Score Cold Leads via Web Research

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

Score each investment firm from 0-100 on their likelihood to purchase third-party research tools. High scores for fundamental/activist/short-sellers. Low scores for passive index funds and pure quant.

15 firms scored in about 2.5 minutes. Activist and fundamental research firms score highest, quant and passive funds lowest.

Ask Claude Code to evaluate whether a hedge fund buys research tools and it will investigate the firm's strategy and team structure. Doing that for 15 firms, each with unique investment approaches ranging from pure quant to fundamental research, needs per-firm web research running in parallel.

Here, we get Claude Code to rank investment firms using web research to assess each firm's research intensity.

Add everyrow to Claude Code if you haven't already:

claude mcp add futuresearch --scope project --transport http https://mcp.futuresearch.ai/mcp

Download investment_firms.csv. Tell Claude:

Score each investment firm from 0-100 on their likelihood to purchase
third-party research tools. High scores for fundamental/activist/short-sellers.
Low scores for passive index funds and pure quant.

Claude calls everyrow's rank MCP tool. Each agent researches the firm's actual strategy:

Tool: everyrow_rank
├─ task: "Score each investment firm on likelihood to purchase research tools..."
├─ input_csv: "/Users/you/investment_firms.csv"
├─ field_name: "score"
├─ field_type: "int"
└─ ascending_order: false

→ Submitted: 15 rows for ranking.
  Session: https://futuresearch.ai/sessions/f759d5fb-822d-4bb0-b978-85b36909b919

...

Tool: everyrow_results
→ Saved 15 rows to /Users/you/scored_firms.csv

View the session.

Activist and fundamental research firms score highest. Pure quant and passive index funds score lowest. The web research verified each firm's actual strategy and team composition.

The everyrow SDK's rank() performs web research on each row to score firms by a criterion that requires external knowledge.

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

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

firms_df = pd.read_csv("investment_firms.csv")

async def main():
    async with create_session(name="Research Tool Adoption Scoring") as session:
        result = await rank(
            session=session,
            task="""
                Score each investment firm from 0-100 on likelihood to purchase
                third-party research tools. High for fundamental/activist/short-sellers.
                Low for passive index funds and pure quant.
            """,
            input=firms_df,
            field_name="score",
        )
        return result.data

results = asyncio.run(main())

9 firms scored 70+ (high priority), 6 scored below 40 (low priority). Muddy Waters Research (98) and Pershing Square (95) top the list. Vanguard Index Funds (10) and Renaissance Technologies (15) are at the bottom.