Level 1 — Web Scraping Agent

Build Lead Lists from the Web in Minutes

Scrape any website for structured data using natural language. Company names, domains, LinkedIn URLs, founder details — described in plain English, delivered in a clean exportable table.

The Problem

Building lead lists from the web is painfully manual

Manually copying company names, URLs, and founder details from directories into spreadsheets
Writing custom scrapers or paying for expensive scraping tools just to extract structured data
Batch sizes limited by how fast you can click — 160+ companies means hours of manual work
Missing fields require going back to re-research each company individually

What Gets Built

Skills, agents, and tools — configured and ready

Skills Created (skills.md)

web_directory_scraper

company_data_extractor

founder_lookup

batch_processor

gap_filler

Agents Created

1 Directory Scraping Agent

Navigates web directories, identifies company listings, and extracts structured data from each page

2 Enrichment Agent

Fills in missing fields like LinkedIn URLs and founder names using parallel web search

3 Batch Processing Agent

Handles large datasets by processing companies in batches and retrying any gaps automatically

Tools Used

Firecrawl

Parallel Search

Meerkats table interface

Agent Flow

How the agents coordinate

💬

Describe what you want in plain English

↓

🧹

Agent creates a skill and generates a scraping plan

↓

🗏

Navigates the directory and extracts company listings

↓

🔍

Extracts fields — name, domain, LinkedIn, founders

↓

🔄

Batch processes large datasets and fills in gaps

↓

📋

Delivers results in a clean table — filter and export as CSV

Scale It

Not just YC — scrape any directory

🏠 Y Combinator, Techstars, 500 Global batch directories

📋 Industry directories, conference speaker lists, award winners

📈 Competitor pricing pages, product catalogs, job boards

Output

What you get

📋

Structured Lead Table

Company names, domains, descriptions, and categories — clean and ready for outreach or CRM import

👤

Founder Details

Founder names and LinkedIn profile URLs extracted automatically for each company

📦

CSV Export

Filter, sort, and export the full dataset as CSV — ready to drop into your outreach tool or CRM

Who This Is For

Built for anyone who needs structured data from the web

Sales Teams

Building targeted prospect lists

Scrape startup directories, conference attendee lists, or industry databases — get structured lead data ready for outreach in minutes.

VCs & Investors

Tracking accelerator batches

Pull the full YC, Techstars, or 500 Global batch with founder details and domains — monitor deal flow without manual research.

Market Researchers

Gathering competitive intelligence

Scrape competitor pricing, product catalogs, or review sites into structured tables for analysis and reporting.

Agencies

Prospecting into niche verticals

Build lead lists from any web directory — award winners, top companies lists, industry associations — without writing a single scraper.

Get Started

Build this agent in minutes

Describe what you want to scrape in plain English. The agent handles the rest — structured data out, ready to export.

Start Building →