scalability\", \"pricing\", \"implementation\"]\n    },\n    \"context_summary\"\
    : {\n        \"customer_needs\": [\"scalable_crm\", \"enterprise_solution\", \"\
    implementation_support\"],\n        \"information_provided\": [\"initial_greeting\"\
    , \"needs_assessment\"],\n        \"next_expected_topics\": [\"pricing_details\"\
    , \"feature_overview\", \"demo_scheduling\"]\n    }\n}\n\nprint(f\"\u2705 Conversation\
    \ history retrieved\")\nprint(f\"   Total messages: {conversation_history['total_messages']}\"\
    )\nprint(f\"   Engagement level: {conversation_history['conversation_analytics']['engagement_level']}\"\
    )\nprint(f\"   Current stage: {conversation_history['conversation_stage']}\")\n\
    \nprint(f\"__OUTPUTS__ {json.dumps(conversation_history)}\")\n"
  outputs:
  - name: conversation_history
    value: Conversation history retrieved
  packages:
  - json==2.0.9
  depends_on:
  - get_customer_context_from_crm
  description: Retrieve WhatsApp conversation history for context
- id: get_product_catalog_from_dynamics
  name: Get Product Catalog from Dynamics
  type: script
  script: "#!/usr/bin/env python3\nimport json\n\nprint(\"\U0001F4E6 Retrieving product\
    \ catalog from Dynamics...\")\n\n# Mock product catalog\nproduct_catalog = {\n\
    \    \"products\": [\n        {\n            \"product_id\": \"CRM_ENT_001\",\n\
    \            \"name\": \"CRM Enterprise Edition\",\n            \"category\":\
    \ \"crm_software\",\n            \"description\": \"Complete CRM solution for\
    \ enterprise organizations with advanced analytics and customization\",\n    \
    \        \"target_company_size\": \"500+\",\n            \"pricing\": {\n    \
    \            \"base_price\": 299.99,\n                \"currency\": \"USD\",\n\
    \                \"billing_cycle\": \"monthly\",\n                \"pricing_tiers\"\
    : [\n                    {\n                        \"tier\": \"500-1000 users\"\
    ,\n                        \"price_per_user\": 199.99,\n                     \
    \   \"setup_fee\": 15000.00,\n                        \"annual_discount\": 0.15\n\
    \                    },\n                    {\n                        \"tier\"\
    : \"1000+ users\",\n                        \"price_per_user\": 179.99,\n    \
    \                    \"setup_fee\": 25000.00,\n                        \"annual_discount\"\
    : 0.20\n                    }\n                ]\n            },\n           \
    \ \"key_features\": [\n                \"Unlimited users\",\n                \"\
    Advanced analytics and reporting\",\n                \"Custom workflows\",\n \
    \               \"API integrations\",\n                \"24/7 enterprise support\"\
    ,\n                \"Multi-tenant architecture\"\n            ],\n           \
    \ \"implementation\": {\n                \"typical_timeline\": \"8-12 weeks\"\
    ,\n                \"implementation_cost\": \"25% of license cost\",\n       \
    \         \"training_included\": True,\n                \"data_migration\": True\n\
    \            },\n            \"competitive_advantages\": [\n                \"\
    Superior scalability\",\n                \"Industry-leading uptime (99.9%)\",\n\
    \                \"Advanced AI features\",\n                \"Comprehensive API\
    \ ecosystem\"\n            ]\n        },\n        {\n            \"product_id\"\
    : \"CRM_PRO_002\",\n            \"name\": \"CRM Professional\",\n            \"\
    category\": \"crm_software\",\n            \"description\": \"Professional CRM\
    \ solution for growing businesses\",\n            \"target_company_size\": \"\
    100-500\",\n            \"pricing\": {\n                \"base_price\": 149.99,\n\
    \                \"currency\": \"USD\",\n                \"billing_cycle\": \"\
    monthly\"\n            },\n            \"key_features\": [\n                \"\
    Up to 500 users\",\n                \"Standard reporting\",\n                \"\
    Email integration\",\n                \"Mobile app\"\n            ]\n        }\n\
    \    ],\n    \"recommendations\": {\n        \"best_match\": \"CRM_ENT_001\",\n\
    \        \"match_reasons\": [\n            \"Company size (500 employees) fits\
    \ enterprise tier\",\n            \"Scalability requirements align with enterprise\
    \ features\",\n            \"Growth trajectory suggests need for advanced capabilities\"\
    \n        ],\n        \"alternative_options\": [\"CRM_PRO_002\"],\n        \"\
    upsell_opportunities\": [\n            \"Advanced Analytics Module\",\n      \
    \      \"AI Automation Add-on\"\n        ]\n    }\n}\n\nrecommended_product =\
    \ product_catalog['recommendations']['best_match']\nmain_product = next(p for\
    \ p in product_catalog['products'] if p['product_id'] == recommended_product)\n\
    \nprint(f\"\u2705 Product catalog retrieved\")\nprint(f\"   Total products: {len(product_catalog['products'])}\"\
