Enrich Contacts with Company Data

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

Merge crm_contacts.csv with crm_funds.csv. Match contacts to their fund based on company name, ignoring legal suffixes (LLC, Inc, LP), abbreviations (Mgmt = Management, Tech = Technologies), and extra descriptors.

All 10 contacts matched in seconds for $0.00.

Claude Code's pandas merge works when column values match exactly. When "Bridgewater" needs to match "Bridgewater Associates" and "D.E. Shaw" needs to match "D. E. Shaw & Co.", the merge needs fuzzy matching that understands company name conventions.

Here, we get Claude Code to merge 10 contacts with 10 fund records, handling company name variations.

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

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

With both CSVs in your working directory, tell Claude:

Merge crm_contacts.csv with crm_funds.csv. Match contacts to their fund based
on company name, ignoring legal suffixes (LLC, Inc, LP), abbreviations
(Mgmt = Management, Tech = Technologies), and extra descriptors.

Claude calls everyrow's merge MCP tool:

Tool: everyrow_merge
├─ task: "Match contacts to their associated fund/company..."
├─ left_csv: "/Users/you/crm_contacts.csv"
├─ right_csv: "/Users/you/crm_funds.csv"
├─ merge_on_left: "company_name"
├─ merge_on_right: "fund_name"
└─ relationship_type: "one_to_one"

→ Submitted: 10 rows for merging.
  Session: https://futuresearch.ai/sessions/8e2eb233-e2cb-4144-b949-0e4fb4962cb2

Tool: everyrow_results
→ Saved 10 rows to /Users/you/merged_contacts.csv

All 10 matched in 9 seconds for $0.00. View the session.

The merge cascade handled all variations (abbreviations, suffixes, spacing) via fuzzy matching without needing LLM calls. When simpler methods work, everyrow uses them.

The everyrow SDK's merge() handles company name variations for CRM data imports.

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 merge

contacts_df = pd.read_csv("crm_contacts.csv")
funds_df = pd.read_csv("crm_funds.csv")

async def main():
    async with create_session(name="CRM Merge Workflow") as session:
        result = await merge(
            session=session,
            task="""
                Match contacts to their associated fund/company.
                Company names may vary between tables. Match on core company name,
                ignoring legal suffixes, abbreviations, and descriptors.
            """,
            left_table=contacts_df,
            right_table=funds_df,
            merge_on_left="company_name",
            merge_on_right="fund_name",
        )
        return result.data

merged = asyncio.run(main())

All 10 contacts matched at $0.00. The fuzzy matching cascade handled abbreviations ("Mgmt" to "Management"), legal suffixes ("LLC"), and spacing variations without needing LLM calls.