Multi-Stage Lead Qualification

Add the everyrow connector if you haven't already. Then upload a CSV of 20 investment funds and ask Claude:

I have a CSV of 20 investment funds. Run this pipeline: 1. Score each fund 0-100 on likelihood to adopt research tools. 2. Filter to funds scoring >= 50. 3. For remaining funds, estimate their investment team size. 4. Final screen: include if score >= 70 OR team size <= 5.

14 of 20 funds qualified after the three-stage pipeline. Results take about 4 minutes.

Claude Code handles a single scoring or filtering step natively. Chaining three stages (score by research adoption, filter by threshold, estimate team sizes, then screen by a compound rule) needs an approach where each stage passes its output to the next with custom logic between steps.

Here, we get Claude Code to run a three-stage qualification pipeline on 20 investment funds.

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

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

Tell Claude to run the multi-stage pipeline:

I have a CSV of 20 investment funds. Run this pipeline:
1. Score each fund 0-100 on likelihood to adopt research tools
2. Filter to funds scoring >= 50
3. For remaining funds, estimate their investment team size
4. Final screen: include if score >= 70 OR team size <= 5

Claude chains three everyrow operations with a pandas filter step:

Tool: everyrow_rank (Stage 1: Score by research adoption)
├─ task: "Score funds 0-100 on likelihood to adopt research tools"
├─ field_name: "score"
→ 20 rows scored in 73s. Session: https://futuresearch.ai/sessions/680fb865-...

[Claude filters to score >= 50: 15 rows remain]

Tool: everyrow_rank (Stage 3: Estimate team size)
├─ task: "Estimate investment team size per fund"
├─ field_name: "team_size_estimate"
→ 15 rows scored in 131s. Session: https://futuresearch.ai/sessions/ab54d4c9-...

Tool: everyrow_screen (Stage 4: Final inclusion)
├─ task: "Include if score >= 70 OR team <= 5"
→ 14 of 15 pass in 49s. Session: https://futuresearch.ai/sessions/5f18a461-...

14 of 20 funds qualified. The one excluded fund (Fixed Income Plus, score 55, team 12) fell below the score threshold and had too large a team.

The everyrow SDK chains multiple operations in a single session. This notebook demonstrates a three-stage lead qualification pipeline using rank(), pandas filtering, and screen().

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

import asyncio
import pandas as pd
from pydantic import BaseModel, Field
from everyrow import create_session
from everyrow.ops import rank, screen

class InclusionResult(BaseModel):
    passes: bool = Field(description="Include if score >= 70 OR team_size <= 5")

async def main():
    async with create_session(name="Multi-Stage Lead Screening") as session:
        # Stage 1: Score by research tool adoption
        scored = await rank(
            session=session,
            task="Score funds 0-100 on likelihood to adopt research tools",
            input=funds_df,
            field_name="score",
        )

        # Stage 2: Filter by threshold
        filtered = scored.data[scored.data["score"] >= 50].copy()

        # Stage 3: Research team sizes
        with_teams = await rank(
            session=session,
            task="Estimate investment team size per fund",
            input=filtered,
            field_name="team_size_estimate",
        )

        # Stage 4: Final screening
        final = await screen(
            session=session,
            task="Include if score >= 70 OR team size <= 5",
            input=with_teams.data,
            response_model=InclusionResult,
        )
        return final.data

results = asyncio.run(main())

The pipeline chains three everyrow operations in a single session: score, filter (pandas), team size estimation, and nuanced inclusion screening. 14 of 20 funds qualified. The single exclusion (Fixed Income Plus) had a moderate score (55) and large team (12).