    )\nprint(f\"   Recommended: {main_product['name']}\")\nprint(f\"   Target size:\
    \ {main_product['target_company_size']}\")\n\nprint(f\"__OUTPUTS__ {json.dumps(product_catalog)}\"\
    )\n"
  outputs:
  - name: product_catalog
    value: Product catalog retrieved from Dynamics
  packages:
  - json==2.0.9
  depends_on:
  - get_conversation_history
  description: Retrieve relevant product information from Dynamics 365
- id: analyze_message_intent
  name: Analyze Message Intent
  type: script
  script: "#!/usr/bin/env python3\nimport json\n\nprint(\"\U0001F916 Analyzing message\
    \ intent...\")\n\nmessage_content = \"Hi, I'm interested in your CRM solution\
    \ for my company. We have about 500 employees and need something that can scale\
    \ with our growth. Can you tell me about pricing and implementation timeline?\"\
    \n\n# Mock AI intent analysis\nintent_analysis = {\n    \"primary_intent\": \"\
    product_inquiry\",\n    \"confidence_score\": 0.94,\n    \"intent_hierarchy\"\
    : [\n        {\"intent\": \"product_inquiry\", \"confidence\": 0.94},\n      \
    \  {\"intent\": \"pricing_request\", \"confidence\": 0.87},\n        {\"intent\"\
    : \"implementation_question\", \"confidence\": 0.76},\n        {\"intent\": \"\
    scalability_concern\", \"confidence\": 0.69}\n    ],\n    \"sentiment_analysis\"\
    : {\n        \"overall_sentiment\": \"positive\",\n        \"sentiment_score\"\
    : 0.78,\n        \"emotional_indicators\": [\"interest\", \"professional\", \"\
    forward_thinking\"],\n        \"tone_analysis\": \"business_focused\",\n     \
    \   \"urgency_level\": \"medium\"\n    },\n    \"entity_extraction\": {\n    \
    \    \"company_size\": \"500 employees\",\n        \"solution_type\": \"CRM solution\"\
    ,\n        \"key_requirements\": [\"scalability\", \"growth_support\"],\n    \
    \    \"information_needs\": [\"pricing\", \"implementation_timeline\"],\n    \
    \    \"decision_stage\": \"evaluation\",\n        \"budget_indicators\": [\"established_company\"\
    , \"500_employees\"]\n    },\n    \"buying_signals\": {\n        \"signals_detected\"\
    : [\n            \"specific_company_size_mentioned\",\n            \"scalability_requirements_defined\"\
    ,\n            \"implementation_timeline_inquiry\",\n            \"pricing_information_requested\"\
    \n        ],\n        \"buying_stage\": \"consideration\",\n        \"urgency_score\"\
    : 0.65,\n        \"decision_authority\": \"likely_influencer\",\n        \"budget_probability\"\
    : \"high\"\n    },\n    \"conversation_context\": {\n        \"follow_up_to_previous\"\
    : True,\n        \"information_gap\": [\"detailed_pricing\", \"implementation_process\"\
    ],\n        \"customer_education_level\": \"informed\",\n        \"technical_sophistication\"\
    : \"medium\"\n    }\n}\n\nprint(f\"\u2705 Intent analysis completed\")\nprint(f\"\
    \   Primary intent: {intent_analysis['primary_intent']} ({intent_analysis['confidence_score']:.2f})\"\
    )\nprint(f\"   Sentiment: {intent_analysis['sentiment_analysis']['overall_sentiment']}\
    \ ({intent_analysis['sentiment_analysis']['sentiment_score']:.2f})\")\nprint(f\"\
    \   Buying stage: {intent_analysis['buying_signals']['buying_stage']}\")\nprint(f\"\
    \   Buying signals: {len(intent_analysis['buying_signals']['signals_detected'])}\"\
    )\n\nprint(f\"__OUTPUTS__ {json.dumps(intent_analysis)}\")\n"
  outputs:
  - name: intent_analysis
    value: Message intent analyzed
  packages:
  - json==2.0.9
  depends_on:
  - get_product_catalog_from_dynamics
  description: AI-powered analysis of customer message intent and sentiment
- id: get_product_info
  name: Get Product Info
  type: script
  script: "#!/usr/bin/env python3\nimport json\n\nprint(\"\U0001F4CB Retrieving product\
    \ information for inquiry...\")\n\n# Mock detailed product info for response\n\
    product_info = {\n    \"product_focus\": \"CRM Enterprise Edition\",\n    \"relevant_features\"\
    : [\n        {\n            \"feature\": \"Unlimited Users\",\n            \"\
    benefit\": \"Perfect for your 500+ employee company with room to grow\",\n   \
    \         \"relevance\": \"high\"\n        },\n        {\n            \"feature\"\
    : \"Advanced Scalability\",\n            \"benefit\": \"Built to handle enterprise\
    \ growth without performance impact\",\n            \"relevance\": \"high\"\n\
    \        },\n        {\n            \"feature\": \"Custom Workflows\",\n     \
    \       \"benefit\": \"Adapt the system to your unique business processes\",\n\
    \            \"relevance\": \"medium\"\n        }\n    ],\n    \"pricing_summary\"\
    : {\n        \"recommended_tier\": \"500-1000 users\",\n        \"price_per_user\"\
    : 199.99,\n        \"estimated_monthly_cost\": 99995.00,\n        \"setup_fee\"\
    : 15000.00,\n        \"annual_savings\": \"15% discount available\",\n       \
