FutureSearch Logofuturesearch
  • Solutions
  • Pricing
  • Research
  • Docs
  • Evals
  • Blog
  • Company
  • LiteLLM Checker
  • Get Researchers
FutureSearch Logo

General inquiry? You can reach us at hello@futuresearch.ai.

Company

Team & CareersPressPrivacy PolicyTerms of Service

Developers

SDK DocsAPI ReferenceCase StudiesGitHubSupport

Integrations

Claude CodeCursorChatGPT CodexClaude.ai

Follow Us

X (Twitter)@dschwarz26LinkedIn
FutureSearchdocs
Your research team
Installation
  • All install methods
  • Claude.ai
  • Claude Cowork
  • Claude Code
  • Web App
  • Python SDK
  • Skill
  • MCP Server
Reference
  • API Key
  • classify
  • dedupe
  • forecast
  • merge
  • rank
  • agent_map
  • Progress Monitoring
  • Chaining Operations
Guides
  • LLM-Powered Data Labeling
  • Add a Column via Web Research
  • Classify and Label Rows
  • Deduplicate Training Data
  • Filter a Dataset Intelligently
  • Find Profitable Polymarket Trades
  • Forecast Outcomes for a List of Entities
  • Value a Private Company
  • Join Tables Without Shared Keys
  • Rank Data by External Metrics
  • Resolve Duplicate Entities
  • Scale Deduplication to 20K Rows
  • Turn Claude into an Accurate Forecaster
Case Studies
  • Deduplicate Contact Lists
  • Deduplicate CRM Records
  • Enrich Contacts with Company Data
  • Fuzzy Match Across Tables
  • Link Records Across Medical Datasets
  • LLM Cost vs. Accuracy
  • Merge Costs and Speed
  • Merge Thousands of Records
  • Multi-Stage Lead Qualification
  • Research and Rank Web Data
  • Run 10,000 LLM Web Research Agents
  • Score Cold Leads via Web Research
  • Score Leads from Fragmented Data
  • Screen 10,000 Rows
  • Screen Job Listings
  • Screen Stocks by Economic Sensitivity
  • Screen Stocks by Investment Thesis
FutureSearchby futuresearch
by futuresearch

Research and Rank Web Data

Research and rank 30 Texas cities by residential building permit processing time. Each city publishes permit data on a different government website in a different format, requiring 30 independent research agents.

MetricValue
Rows processed30
Cost$0.88
Time2.5 minutes

Add FutureSearch 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 FutureSearch's rank MCP tool. Each agent conducts independent web research:

Tool: futuresearch_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: futuresearch_results
→ Saved 30 rows to /Users/you/permit_times.csv

View the session.

Add the FutureSearch 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.

Results take about 2.5 minutes.

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.

The FutureSearch 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.

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 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())

Results

Top 10 fastest cities:

CityPopulationRegionPermit Days
San Antonio1,500,000South Texas3
Irving240,000North Texas3
McAllen145,000Rio Grande Valley3
Plano285,000North Texas5
Lubbock260,000West Texas5
Brownsville185,000Rio Grande Valley5
Killeen155,000Central Texas5
Waco140,000Central Texas6
Fort Worth920,000North Texas7
Garland240,000North Texas7

Slowest: Denton (31 days), Round Rock (30 days), Houston (30 days). Average across all 30 cities: 10.3 days.

By region: Rio Grande Valley cities are fastest (4.0 days avg), Central Texas slowest (15.3 days avg). Each result includes detailed source citations with URLs from official city permit department pages.