Score Leads from Fragmented Data

Add the FutureSearch connector if you haven't already. Then upload b2b_companies.csv and ask Claude:

Score each company from 0-100 on their likelihood of suffering from data fragmentation challenges. High scores for multi-location operations, M&A history, disconnected systems. Low scores for single-location, cloud-native, integrated stacks.

Results take about 40 seconds.

Go to futuresearch.ai/app, upload b2b_companies.csv, and enter:

Score each company from 0-100 on their likelihood of suffering from data fragmentation challenges. High scores for multi-location operations, M&A history, disconnected systems. Low scores for single-location, cloud-native, integrated stacks.

The FutureSearch SDK's rank() scores every row using LLM reasoning. For B2B lead scoring, it evaluates operational complexity from company descriptions.

pip install futuresearch
export FUTURESEARCH_API_KEY=your_key_here  # Get one at futuresearch.ai/app/api-key

import asyncio
import pandas as pd
from futuresearch import create_session
from futuresearch.ops import rank

companies_df = pd.read_csv("b2b_companies.csv")

async def main():
    async with create_session(name="Data Fragmentation Lead Scoring") as session:
        result = await rank(
            session=session,
            task="""
                Score each company from 0-100 on data fragmentation risk.
                High (70-100): Multiple locations, M&A history, disconnected systems.
                Low (0-30): Single location, cloud-native, integrated stack.
            """,
            input=companies_df,
            field_name="score",
        )
        return result.data.sort_values("score", ascending=False)

results = asyncio.run(main())