    \ \"roi_estimate\": \"Typically 300% ROI within 18 months\"\n    },\n    \"implementation_details\"\
    : {\n        \"timeline\": \"8-12 weeks for full implementation\",\n        \"\
    phases\": [\n            \"Planning and setup (2 weeks)\",\n            \"Data\
    \ migration (3-4 weeks)\",\n            \"User training (2 weeks)\",\n       \
    \     \"Go-live and support (1-2 weeks)\"\n        ],\n        \"support_included\"\
    : \"Dedicated implementation manager and 24/7 support\",\n        \"training\"\
    : \"Comprehensive user training for all 500 employees\"\n    },\n    \"next_steps\"\
    : [\n        \"Schedule detailed demo\",\n        \"Provide customized pricing\
    \ proposal\",\n        \"Connect with implementation specialist\"\n    ]\n}\n\n\
    print(f\"\u2705 Product information compiled\")\nprint(f\"   Focus product: {product_info['product_focus']}\"\
    )\nprint(f\"   Estimated monthly cost: ${product_info['pricing_summary']['estimated_monthly_cost']:,.2f}\"\
    )\nprint(f\"   Implementation timeline: {product_info['implementation_details']['timeline']}\"\
    )\n\nprint(f\"__OUTPUTS__ {json.dumps(product_info)}\")\n"
  outputs:
  - name: product_info
    value: Product information retrieved
  packages:
  - json==2.0.9
  condition: ${intent_analysis.primary_intent} == 'product_inquiry'
  depends_on:
  - analyze_message_intent
  description: Retrieve specific product information for inquiry intent
- id: get_support_context
  name: Get Support Context
  type: script
  script: "#!/usr/bin/env python3\nimport json\n\nprint(\"\U0001F6E0\uFE0F Retrieving\
    \ support context for complaint...\")\n\n# Mock support context\nsupport_context\
    \ = {\n    \"complaint_type\": \"service_issue\",\n    \"severity\": \"medium\"\
    ,\n    \"related_tickets\": [\n        {\n            \"ticket_id\": \"SUP_2025_001234\"\
    ,\n            \"status\": \"open\",\n            \"created_date\": \"2025-06-20T09:00:00Z\"\
    ,\n            \"issue\": \"Login problems\",\n            \"assigned_agent\"\
    : \"AGENT_001\"\n        }\n    ],\n    \"customer_satisfaction_score\": 3.2,\n\
    \    \"recent_issues\": [\n        \"Authentication delays\",\n        \"Slow\
    \ report generation\"\n    ],\n    \"escalation_needed\": False,\n    \"support_actions\"\
    : [\n        \"Acknowledge complaint\",\n        \"Provide immediate troubleshooting\"\
    ,\n        \"Schedule follow-up call\"\n    ]\n}\n\nprint(f\"\u2705 Support context\
    \ retrieved\")\nprint(f\"   Complaint type: {support_context['complaint_type']}\"\
    )\nprint(f\"   Open tickets: {len(support_context['related_tickets'])}\")\n\n\
    print(f\"__OUTPUTS__ {json.dumps(support_context)}\")\n"
  outputs:
  - name: support_context
    value: Support context retrieved
  packages:
  - json==2.0.9
  condition: ${intent_analysis.primary_intent} == 'complaint'
  depends_on:
  - analyze_message_intent
  description: Retrieve support context for complaint intent
- id: get_order_details
  name: Get Order Details
  type: script
  script: "#!/usr/bin/env python3\nimport json\n\nprint(\"\U0001F4E6 Retrieving order\
    \ details...\")\n\n# Mock order details\norder_details = {\n    \"recent_orders\"\
    : [\n        {\n            \"order_id\": \"ORD_2025_001234\",\n            \"\
    status\": \"processing\",\n            \"order_date\": \"2025-06-20T00:00:00Z\"\
    ,\n            \"total_amount\": 15000.00,\n            \"items\": [\n       \
    \         {\n                    \"product\": \"CRM Professional License\",\n\
    \                    \"quantity\": 100,\n                    \"unit_price\": 149.99\n\
    \                }\n            ],\n            \"estimated_delivery\": \"2025-07-15T00:00:00Z\"\
    \n        }\n    ],\n    \"order_status_options\": [\n        \"Check order status\"\
    ,\n        \"Modify order\",\n        \"Cancel order\",\n        \"Track delivery\"\
    \n    ],\n    \"payment_information\": {\n        \"payment_method\": \"Corporate\
    \ credit card\",\n        \"payment_status\": \"approved\",\n        \"invoice_sent\"\
    : True\n    }\n}\n\nprint(f\"\u2705 Order details retrieved\")\nprint(f\"   Recent\
    \ orders: {len(order_details['recent_orders'])}\")\n\nprint(f\"__OUTPUTS__ {json.dumps(order_details)}\"\
    )\n"
  outputs:
  - name: order_details
    value: Order details retrieved
  packages:
  - json==2.0.9
  condition: ${intent_analysis.primary_intent} == 'order'
  depends_on:
  - analyze_message_intent
  description: Retrieve order information for order intent
- id: get_troubleshooting
  name: Get Troubleshooting
  type: script
  script: "#!/usr/bin/env python3\nimport json\n\nprint(\"\U0001F527 Retrieving troubleshooting\
    \ information...\")\n\n# Mock troubleshooting info\ntroubleshooting_info = {\n\
    \    \"common_issues\": [\n        {\n            \"issue\": \"Login problems\"\
