Screen Stocks by Investment Thesis

Add the everyrow connector if you haven't already. Then upload your S&P 500 CSV and ask Claude:

Screen to find companies with high-quality recurring revenue business models (>75% recurring) that would also benefit from escalating US-China tensions over Taiwan. Include CHIPS Act beneficiaries, defense contractors, cybersecurity, reshoring plays. Exclude companies dependent on Taiwan manufacturing or with significant China revenue at risk.

63 of 502 companies pass (12.5%). Results take about 15.5 minutes.

Ask Claude Code to evaluate whether Apple has >75% recurring revenue and benefits from US-China tensions, and it will research both questions and give you a thorough answer. Applying that same depth of analysis to all 502 S&P 500 companies needs 502 independent research tasks running in parallel.

Here, we get Claude Code to screen the S&P 500 for companies with >75% recurring revenue that would also benefit from escalating US-China tensions over Taiwan.

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

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

With your S&P 500 CSV in the working directory, tell Claude:

Screen this S&P 500 dataset to find companies with high-quality recurring revenue
business models that would also benefit from escalating US-China tensions over Taiwan.

Recurring revenue >75%: Subscription services, long-term contracts, maintenance
agreements, royalty streams. Not one-time product sales or project-based work.

Taiwan tensions beneficiary: CHIPS Act beneficiaries, defense contractors,
cybersecurity, reshoring plays, alternative supply chain providers. Exclude
companies dependent on Taiwan manufacturing or with significant China revenue at risk.

Claude calls everyrow's screen MCP tool, which runs a two-pass pipeline: a fast first pass triages all rows, then a careful second pass re-evaluates borderline cases:

Tool: everyrow_screen
├─ task: "Find companies with high-quality recurring revenue business models..."
├─ input_csv: "/Users/you/sp500.csv"
└─ response_schema: null

→ Submitted: 502 rows for screening.
  Session: https://futuresearch.ai/sessions/374a9a36-55e7-4b7c-92e8-6d396b40071b
  Task ID: fc3d...

Tool: everyrow_progress
├─ task_id: "fc3d..."
→ Running: 0/502 complete, 502 running (30s elapsed)

...

Tool: everyrow_progress
→ Completed: 502/502 (0 failed) in 930s.

Tool: everyrow_results
├─ task_id: "fc3d..."
├─ output_path: "/Users/you/thesis_screen.csv"
→ Saved 63 rows to /Users/you/thesis_screen.csv

63 of 502 companies passed (12.5%). View the session.

Sample passing companies:

Each result includes research explaining the decision. For ServiceNow: "97% of revenue from subscriptions. Critical enabler of cybersecurity and digital transformation for US federal government infrastructure."

The everyrow SDK screens every row with LLM-powered web research agents, handling the batching and parallelism in a single function call.

Here, we screen the S&P 500 for companies with >75% recurring revenue that benefit from US-China tensions over Taiwan.

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 screen

stocks = pd.read_csv("sp500.csv")

class ScreenResult(BaseModel):
    passes: bool = Field(
        description="True if company has >75% recurring revenue AND is a Taiwan tensions beneficiary"
    )

async def main():
    async with create_session(name="Stock Screening: Investment Thesis") as session:
        result = await screen(
            session=session,
            task="""
                Find companies with high-quality recurring revenue business models
                that would also benefit from escalating US-China tensions over Taiwan.

                Recurring revenue >75%: Subscription services, long-term contracts,
                maintenance agreements, royalty streams.

                Taiwan tensions beneficiary: CHIPS Act beneficiaries, defense contractors,
                cybersecurity, reshoring plays, alternative supply chain providers.
            """,
            input=stocks,
            response_model=ScreenResult,
        )
        return result.data

results = asyncio.run(main())

63 companies passed. Sector breakdown: Information Technology (13), Utilities (13), Financials (12), Industrials (11). The screen identified cybersecurity firms (CrowdStrike, Palo Alto Networks), defense contractors (General Dynamics, Northrop Grumman), and infrastructure companies with high recurring revenue.