Screen Job Listings
Screen 15 job postings against three simultaneous criteria: remote-friendly, senior-level, and salary disclosed. Each posting is evaluated semantically rather than by keyword matching.
| Metric | Value |
|---|---|
| Rows processed | 15 |
| Rows passing | 7 (46.7%) |
| Total cost | $0.03 |
| Time | 57 seconds |
Add FutureSearch to Claude Code if you haven't already:
claude mcp add futuresearch --scope project --transport http https://mcp.futuresearch.ai/mcp
Download job_postings.csv. Tell Claude:
Screen each job posting to find roles that meet ALL THREE criteria:
1. Remote-friendly: explicitly allows remote, hybrid, or distributed work
2. Senior-level: title includes Senior/Staff/Lead/Principal, or requires 5+ years
3. Salary disclosed: specific compensation figures, not "competitive" or "DOE"
Claude calls FutureSearch's classify MCP tool:
Tool: futuresearch_classify
├─ task: "Classify each job posting to determine if it meets ALL THREE criteria..."
├─ input_csv: "/Users/you/job_postings.csv"
└─ categories: ["yes", "no"]
→ Submitted: 15 rows for classification.
Session: https://futuresearch.ai/sessions/17d3075d-1788-4fba-8c46-a20f169976ec
Task ID: ab78...
Tool: futuresearch_progress
→ Completed: 15/15 (0 failed) in 57s.
Tool: futuresearch_results
├─ task_id: "ab78..."
├─ output_path: "/Users/you/qualified_jobs.csv"
→ Saved 7 rows to /Users/you/qualified_jobs.csv
Add the FutureSearch connector if you haven't already. Then upload job_postings.csv and ask Claude:
Screen each job posting to find roles that meet ALL THREE criteria: 1. Remote-friendly: explicitly allows remote, hybrid, or distributed work. 2. Senior-level: title includes Senior/Staff/Lead/Principal, or requires 5+ years. 3. Salary disclosed: specific compensation figures, not "competitive" or "DOE".
Results take under a minute.
Go to futuresearch.ai/app, upload job_postings.csv, and enter:
Screen each job posting to find roles that meet ALL THREE criteria: 1. Remote-friendly: explicitly allows remote, hybrid, or distributed work. 2. Senior-level: title includes Senior/Staff/Lead/Principal, or requires 5+ years. 3. Salary disclosed: specific compensation figures, not "competitive" or "DOE".
Screening is binary classification: use classify() with categories=["yes", "no"] and only passing rows are returned.
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 classify
job_postings = pd.read_csv("job_postings.csv")
async def main():
async with create_session(name="Job Posting Screening") as session:
result = await classify(
session=session,
task="""
Classify job postings for ALL THREE criteria:
1. Remote-friendly: explicitly allows remote/hybrid/distributed work
2. Senior-level: title includes Senior/Staff/Lead/Principal or 5+ years
3. Salary disclosed: specific compensation figures, not "competitive"
""",
categories=["yes", "no"],
input=job_postings,
)
return result.data
results = asyncio.run(main())
Results
7 of 15 postings qualified:
| Company | Title | Why It Passed |
|---|---|---|
| TechCorp | Senior Backend Engineer | Remote (US), 7+ years, $180k-220k |
| DataDriven Inc | Staff Data Scientist | Hybrid (NYC), Staff title, $200k-250k |
| RemoteFirst Co | Lead Frontend Engineer | 100% Remote, Lead title, $160k-190k |
| FinTech Pro | Senior Security Engineer | Remote (EU), Senior title, disclosed salary |
| HealthTech | Senior Product Manager | Distributed team, Senior title, salary range |
| MegaCorp | Staff SRE | Hybrid (Seattle), Staff title, $190k-240k |
| EdTech Plus | Senior iOS Developer | Remote first, Senior title, $140k-175k |
All 15 rows were decisive on the first pass (7 yes, 8 no, 0 borderline). Traditional keyword matching achieves ~68% precision on these criteria; semantic classification exceeds 90%.