    ,\n            \"solution\": \"Clear browser cache and try again\",\n        \
    \    \"success_rate\": 0.85\n        },\n        {\n            \"issue\": \"\
    Slow performance\",\n            \"solution\": \"Check internet connection and\
    \ try during off-peak hours\",\n            \"success_rate\": 0.70\n        },\n\
    \        {\n            \"issue\": \"Data sync issues\",\n            \"solution\"\
    : \"Refresh the page and wait 5 minutes for sync\",\n            \"success_rate\"\
    : 0.90\n        }\n    ],\n    \"self_service_options\": [\n        \"Knowledge\
    \ base articles\",\n        \"Video tutorials\",\n        \"Community forum\"\
    ,\n        \"Live chat support\"\n    ],\n    \"escalation_triggers\": [\n   \
    \     \"Technical complexity high\",\n        \"Customer frustration detected\"\
    ,\n        \"Multiple failed self-service attempts\"\n    ]\n}\n\nprint(f\"\u2705\
    \ Troubleshooting information retrieved\")\nprint(f\"   Common issues: {len(troubleshooting_info['common_issues'])}\"\
    )\n\nprint(f\"__OUTPUTS__ {json.dumps(troubleshooting_info)}\")\n"
  outputs:
  - name: troubleshooting_info
    value: Troubleshooting information retrieved
  packages:
  - json==2.0.9
  condition: ${intent_analysis.primary_intent} == 'support'
  depends_on:
  - analyze_message_intent
  description: Retrieve troubleshooting information for support intent
- id: generate_response
  name: Generate Response
  type: script
  script: "#!/usr/bin/env python3\nimport json\n\nprint(\"\u270D\uFE0F Generating\
    \ AI response...\")\n\n# Mock AI response generation based on product inquiry\
    \ intent\ngenerated_response = {\n    \"response_type\": \"product_inquiry_response\"\
    ,\n    \"tone\": \"professional_helpful\",\n    \"personalization_level\": \"\
    high\",\n    \"message_text\": \"Hi John! Great to hear from you again. For TechCorp\
    \ with 500 employees, our CRM Enterprise Edition would be perfect - it's designed\
    \ specifically for companies your size with unlimited users and advanced scalability\
    \ features.\\n\\nHere's what you're looking at:\\n\U0001F4B0 Pricing: $199.99/user/month\
    \ (about $100K/month for 500 users)\\n\u23F1\uFE0F Implementation: 8-12 weeks\
    \ with full training included\\n\U0001F4C8 ROI: Most clients see 300% ROI within\
    \ 18 months\\n\\nThe system grows with you - no performance issues as you scale\
    \ beyond 500 employees. Would you like me to schedule a personalized demo to show\
    \ you exactly how it would work for TechCorp?\",\n    \"key_elements\": [\n  \
    \      \"Personal greeting using name and company\",\n        \"Specific product\
    \ recommendation with reasoning\",\n        \"Clear pricing information\",\n \
    \       \"Implementation timeline\",\n        \"ROI value proposition\",\n   \
    \     \"Scalability assurance\",\n        \"Clear call-to-action\"\n    ],\n \
    \   \"call_to_action\": {\n        \"primary\": \"Schedule personalized demo\"\
    ,\n        \"secondary\": \"Request detailed pricing proposal\",\n        \"urgency\"\
    : \"medium\"\n    },\n    \"follow_up_suggestions\": [\n        \"Demo scheduling\"\
    ,\n        \"Detailed proposal preparation\",\n        \"Implementation timeline\
    \ discussion\"\n    ],\n    \"estimated_response_effectiveness\": 0.87,\n    \"\
    expected_customer_actions\": [\n        \"Request demo\",\n        \"Ask follow-up\
    \ questions\",\n        \"Request proposal\"\n    ]\n}\n\nprint(f\"\u2705 Response\
    \ generated\")\nprint(f\"   Response type: {generated_response['response_type']}\"\
    )\nprint(f\"   Tone: {generated_response['tone']}\")\nprint(f\"   Effectiveness\
    \ estimate: {generated_response['estimated_response_effectiveness']:.2f}\")\n\
    print(f\"   Message length: {len(generated_response['message_text'])} characters\"\
    )\n\nprint(f\"__OUTPUTS__ {json.dumps(generated_response)}\")\n"
  outputs:
  - name: generated_response
    value: AI response generated
  packages:
  - json==2.0.9
  depends_on:
  - get_product_info
  - get_support_context
  - get_order_details
  - get_troubleshooting
  description: AI-powered response generation based on intent and context
- id: determine_escalation_need
  name: Determine Escalation Need
  type: script
  script: "#!/usr/bin/env python3\nimport json\n\nprint(\"\U0001F3AF Determining escalation\
    \ need...\")\n\n# Mock escalation assessment\nescalation_assessment = {\n    \"\
    needs_human_escalation\": False,\n    \"escalation_confidence\": 0.85,\n    \"\
    assessment_factors\": [\n        {\n            \"factor\": \"message_complexity\"\
    ,\n            \"score\": 0.3,\n            \"threshold\": 0.7,\n            \"\
    status\": \"below_threshold\"\n        },\n        {\n            \"factor\":\
    \ \"customer_sentiment\",\n            \"score\": 0.78,\n            \"threshold\"\
