Company Research Agent: website to company profile, contacts, tech stack and your questions answered

Give company websites, get a sales-ready profile for each: what the company does, who it sells to, its products and prices, where it is, the leaders its site names, emails, phones and social profiles, and the technologies the site runs on.

Add your own research questions (Do they offer an API?, Which countries do they ship to?) and each is answered from the company's pages with the page it came from. Facts from the site only: when the site does not say, the field is empty, never guessed.

What you get

Field	What it holds
Profile	companyName, legalName, oneLiner, description, industry, businessModel, offerings, pricing, hasFreePlanOrTrial, targetCustomers, industriesServed, customersNamed, headquarters, otherLocations, foundedYear, employeesStated, leadership, hiring, openRoles, certifications, siteLanguages
Contacts	primaryEmail, primaryPhone, emails (with source page), phones (E.164), socials, contactPages, contactFormPages
Research	answers (question, answer, sourceUrl), technologies, pagesRead; optional pageTexts
SUMMARY	companies researched, failures, the model used, what was charged

What people use it for

• Lead qualification: what each prospect sells, to whom and at what price, before you reach out
• Account research: your own questions answered for a whole list of companies
• Market maps: offerings, pricing and customers across a market's companies
• CRM enrichment: contacts, location, industry and tech stack per domain

How to use it

1. Add company websites (links or bare domains, or a file with one per line).
2. Optionally add research questions.
3. Click Start and open the Company profiles table.

Input

Field	Example	Notes
Company websites	example.com	One per company
Research questions	Do they offer an API or integrations?	Answered with their source page
Profile language	English	The site can be in any language
Most pages per website	8	Up to 20
Also the pages' text	off	For your own AI steps
JavaScript pages	auto	Chrome only when needed

Output

Each result is one row in the run's dataset (download it as JSON, CSV, Excel, XML or HTML, or read it through the API). An example row (values shortened):

{
  "url": "https://www.example.org/",
  "domain": "example.org",
  "status": "ok",
  "companyName": "Example",
  "legalName": "Example Software Foundation",
  "oneLiner": "An open-source programming language that lets you work quickly and integrate systems more effectively.",
  "industry": "Software",
  "businessModel": "non-profit",
  "offerings": [
    {
      "name": "The Example language",
      "type": "product",
      "description": "An open-source, high-level programming language."
    },
    {
      "name": "Package index",
      "type": "service",
      "description": "A repository of community-contributed packages."
    }
  ],
  "pricing": [],
  "customersNamed": [
    "(11 organisations named on its success-stories page)"
  ],
  "headquarters": {
    "city": "(city)",
    "region": "OR",
    "country": "USA"
  },
  "leadership": [
    {
      "name": "(name)",
      "title": "Chair"
    },
    {
      "name": "(name)",
      "title": "Executive Director"
    }
  ],
  "primaryEmail": "jobs@example.org",
  "emails": [
    {
      "email": "jobs@example.org",
      "source": "mailto",
      "sourceUrl": "https://www.example.org/jobs/"
    }
  ],
  "socials": {
    "x": [
      "https://x.com/example"
    ],
    "github": [
      "https://github.com/example"
    ]
  },
  "technologies": [
    "jQuery",
    "Plausible"
  ],
  "answers": [
    {
      "question": "How can someone donate or become a member?",
      "answer": "Through direct donations, supporting memberships or matching donations, and by signing up on the membership pages.",
      "sourceUrl": "https://www.example.org/foundation/board/"
    }
  ],
  "model": "google/gemini-3.8-flash",
  "aiCostUsd": 0.0105
}

From a run on 17 October 2026 on a software foundation's website (names and address replaced): 8 pages read, the registered name, a non-profit model, 11 organisations named as users, the headquarters, the board and the executive director, two emails, three social profiles, and one research question answered with its source page; the other came back empty because no page answered it. AI usage $0.0105.

Pricing

• $0.02 per company researched into a profile with its contacts
• Free: websites that cannot be read and profiles that fail
• The AI model that writes the profile (Google's Gemini Flash) is billed by Apify's AI gateway at its exact cost: about $0.01 a company from 8 pages (measured 17 October 2026); Apify charges free-plan accounts 10 times the AI usage

What typical jobs cost at the list price:

Job	Cost
1 company	$0.02 + about $0.01 AI
100 companies	$2 + about $1 AI
1,000 companies	$20 + about $10 AI

On Apify's Scale and Business plans the per-event prices are lower (Store discounts). Set Maximum cost per run and the Actor stops cleanly when it is reached: you never pay more than that.

Tips

• Ask the questions your sales team asks on every call: they are answered for every company in the list.
• Upload a CSV or text file of domains (Link remote text file) for large lists.
• Turn on the pages' text to run your own prompts on it with the Bulk AI Runner.

Use it through the API

Python

from apify_client import ApifyClient

client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("zaiq/company-research-agent").call(run_input={"websites": ["example.com"], "questions": ["Do they offer an API or integrations?"]})
for row in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(row)

JavaScript

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });
const run = await client.actor('zaiq/company-research-agent').call({"websites": ["example.com"], "questions": ["Do they offer an API or integrations?"]});
const { items } = await client.dataset(run.defaultDatasetId).listItems();

HTTP (one call, results back)

curl -X POST 'https://api.apify.com/v2/acts/zaiq~company-research-agent/run-sync-get-dataset-items?token=<YOUR_APIFY_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{"websites": ["example.com"], "questions": ["Do they offer an API or integrations?"]}'

Integrations and schedules

• Schedules: run it every hour, day or week from the Apify Console (Schedules) and keep a history of results.
• Make, Zapier, n8n, Google Sheets, Slack, Airtable: connect it through Apify's integrations, or send each finished run to a webhook.
• Datasets: results stay in the run's dataset; export them or read them by API whenever you need them.

Use it with AI agents (MCP)

Add Apify's MCP server (https://mcp.apify.com) to Claude, ChatGPT, Cursor, VS Code or any MCP client. The agent can find this Actor and run it for you: ask it for "research these five company websites and tell me who they sell to and what they charge". AI agents can also pay for runs directly through Apify's agentic payments.

Limits

• Only what the company's own website says: no business registries, social networks or paid databases.
• Employee counts, revenue and founding years appear only when a page states them.
• Sites that block datacenter addresses cannot be read (free); robots.txt is respected by default.
• Like any AI, the profile can misread a page: the pages read are listed in every row to check against.

FAQ

Where does the data come from?

The company's own website: the home page, contact, about, team, imprint, careers and legal pages, then its pricing, product and customer pages.

Do I need an AI key?

No. Apify's AI gateway runs the model and bills its exact cost to your Apify account.

Does it find personal emails?

It finds the addresses the website publishes, ranked with the company's generic addresses first; it does not guess addresses.

Can I get only the contacts?

Use the Contact Details Extractor: contacts only, without the AI profile.

Related Actors from Zaiq

• contact-details-extractor: contacts only, from any website
• bulk-ai-runner: your own prompt on every company
• ai-web-scraper: any page to JSON with a prompt
• llm-website-crawler: whole sites as Markdown

Support

Questions, a site that changed, or a field you need? Open an issue on this Actor's Issues tab: we answer there, usually within a day.

---

Also found as: company research, company enrichment, ai company research, website enrichment, company profile scraper, lead enrichment, account research, firmographics, tech stack lookup.