AI Agent

{
  "type": "object",
  "properties": {
    "company_name": {"type": "string", "description": "Name of the prospect's company"},
    "contact_name": {"type": "string", "description": "Full name of the primary contact"},
    "contact_email": {"type": "string", "description": "Email address of the primary contact"},
    "contact_phone": {"type": "string", "description": "Phone number of the primary contact"},
    "company_size": {"type": "string", "enum": ["1-10", "11-50", "51-200", "201-1000", "1000+"], "description": "Number of employees in the company"},
    "industry": {"type": "string", "description": "Industry or sector the company operates in"},
    "use_case": {"type": "string", "description": "Specific use case or problem they want to solve"},
    "timeline": {"type": "string", "enum": ["Immediate", "1-3 months", "3-6 months", "6+ months"], "description": "Timeline for implementation"},
    "budget_range": {"type": "string", "enum": ["Under $10k", "$10k-$50k", "$50k-$100k", "$100k+"], "description": "Approximate budget range"},
    "lead_score": {"type": "integer", "minimum": 1, "maximum": 100, "description": "Qualification score (1-100)"},
    "qualification_status": {"type": "string", "enum": ["qualified", "nurture", "disqualified"], "description": "Lead qualification status"},
    "lead_source": {"type": "string", "default": "AI Agent Qualification"},
    "notes": {"type": "string", "description": "Additional notes from the qualification conversation"}
  },
  "required": ["company_name", "contact_name", "contact_email", "use_case", "lead_score", "qualification_status"]
}

pip install orq-ai-sdk

npm install @orq-ai/node

import os
from orq_ai_sdk import Orq

client = Orq(
    api_key=os.environ.get("ORQ_API_KEY", "__API_KEY__"),
    environment="production",
    contact_id="prospect_agent" # optional
)

import { Orq } from "@orq-ai/node";

const client = new Orq({
    apiKey: process.env.ORQ_API_KEY || "__API_KEY__",
    environment: "production",
    contactId: "prospect_agent" // optional
});

import os
from orq_ai_sdk import Orq
import json

class SimpleProspectSystem:
    def __init__(self, client: Orq):
        self.client = client
        
        # Agent deployment keys
        self.agents = {
            "ingestion": "ingestionAgent",
            "qualification": "qualificationAgent", 
            "insertion": "insertionAgent"
        }
    
    def run_prospect_qualification(self, prospect_responses: list) -> dict:
        """Run complete prospect qualification workflow"""
        print("🚀 Starting 3-Agent Prospect Qualification")
        print("=" * 50)
        
        # Step 1: Ingestion Loop
        conversation = []
        print("📞 INGESTION PHASE")
        print("-" * 30)
        
        for i, user_message in enumerate(prospect_responses):
            print(f"👤 Prospect: {user_message}")
            
            # Add user message to conversation
            conversation.append({"role": "user", "content": user_message})
            
            # Call ingestion agent
            response = self.client.deployments.invoke(
                key=self.agents["ingestion"],
                messages=conversation
            )
            
            agent_response = response.choices[0].message.content
            conversation.append({"role": "assistant", "content": agent_response})
            
            print(f"🤖 Ingestion Agent: {agent_response}")
            print("-" * 30)
        
        print("\n🔍 QUALIFICATION PHASE")
        print("-" * 30)
        
        # Step 2: Explicit Qualification Call  
        qualification_prompt = f"""
        Analyze this complete prospect conversation and provide qualification analysis:
        
        Conversation: {json.dumps(conversation, indent=2)}
        
        Provide your analysis including lead score and qualification status.
        """
        
        qualification_response = self.client.deployments.invoke(
            key=self.agents["qualification"],
            messages=[{"role": "user", "content": qualification_prompt}]
        )
        
        qualification_analysis = qualification_response.choices[0].message.content
        print(f"🤖 Qualification Agent: {qualification_analysis}")
        print("-" * 30)
        
        print("\n💾 INSERTION PHASE")
        print("-" * 30)
        
        # Step 3: Explicit Insertion Call
        insertion_prompt = f"""
        Based on this conversation and qualification analysis, extract the prospect data and insert into CRM:
        
        Conversation: {json.dumps(conversation, indent=2)}
        
        Qualification Analysis: {qualification_analysis}
        
        Use the crminsert tool to add this prospect to the CRM system.
        """
        
        insertion_response = self.client.deployments.invoke(
            key=self.agents["insertion"],
            messages=[{"role": "user", "content": insertion_prompt}]
        )
        
        insertion_result = insertion_response.choices[0].message.content
        print(f"🤖 Insertion Agent: {insertion_result}")
        
        # Step 4: Extract and Print Insertion Payload
        tool_calls = getattr(insertion_response.choices[0].message, 'tool_calls', [])
        insertion_payload = None
        
        for tool_call in tool_calls:
            if tool_call.function.name == 'crminsert':
                insertion_payload = json.loads(tool_call.function.arguments)
                break
        
        print("\n🎯 FINAL INSERTION PAYLOAD")
        print("=" * 50)
        if insertion_payload:
            print(json.dumps(insertion_payload, indent=2))
        else:
            print("No CRM insertion payload found")
        
        return {
            "conversation": conversation,
            "qualification_analysis": qualification_analysis,
            "insertion_result": insertion_result,
            "insertion_payload": insertion_payload
        }

# Initialize the system
client = Orq(
    api_key=os.environ.get("ORQ_API_KEY", "__API_KEY__"),
    environment="production"
)

prospect_system = SimpleProspectSystem(client)

