Agent: Sales Lead Scoring

pip install kumo-rfm-mcp openai-agents==0.2.9 fsspec s3fs pandas

# Import required libraries
import asyncio
import os
from datetime import datetime, timedelta
from typing import List

from agents import Agent, Runner, gen_trace_id, trace
from agents.mcp import MCPServer, MCPServerStdio
import pandas as pd

import kumoai.experimental.rfm as rfm

import pandas as pd
from datetime import datetime, timedelta
from typing import List

def get_leads_from_previous_day(meeting_date: str, data_source: str) -> List[int]:
    """
    Get lead IDs from the day before the meeting date.
    
    Args:
        meeting_date: Format "YYYY-MM-DD" (e.g., "2025-06-02")
        data_source: Data source URL (e.g., S3 path)
    Returns:
        List of lead IDs from the previous day
    """
    # Get leads data from data source
    leads_data = pd.read_csv(data_source)
    
    # Parse meeting date
    meeting_dt = datetime.strptime(meeting_date, "%Y-%m-%d")
    previous_day = meeting_dt - timedelta(days=1)
    
    print(f"📅 Meeting date: {meeting_date}")
    print(f"🔍 Looking for leads from previous day: {previous_day.strftime('%Y-%m-%d')}")
    
    # Parse contact date
    leads_data['contact_date'] = pd.to_datetime(leads_data['contact_date'])
    
    # Filter by previous day
    filtered_leads = leads_data[
        leads_data['contact_date'].dt.date == previous_day.date()
    ]
    
    # Extract lead IDs
    previous_day_leads = filtered_leads['lead_id'].tolist()
    
    print(f"📊 Found {len(previous_day_leads)} leads from previous day: {previous_day_leads}")
    return previous_day_leads

# Test the function
DATA_SOURCE = "s3://kumo-sdk-public/rfm-datasets/lead_scoring/lead_scoring.csv"
MEETING_DATE = "2025-05-31"  # Demo date - in practice this would be today's date

test_leads = get_leads_from_previous_day(MEETING_DATE, DATA_SOURCE)

📅 Meeting date: 2025-05-31
🔍 Looking for leads from previous day: 2025-05-30
📊 Found 30 leads from previous day: [42, 322, 495, 834, 954, 1370, 1376, 1524, 2141, 2202, 2236, 2255, 2838, 2882, 2991, 3167, 3912, 3928, 4336, 4891, 5301, 5693, 5709, 5779, 5866, 6022, 6052, 6377, 6869, 7213]

   result = await Runner.run(starting_agent=lead_scoring_agent, input=request)

LEAD_SCORING_AGENT_PROMPT = """
You are a lead scoring agent for the daily sales team meeting. Your task is to:

1. Set up the KumoRFM model with the S3 lead scoring data
2. Make predictions for the provided lead IDs from yesterday
3. Create a prioritized outreach list for SDRs
4. Provide actionable insights

Workflow:
- add_table: s3://kumo-sdk-public/rfm-datasets/lead_scoring/lead_scoring.csv (name: "leads")
- inspect_table: Check the data structure
- finalize_graph: Prepare for predictions
- predict: Use query "PREDICT leads.converted=1 FOR leads.lead_id IN (<lead_ids>)"
- lookup_table_rows: Get lead details for the high-priority leads

Output format:
🚀 HIGH PRIORITY (>15% conversion probability)
🔥 MEDIUM PRIORITY (10-15% conversion probability)
⏳ LOW PRIORITY (<10% conversion probability)

For each lead, show: ID, probability, business segment, origin, lead type
Focus on actionable SDR guidance.
""".strip()

async def run_daily_sales_agent(mcp_server: MCPServer):
    """
    Run the daily lead scoring agent demo
    """
    # Daily Lead Scoring Agent
    lead_scoring_agent = Agent(
        name="Daily Lead Scoring Agent",
        model="gpt-5",
        instructions=LEAD_SCORING_AGENT_PROMPT,
        mcp_servers=[mcp_server],
    )

    # Get leads from previous day
    previous_day_leads = get_leads_from_previous_day(MEETING_DATE, DATA_SOURCE)
    
    if not previous_day_leads:
        print("❌ No leads found from previous day")
        return
    
    # Create the daily sales meeting request
    lead_ids_str = ",".join(map(str, previous_day_leads))
    request = f"""
    📋 DAILY SALES TEAM MEETING - {MEETING_DATE}

    We need to prioritize outreach for {len(previous_day_leads)} leads that came in yesterday.

    Lead IDs to score: {lead_ids_str}

    Please:
    1. Set up the lead scoring model 
    2. Score these leads for conversion probability
    3. Create a prioritized outreach list for our SDRs
    4. Provide insights on which leads to focus on first

    Data source: {DATA_SOURCE}
    """
    
    print("🎯 Daily Lead Scoring Meeting")
    print("=" * 50)
    print(f"Request: {request.strip()}")
    print("-" * 50)
    
    # Run the agent
    result = await Runner.run(starting_agent=lead_scoring_agent, input=request, max_turns=20)
    print("\n📊 SDR Prioritization Results:")
    print(result.final_output)
    
    return result

server = MCPServerStdio(
    name="kumo_rfm",
    args=["-m", "kumo_rfm_mcp.server"],
    env={"KUMO_API_KEY": os.environ["KUMO_API_KEY"]},
)

async def main():
    """
    Main demo function - connects to MCP server and runs the agent
    """
    print("🔌 Connecting to KumoRFM MCP Server...")
    
    async with MCPServerStdio(
        name="KumoRFM Server",
        params={
            "command": "python",
            "args": ["-m", "kumo_rfm_mcp.server"],
            "env": {
                "KUMO_API_KEY": os.getenv("KUMO_API_KEY"),
            }
        },
    ) as server:
        trace_id = gen_trace_id()
        with trace(workflow_name="Daily Lead Scoring Meeting", trace_id=trace_id):
            print(f"📊 View trace: https://platform.openai.com/traces/trace?trace_id={trace_id}\n")
            print("✅ MCP Server connected successfully!")
            print("🤖 Running Daily Lead Scoring Agent...\n")
            
            # Run the demo
            result = await run_daily_sales_agent(server)
            
            print("\n" + "="*60)
            print("🎉 DONE TODAY!")
            print("="*60)
            return result