    : 0.3,\n            \"status\": \"positive\"\n        },\n        {\n        \
    \    \"factor\": \"technical_complexity\",\n            \"score\": 0.2,\n    \
    \        \"threshold\": 0.6,\n            \"status\": \"low_complexity\"\n   \
    \     },\n        {\n            \"factor\": \"deal_value\",\n            \"score\"\
    : 0.8,\n            \"threshold\": 0.7,\n            \"status\": \"high_value\"\
    \n        },\n        {\n            \"factor\": \"conversation_duration\",\n\
    \            \"score\": 0.2,\n            \"threshold\": 0.8,\n            \"\
    status\": \"short_conversation\"\n        }\n    ],\n    \"escalation_triggers\"\
    : {\n        \"high_value_deal\": True,\n        \"enterprise_customer\": True,\n\
    \        \"complex_technical_query\": False,\n        \"customer_frustration\"\
    : False,\n        \"pricing_negotiation\": False\n    },\n    \"ai_capability_assessment\"\
    : {\n        \"can_handle_query\": True,\n        \"information_complete\": True,\n\
    \        \"response_quality_sufficient\": True,\n        \"follow_up_manageable\"\
    : True\n    },\n    \"recommendation\": \"ai_handled\",\n    \"escalation_reason\"\
    : None,\n    \"monitoring_required\": True,\n    \"escalation_threshold_met\"\
    : False\n}\n\nescalation_needed = escalation_assessment[\"needs_human_escalation\"\
    ]\n\nif escalation_needed:\n    print(f\"\U0001F6A8 Human escalation required\"\
    )\n    print(f\"   Reason: {escalation_assessment.get('escalation_reason', 'Multiple\
    \ factors')}\")\nelse:\n    print(f\"\u2705 AI can handle this query\")\n    print(f\"\
    \   Confidence: {escalation_assessment['escalation_confidence']:.2f}\")\n\nprint(f\"\
    \   High value deal detected: {escalation_assessment['escalation_triggers']['high_value_deal']}\"\
    )\nprint(f\"   Monitoring required: {escalation_assessment['monitoring_required']}\"\
    )\n\nprint(f\"__OUTPUTS__ {json.dumps(escalation_assessment)}\")\n"
  outputs:
  - name: escalation_assessment
    value: Escalation need determined
  packages:
  - json==2.0.9
  depends_on:
  - generate_response
  description: Assess if human escalation is needed
- id: send_whatsapp_response
  name: Send WhatsApp Response
  type: script
  script: "#!/usr/bin/env python3\nimport json\nfrom datetime import datetime\n\n\
    print(\"\U0001F4E4 Sending WhatsApp response...\")\n\nrecipient_phone = \"+1234567890\"\
    \nmessage_content = \"Hi John! Great to hear from you again. For TechCorp with\
    \ 500 employees, our CRM Enterprise Edition would be perfect - it's designed specifically\
    \ for companies your size with unlimited users and advanced scalability features.\\\
    n\\nHere's what you're looking at:\\n\U0001F4B0 Pricing: $199.99/user/month (about\
    \ $100K/month for 500 users)\\n\u23F1\uFE0F Implementation: 8-12 weeks with full\
    \ training included\\n\U0001F4C8 ROI: Most clients see 300% ROI within 18 months\\\
    n\\nThe system grows with you - no performance issues as you scale beyond 500\
    \ employees. Would you like me to schedule a personalized demo to show you exactly\
    \ how it would work for TechCorp?\"\n\n# Mock WhatsApp response sending\nresponse_result\
    \ = {\n    \"message_id\": \"wamid.HBgLMTIzNDU2Nzg5MDE_response...\",\n    \"\
    recipient\": recipient_phone,\n    \"recipient_name\": \"John Smith\",\n    \"\
    message_status\": \"sent\",\n    \"sent_at\": datetime.now().isoformat(),\n  \
    \  \"delivery_status\": \"delivered\",\n    \"message_type\": \"text\",\n    \"\
    character_count\": len(message_content),\n    \"estimated_delivery\": \"immediate\"\
    ,\n    \"conversation_id\": \"conv_12345\",\n    \"ai_handled\": True,\n    \"\
    response_time_seconds\": 8.5,\n    \"campaign_tracking\": {\n        \"campaign_type\"\
    : \"ai_customer_engagement\",\n        \"intent_addressed\": \"product_inquiry\"\
    ,\n        \"personalization_level\": \"high\",\n        \"expected_engagement\"\
    : \"high\"\n    }\n}\n\nprint(f\"\u2705 WhatsApp response sent to {response_result['recipient_name']}\"\
    )\nprint(f\"   Message ID: {response_result['message_id']}\")\nprint(f\"   Status:\
    \ {response_result['message_status']}\")\nprint(f\"   Response time: {response_result['response_time_seconds']}\
    \ seconds\")\nprint(f\"   Character count: {response_result['character_count']}\"\
    )\n\nprint(f\"__OUTPUTS__ {json.dumps(response_result)}\")\n"
  outputs:
  - name: whatsapp_response_sent
    value: WhatsApp response sent
  packages:
  - json==2.0.9
  condition: ${escalation_assessment.needs_human_escalation} == false
  depends_on:
  - determine_escalation_need
  description: Send AI-generated response via WhatsApp
- id: escalate_to_human
  name: Escalate to Human
  type: script
  script: "#!/usr/bin/env python3\nimport json\nfrom datetime import datetime\n\n\
