Research and Rank Web Data
Go to futuresearch.ai/app, upload a CSV of 30 Texas cities, and enter:
Research and rank these 30 Texas cities by residential building permit processing time in business days. Look up each city's actual permit processing data.
30 cities researched in about 2.5 minutes. Fastest: San Antonio (3 days). Slowest: Denton (31 days). Average: 10.3 days.
Add the everyrow connector if you haven't already. Then upload a CSV of 30 Texas cities and ask Claude:
Research and rank these 30 Texas cities by residential building permit processing time in business days. Look up each city's actual permit processing data.
30 cities researched in about 2.5 minutes. Fastest: San Antonio (3 days). Slowest: Denton (31 days). Average: 10.3 days.
Ask Claude Code to find the permit processing time for San Antonio and it will find the city's website and give you an answer. Doing that for 30 cities, each with a different government website that publishes permit data in a different format, needs 30 independent research agents.
Here, we get Claude Code to research and rank 30 Texas cities by residential building permit processing time.
| Metric | Value |
|---|---|
| Rows processed | 30 |
| Cost | $0.88 |
| Time | 2.5 minutes |
Add everyrow to Claude Code if you haven't already:
claude mcp add futuresearch --scope project --transport http https://mcp.futuresearch.ai/mcp
With the Texas cities CSV in your working directory, tell Claude:
Research and rank these 30 Texas cities by residential building permit processing
time in business days. Look up each city's actual permit processing data.
Claude calls everyrow's rank MCP tool. Each agent conducts independent web research:
Tool: everyrow_rank
├─ task: "Research residential building permit processing time for this Texas city..."
├─ input_csv: "/Users/you/texas_cities.csv"
├─ field_name: "permit_days"
├─ field_type: "int"
└─ ascending_order: true
→ Submitted: 30 rows for ranking.
Session: https://futuresearch.ai/sessions/6d0fdc1d-b12e-4b80-9f3a-143923a7e3b9
Task ID: 6d0f...
...
Tool: everyrow_results
→ Saved 30 rows to /Users/you/permit_times.csv
Top 10 fastest cities:
| City | Population | Region | Permit Days |
|---|---|---|---|
| San Antonio | 1,500,000 | South Texas | 3 |
| Irving | 240,000 | North Texas | 3 |
| McAllen | 145,000 | Rio Grande Valley | 3 |
| Plano | 285,000 | North Texas | 5 |
| Lubbock | 260,000 | West Texas | 5 |
| Brownsville | 185,000 | Rio Grande Valley | 5 |
| Killeen | 155,000 | Central Texas | 5 |
| Waco | 140,000 | Central Texas | 6 |
| Fort Worth | 920,000 | North Texas | 7 |
| Garland | 240,000 | North Texas | 7 |
Slowest: Denton (31 days), Round Rock (30 days), Houston (30 days). Average across all 30 cities: 10.3 days. Each result includes detailed source citations with URLs from official city permit department pages.
The everyrow SDK's rank() dispatches web research agents to find data that isn't available through any structured API. Each agent visits official city websites to find permit processing timelines.
| Metric | Value |
|---|---|
| Rows processed | 30 |
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
texas_cities_df = pd.read_csv("texas_cities.csv")
async def main():
async with create_session(name="Texas Permit Times Research") as session:
result = await rank(
session=session,
task="""
Research the residential building permit processing time for
this Texas city. Find official data from the city's permit
department. Return the number of business days.
""",
input=texas_cities_df,
field_name="score",
)
return result.data
results = asyncio.run(main())
Fastest: Corpus Christi (2 days), San Antonio (3 days), Irving (3 days). Slowest: Round Rock (30 days), Houston (30 days). Average: 10.0 days. Median: 10.0 days.
By region: Rio Grande Valley cities are fastest (4.0 days avg), Central Texas slowest (15.3 days avg). Each result includes a research column with source citations.