AI Company Researcher Agent

AI Company Researcher Agent

AI-powered agent that performs comprehensive company research and generates detailed business reports.

AIAGENTSDEVELOPER_TOOLSApify

This Apify Actor is an AI-powered agent that performs comprehensive company research and generates detailed business reports. It leverages the Gemini 2.0 Flash model to research companies, collect data from multiple sources, and produce an in-depth business analysis report. The agent offers flexibility in both data collection and reporting, adapting its output to the available information.

Features

  • Adaptive Company Research: Uses AI to find and collate company information based on what's available
  • Multi-source Data Collection: Gathers data from LinkedIn, Trustpilot, Similarweb, and Google Maps
  • Flexible Business Reports: Generates tailored markdown reports that adapt to the available data
  • Comprehensive Analysis: Applies relevant business frameworks based on the company and available information
  • Structured Data Output: All collected data is available in structured JSON format

Business Analysis Approaches

The report generation is adaptable and may include analysis frameworks such as:

  1. SWOT Analysis (Strengths, Weaknesses, Opportunities, Threats)
  2. PESTLE Analysis (Political, Economic, Social, Technological, Legal, Environmental factors)
  3. Porter's Five Forces (Competitive Rivalry, Supplier Power, Buyer Power, Threat of Substitution, Threat of New Entry)
  4. Business Model Canvas Elements (Value Propositions, Customer Segments, Key Resources, etc.)
  5. Competitor Analysis
  6. Market Positioning
  7. Digital Presence Evaluation (based on social media profiles and web analytics)
  8. Customer Sentiment Analysis (based on reviews if available)

The agent tailors its analysis to the available data and the specific company context, selecting the most relevant frameworks rather than forcing information into a rigid structure.

Input

The Actor accepts a single input parameter:

1{
2  "company_name": "Apify"
3}
FieldTypeDescription
company_nameStringName of the company to research

Output

The Actor produces two main outputs:

  1. Business Report: A comprehensive markdown file stored in the Key-Value store with the key report
  2. Structured Data: A JSON output in the default dataset containing all collected company information

Example Output Structure

1{
2  "company_name": "Apify",
3  "website_url": "https://apify.com",
4  "short_description": "...",
5  "industry": "...",
6  "business_model": "...",
7  "target_market": "...",
8  "products_services": [...],
9  "founding_year": 2015,
10  "funding_information": "...",
11  "estimated_revenue": "...",
12  "key_employees": [...],
13  "employee_count": "...",
14  "headquarters_location": "...",
15  "competitors": [...],
16  "market_position": "...",
17  "social_media": {
18    "linkedin": "https://www.linkedin.com/company/apify/",
19    "twitter": "https://twitter.com/apify",
20    "...": "..."
21  },
22  "latest_news": [...],
23  "linkedin_data": {...},
24  "trustpilot_data": [...],
25  "similarweb_data": {...},
26  "google_maps_data": [...],
27  "extra_data": {...},
28  "report": "# Comprehensive Business Report for Apify

## Executive Summary
..."
29}

Data Sources

The Actor collects information from the following data sources:

  • Google Search: For basic company information
  • LinkedIn: Company profile, employee count, specialties, industry
  • Trustpilot: Customer reviews and ratings
  • Similarweb: Website analytics, traffic sources, demographics
  • Google Maps: Physical locations, customer reviews

Implementation

The Actor is built using:

  • Python: Core programming language
  • Apify SDK: For Actor lifecycle management
  • Pydantic-AI: For structured LLM agents and function calling
  • Gemini 2.0 Flash: Google's LLM for AI-powered research and analysis

Architecture

The Actor uses a multi-stage process:

  1. Research Phase: An AI agent researches comprehensive company information using web searches
  2. Data Collection Phase: Targeted data collection from external APIs (LinkedIn, Trustpilot, etc.)
  3. Report Generation Phase: A second AI agent analyzes collected data and generates a tailored business report

License

This project is licensed under the MIT License.

Frequently Asked Questions

Is it legal to scrape job listings or public data?

Yes, if you're scraping publicly available data for personal or internal use. Always review Websute's Terms of Service before large-scale use or redistribution.

Do I need to code to use this scraper?

No. This is a no-code tool — just enter a job title, location, and run the scraper directly from your dashboard or Apify actor page.

What data does it extract?

It extracts job titles, companies, salaries (if available), descriptions, locations, and post dates. You can export all of it to Excel or JSON.

Can I scrape multiple pages or filter by location?

Yes, you can scrape multiple pages and refine by job title, location, keyword, or more depending on the input settings you use.

How do I get started?

You can use the Try Now button on this page to go to the scraper. You’ll be guided to input a search term and get structured results. No setup needed!