    print(\"\U0001F6A8 Escalating to human agent...\")\n\n# Mock human escalation\n\
    escalation_result = {\n    \"escalation_id\": \"ESC_2025_WA_001234\",\n    \"\
    customer_phone\": \"+1234567890\",\n    \"customer_name\": \"John Smith\",\n \
    \   \"escalation_reason\": \"high_value_enterprise_inquiry\",\n    \"urgency_level\"\
    : \"high\",\n    \"escalated_at\": datetime.now().isoformat(),\n    \"assigned_agent\"\
    : \"AGENT_001\",\n    \"agent_name\": \"Sarah Johnson\",\n    \"estimated_response_time\"\
    : \"15 minutes\",\n    \"escalation_context\": {\n        \"conversation_summary\"\
    : \"Enterprise customer inquiry about CRM for 500 employees, pricing and implementation\
    \ questions\",\n        \"customer_tier\": \"enterprise\",\n        \"deal_potential\"\
    : 125000.00,\n        \"previous_interactions\": 3,\n        \"ai_assessment\"\
    : \"high_value_opportunity_requiring_personal_attention\"\n    },\n    \"handover_message\"\
    : \"Hi John! I'm connecting you with Sarah Johnson, our enterprise specialist,\
    \ who can provide detailed pricing and implementation planning for TechCorp. She'll\
    \ be with you shortly!\",\n    \"agent_briefing\": {\n        \"customer_background\"\
    : \"Existing prospect, 500-employee tech company\",\n        \"current_need\"\
    : \"CRM Enterprise pricing and implementation timeline\",\n        \"recommended_approach\"\
    : \"consultative_sales_focus_on_scalability_and_roi\",\n        \"next_actions\"\
    : [\"detailed_needs_assessment\", \"custom_proposal_preparation\", \"demo_scheduling\"\
    ]\n    }\n}\n\nprint(f\"\u2705 Escalated to {escalation_result['agent_name']}\"\
    )\nprint(f\"   Escalation ID: {escalation_result['escalation_id']}\")\nprint(f\"\
    \   Urgency: {escalation_result['urgency_level']}\")\nprint(f\"   ETA: {escalation_result['estimated_response_time']}\"\
    )\n\nprint(f\"__OUTPUTS__ {json.dumps(escalation_result)}\")\n"
  outputs:
  - name: escalation_result
    value: Conversation escalated to human
  packages:
  - json==2.0.9
  condition: ${escalation_assessment.needs_human_escalation} == true
  depends_on:
  - determine_escalation_need
  description: Escalate conversation to human agent
- id: update_conversation_log
  name: Update Conversation Log
  type: script
  script: "#!/usr/bin/env python3\nimport json\nfrom datetime import datetime\n\n\
    print(\"\U0001F4DD Updating conversation log...\")\n\n# Mock conversation logging\n\
    conversation_log = {\n    \"log_id\": \"LOG_2025_WA_001234\",\n    \"customer_id\"\
    : \"CUST_789\",\n    \"interaction_type\": \"whatsapp\",\n    \"interaction_date\"\
    : datetime.now().isoformat(),\n    \"direction\": \"inbound\",\n    \"channel\"\
    : \"whatsapp\",\n    \"duration_seconds\": 8.5,\n    \"ai_handled\": True,\n \
    \   \"escalated\": False,\n    \"interaction_summary\": {\n        \"customer_message\"\
    : \"CRM inquiry for 500-employee company, pricing and implementation questions\"\
    ,\n        \"intent_classified\": \"product_inquiry\",\n        \"response_provided\"\
    : \"Detailed CRM Enterprise information with pricing, timeline, and demo offer\"\
    ,\n        \"outcome\": \"information_provided\",\n        \"next_expected_action\"\
    : \"demo_request_or_follow_up_questions\"\n    },\n    \"sentiment_analysis\"\
    : {\n        \"customer_sentiment\": \"positive\",\n        \"satisfaction_predicted\"\
    : 0.85,\n        \"engagement_level\": \"high\"\n    },\n    \"business_impact\"\
    : {\n        \"lead_score_change\": \"+5\",\n        \"deal_progression\": \"\
    information_stage_to_consideration\",\n        \"opportunity_value\": 125000.00,\n\
    \        \"conversion_probability\": 0.68\n    },\n    \"ai_performance\": {\n\
    \        \"response_time\": 8.5,\n        \"intent_accuracy\": 0.94,\n       \
    \ \"response_quality_score\": 0.87,\n        \"escalation_avoidance\": True\n\
    \    },\n    \"follow_up_actions\": [\n        {\n            \"action\": \"monitor_for_response\"\
    ,\n            \"timeline\": \"24_hours\",\n            \"automated\": True\n\
    \        },\n        {\n            \"action\": \"prepare_demo_materials\",\n\
    \            \"timeline\": \"if_requested\",\n            \"automated\": False\n\
    \        }\n    ]\n}\n\nprint(f\"\u2705 Conversation logged\")\nprint(f\"   Log\
    \ ID: {conversation_log['log_id']}\")\nprint(f\"   AI handled: {conversation_log['ai_handled']}\"\
    )\nprint(f\"   Customer sentiment: {conversation_log['sentiment_analysis']['customer_sentiment']}\"\
    )\nprint(f\"   Opportunity value: ${conversation_log['business_impact']['opportunity_value']:,.2f}\"\
    )\n\nprint(f\"__OUTPUTS__ {json.dumps(conversation_log)}\")\n"
  outputs:
  - name: conversation_log
    value: Conversation logged in CRM
  packages:
  - json==2.0.9
  depends_on:
  - send_whatsapp_response
  - escalate_to_human