# Example prospect responses for the ingestion loop
prospect_responses = [
    "Hi, I'm exploring AI solutions for our customer support team.",
    "We're TechCorp, a B2B SaaS company with about 200 employees in the healthcare tech space.",
    "I'm Sarah Johnson, VP of Customer Success. You can reach me at [email protected] or 555-0123.",
    "We're handling 1000+ support tickets daily and our team is overwhelmed. We need AI to handle tier-1 inquiries automatically and escalate complex issues to human agents.",
    "We're looking to implement within 3 months and have allocated $75,000 annually for this type of solution.",
    "Yes, I'm the final decision maker for customer success tools under $100k.",
    "We currently use Zendesk and have a team of 12 support agents. Our main pain point is response time - currently averaging 4 hours."
]

# Run the complete workflow
result = prospect_system.run_prospect_qualification(prospect_responses)

import { Orq } from "@orq-ai/node";

class SimpleProspectSystem {
    constructor(client) {
        this.client = client;
        
        // Agent deployment keys
        this.agents = {
            ingestion: "ingestionAgent",
            qualification: "qualificationAgent", 
            insertion: "insertionAgent"
        };
    }
    
    async runProspectQualification(prospectResponses) {
        console.log("🚀 Starting 3-Agent Prospect Qualification");
        console.log("=".repeat(50));
        
        // Step 1: Ingestion Loop
        const conversation = [];
        console.log("📞 INGESTION PHASE");
        console.log("-".repeat(30));
        
        for (const userMessage of prospectResponses) {
            console.log(`👤 Prospect: ${userMessage}`);
            
            // Add user message to conversation
            conversation.push({ role: "user", content: userMessage });
            
            // Call ingestion agent
            const response = await this.client.deployments.invoke({
                key: this.agents.ingestion,
                messages: conversation
            });
            
            const agentResponse = response.choices[0].message.content;
            conversation.push({ role: "assistant", content: agentResponse });
            
            console.log(`🤖 Ingestion Agent: ${agentResponse}`);
            console.log("-".repeat(30));
        }
        
        console.log("\n🔍 QUALIFICATION PHASE");
        console.log("-".repeat(30));
        
        // Step 2: Explicit Qualification Call  
        const qualificationPrompt = `
        Analyze this complete prospect conversation and provide qualification analysis:
        
        Conversation: ${JSON.stringify(conversation, null, 2)}
        
        Provide your analysis including lead score and qualification status.
        `;
        
        const qualificationResponse = await this.client.deployments.invoke({
            key: this.agents.qualification,
            messages: [{ role: "user", content: qualificationPrompt }]
        });
        
        const qualificationAnalysis = qualificationResponse.choices[0].message.content;
        console.log(`🤖 Qualification Agent: ${qualificationAnalysis}`);
        console.log("-".repeat(30));
        
        console.log("\n💾 INSERTION PHASE");
        console.log("-".repeat(30));
        
        // Step 3: Explicit Insertion Call
        const insertionPrompt = `
        Based on this conversation and qualification analysis, extract the prospect data and insert into CRM:
        
        Conversation: ${JSON.stringify(conversation, null, 2)}
        
        Qualification Analysis: ${qualificationAnalysis}
        
        Use the crminsert tool to add this prospect to the CRM system.
        `;
        
        const insertionResponse = await this.client.deployments.invoke({
            key: this.agents.insertion,
            messages: [{ role: "user", content: insertionPrompt }]
        });
        
        const insertionResult = insertionResponse.choices[0].message.content;
        console.log(`🤖 Insertion Agent: ${insertionResult}`);
        
        // Step 4: Extract and Print Insertion Payload
        const toolCalls = insertionResponse.choices[0].message.tool_calls || [];
        let insertionPayload = null;
        
        for (const toolCall of toolCalls) {
            if (toolCall.function.name === 'crminsert') {
                insertionPayload = JSON.parse(toolCall.function.arguments);
                break;
            }
        }
        
        console.log("\n🎯 FINAL INSERTION PAYLOAD");
        console.log("=".repeat(50));
        if (insertionPayload) {
            console.log(JSON.stringify(insertionPayload, null, 2));
        } else {
            console.log("No CRM insertion payload found");
        }
        
        return {
            conversation,
            qualificationAnalysis,
            insertionResult,
            insertionPayload
        };
    }
}

// Initialize the system
const client = new Orq({
    apiKey: process.env.ORQ_API_KEY || "__API_KEY__",
    environment: "production"
});

const prospectSystem = new SimpleProspectSystem(client);

// Example prospect responses for the ingestion loop
const prospectResponses = [
    "Hi, I'm exploring AI solutions for our customer support team.",
    "We're TechCorp, a B2B SaaS company with about 200 employees in the healthcare tech space.",
    "I'm Sarah Johnson, VP of Customer Success. You can reach me at [email protected] or 555-0123.",
    "We're handling 1000+ support tickets daily and our team is overwhelmed. We need AI to handle tier-1 inquiries automatically and escalate complex issues to human agents.",
    "We're looking to implement within 3 months and have allocated $75,000 annually for this type of solution.",
    "Yes, I'm the final decision maker for customer success tools under $100k.",
    "We currently use Zendesk and have a team of 12 support agents. Our main pain point is response time - currently averaging 4 hours."
];

// Run the complete workflow
const result = await prospectSystem.runProspectQualification(prospectResponses);