  description: Log interaction details in CRM system
- id: check_new_inquiry
  name: Check New Inquiry
  type: script
  script: "#!/usr/bin/env python3\nimport json\n\nprint(\"\U0001F50D Checking if new\
    \ inquiry should be created...\")\n\n# Mock new inquiry assessment\nnew_inquiry_check\
    \ = {\n    \"creates_new_inquiry\": True,\n    \"inquiry_criteria_met\": [\n \
    \       \"specific_product_interest_expressed\",\n        \"company_size_and_requirements_defined\"\
    ,\n        \"pricing_information_requested\",\n        \"implementation_timeline_discussed\"\
    \n    ],\n    \"existing_inquiries\": [\n        {\n            \"inquiry_id\"\
    : \"INQ_2025_001234\",\n            \"status\": \"pending_follow_up\",\n     \
    \       \"created_date\": \"2025-06-20\",\n            \"topic\": \"Initial CRM\
    \ interest\"\n        }\n    ],\n    \"inquiry_relationship\": \"follow_up_to_existing\"\
    ,\n    \"should_create_new\": True,\n    \"reason\": \"Significant progression\
    \ from initial interest to specific requirements and pricing inquiry\"\n}\n\n\
    creates_inquiry = new_inquiry_check[\"creates_new_inquiry\"]\n\nif creates_inquiry:\n\
    \    print(f\"\u2705 New inquiry should be created\")\n    print(f\"   Reason:\
    \ {new_inquiry_check['reason']}\")\nelse:\n    print(f\"\u2139\uFE0F No new inquiry\
    \ needed\")\n\nprint(f\"   Existing inquiries: {len(new_inquiry_check['existing_inquiries'])}\"\
    )\n\nprint(f\"__OUTPUTS__ {json.dumps(new_inquiry_check)}\")\n"
  outputs:
  - name: inquiry_check_result
    value: New inquiry check completed
  packages:
  - json==2.0.9
  depends_on:
  - update_conversation_log
  description: Determine if this creates a new inquiry/opportunity
- id: create_crm_inquiry
  name: Create CRM Inquiry
  type: script
  script: "#!/usr/bin/env python3\nimport json\nfrom datetime import datetime\n\n\
    print(\"\U0001F4CB Creating new CRM inquiry...\")\n\n# Mock CRM inquiry creation\n\
    crm_inquiry = {\n    \"inquiry_id\": \"INQ_2025_005678\",\n    \"customer_id\"\
    : \"CUST_789\",\n    \"customer_phone\": \"+1234567890\",\n    \"customer_email\"\
    : \"john.smith@techcorp.com\",\n    \"inquiry_type\": \"product_interest\",\n\
    \    \"source\": \"whatsapp\",\n    \"priority\": \"high\",\n    \"subject\":\
    \ \"CRM Enterprise Solution for 500 Employees\",\n    \"description\": \"Customer\
    \ interested in CRM Enterprise Edition for 500-employee technology company. Specific\
    \ questions about pricing ($199.99/user/month tier) and implementation timeline\
    \ (8-12 weeks). Company name: TechCorp Industries.\",\n    \"products_of_interest\"\
    : [\"CRM_ENT_001\"],\n    \"customer_context\": {\n        \"company_size\": \"\
    500\",\n        \"industry\": \"technology\",\n        \"current_solution\": \"\
    unknown\",\n        \"scalability_important\": True,\n        \"budget_range\"\
    : \"enterprise_level\"\n    },\n    \"ai_analysis\": {\n        \"intent_confidence\"\
    : 0.94,\n        \"urgency_score\": 0.65,\n        \"budget_indicators\": [\"\
    enterprise\", \"500_employees\", \"scalability_focus\"],\n        \"buying_stage\"\
    : \"consideration\",\n        \"conversion_probability\": 0.68\n    },\n    \"\
    created_at\": datetime.now().isoformat(),\n    \"assigned_to\": \"TEAM_ENTERPRISE_SALES\"\
    ,\n    \"estimated_response_time\": \"2 hours\",\n    \"follow_up_sequence\":\
    \ [\n        {\n            \"step\": 1,\n            \"action\": \"send_detailed_proposal\"\
    ,\n            \"scheduled_for\": (datetime.now()).isoformat(),\n            \"\
    owner\": \"sales_team\"\n        },\n        {\n            \"step\": 2,\n   \
    \         \"action\": \"schedule_demo_call\",\n            \"scheduled_for\":\
    \ \"on_customer_request\",\n            \"owner\": \"demo_specialist\"\n     \
    \   }\n    ],\n    \"related_records\": {\n        \"customer_id\": \"CUST_789\"\
    ,\n        \"existing_deal\": \"DEAL_2025_001234\",\n        \"conversation_log\"\
    : \"LOG_2025_WA_001234\"\n    }\n}\n\nprint(f\"\u2705 CRM inquiry created\")\n\
    print(f\"   Inquiry ID: {crm_inquiry['inquiry_id']}\")\nprint(f\"   Priority:\
    \ {crm_inquiry['priority']}\")\nprint(f\"   Subject: {crm_inquiry['subject']}\"\
    )\nprint(f\"   Assigned to: {crm_inquiry['assigned_to']}\")\nprint(f\"   Conversion\
    \ probability: {crm_inquiry['ai_analysis']['conversion_probability']:.2f}\")\n\
    \nprint(f\"__OUTPUTS__ {json.dumps(crm_inquiry)}\")\n"
  outputs:
  - name: crm_inquiry_created
    value: CRM inquiry created
  packages:
  - json==2.0.9
  condition: ${inquiry_check_result.creates_new_inquiry} == true
  depends_on:
  - check_new_inquiry
  description: Create new inquiry record in CRM
- id: schedule_follow_up
  name: Schedule Follow-up
  type: script
  script: "#!/usr/bin/env python3\nimport json\nfrom datetime import datetime\nfrom\
    \ datetime import timedelta\n\nprint(\"\U0001F4C5 Scheduling follow-up actions...\"\
    )\n\n# Mock follow-up scheduling\nfollow_up_schedule = {\n    \"follow_up_id\"\
    : \"FOLLOWUP_2025_001234\",\n    \"customer_id\": \"CUST_789\",\n    \"conversation_id\"\
    : \"conv_12345\",\n    \"follow_up_type\": \"whatsapp_engagement_follow_up\",\n\
    \    \"scheduled_actions\": [\n        {\n            \"action_id\": \"ACTION_001\"\
    ,\n            \"action_type\": \"response_monitoring\",\n            \"description\"\
    : \"Monitor for customer response to CRM Enterprise information\",\n         \
    \   \"scheduled_for\": datetime.now().isoformat(),\n            \"duration_hours\"\
    : 24,\n            \"automated\": True,\n            \"trigger_condition\": \"\
    no_customer_response_within_24h\"\n        },\n        {\n            \"action_id\"\
    : \"ACTION_002\",\n            \"action_type\": \"proactive_follow_up\",\n   \
    \         \"description\": \"Send follow-up message if no response received\"\
    ,\n            \"scheduled_for\": (datetime.now() + timedelta(hours=48)).isoformat(),\n\
    \            \"automated\": True,\n            \"message_template\": \"demo_offer_follow_up\"\
    ,\n            \"condition\": \"no_response_received\"\n        },\n        {\n\
    \            \"action_id\": \"ACTION_003\",\n            \"action_type\": \"sales_team_notification\"\
    ,\n            \"description\": \"Notify enterprise sales team of high-value opportunity\"\
    ,\n            \"scheduled_for\": (datetime.now() + timedelta(hours=2)).isoformat(),\n\
    \            \"automated\": True,\n            \"recipient\": \"TEAM_ENTERPRISE_SALES\"\
    \n        }\n    ],\n    \"escalation_rules\": [\n        {\n            \"condition\"\
    : \"no_response_after_72_hours\",\n            \"action\": \"escalate_to_sales_manager\"\
    ,\n            \"priority\": \"medium\"\n        },\n        {\n            \"\
    condition\": \"negative_sentiment_detected\",\n            \"action\": \"immediate_human_intervention\"\
    ,\n            \"priority\": \"high\"\n        }\n    ],\n    \"success_metrics\"\
    : {\n        \"target_response_rate\": 0.75,\n        \"target_demo_conversion\"\
    : 0.40,\n        \"target_proposal_acceptance\": 0.60\n    }\n}\n\nprint(f\"\u2705\
    \ Follow-up actions scheduled\")\nprint(f\"   Follow-up ID: {follow_up_schedule['follow_up_id']}\"\
    )\nprint(f\"   Scheduled actions: {len(follow_up_schedule['scheduled_actions'])}\"\
    )\n\nfor action in follow_up_schedule['scheduled_actions']:\n    print(f\"   \u2022\
    \ {action['action_type']}: {action['description']}\")\n\nprint(f\"__OUTPUTS__\
    \ {json.dumps(follow_up_schedule)}\")\n"
  outputs:
  - name: follow_up_scheduled
    value: Follow-up actions scheduled
  packages:
  - json==2.0.9
  depends_on:
  - create_crm_inquiry
  - check_new_inquiry
  description: Schedule appropriate follow-up actions
inputs:
- name: message_id
  type: string
  default: wamid.HBgLMTIzNDU2Nzg5MDE...
  description: WhatsApp message ID from webhook
- name: sender_phone
  type: string
  default: '+1234567890'
  description: Customer phone number
outputs:
  escalation_details:
    type: object
    source: escalate_to_human
    description: Human escalation details if applicable
  message_processing:
    type: object
    source: get_whatsapp_message
    description: WhatsApp message processing results
  conversation_record:
    type: object
    source: update_conversation_log
    description: Complete conversation log and follow-up schedule
  customer_engagement:
    type: object
    source: send_whatsapp_response
    description: Customer engagement outcome
  intent_analysis_result:
    type: object
    source: analyze_message_intent
    description: AI intent analysis and classification
version: '1.0'
triggers:
- name: WhatsApp Message Received
  path: /webhook/whatsapp-message
  type: webhook
  config:
    method: POST
    headers:
    - name: Content-Type
      value: application/json
      required: true
    - name: X-Hub-Signature
      value: webhook_signature
      required: true
    authentication: none
  description: Triggered when new WhatsApp message is received
  input_mapping:
  - webhook_field: entry[0].changes[0].value.messages[0].id
    workflow_input: message_id
  - webhook_field: entry[0].changes[0].value.messages[0].from
    workflow_input: sender_phone
- name: Manual Message Processing
  type: manual
  description: Manually process WhatsApp message
description: Automated WhatsApp customer engagement with AI-powered intent analysis
  and response generation

Execution ID	Status	Started	Duration	Actions
`3f8ca734...`	COMPLETED	2025-07-04 15:14:26	N/A	View
`f61edea2...`	COMPLETED	2025-07-02 11:12:59	N/A	View
`b2e8ce19...`	COMPLETED	2025-07-02 11:04:42	N/A	View
`6428d13b...`	COMPLETED	2025-07-02 05:26:01	N/A	View
`976e850a...`	COMPLETED	2025-07-01 19:03:18	N/A	View