AI Company Enrichment — Website to Firmographics, ICP & Tech Stack

Turn any company website into structured B2B data — fresh from the live site, not a stale database. Give this Actor a list of company URLs and get back clean JSON per company: firmographics, ideal customer profile, pricing model, tech stack hints, hiring signals, contacts, and social links.

Enrichment databases go stale the day they're built. This Actor reads the company's actual website right now — homepage, about, pricing, careers, and contact pages — and uses AI extraction to turn it into the fields your sales and GTM workflows need.

What data does this company enrichment API return?

For each company website you provide:

Field	Example
companyName, description	Clean identity + 1–2 sentence summary
industry, businessModel	"Technology", "B2B SaaS" / ecommerce / agency / marketplace…
icpSummary	Who their ideal customer is, in one sentence
pricingModel, pricingTiers	freemium / subscription / usage-based / custom quote + visible tiers
techStackHints	Technologies & integrations mentioned on the site
keyProducts	Product/service names
isHiring, hiringRoles	Careers-page signal — hiring = growing = buying
contactEmails, phones	Generic company contacts only (info@, sales@ — never personal data)
socialLinks, hqLocation, foundedYear, employeeCountEstimate	Firmographics
confidence, sourcePages	How sure the extraction is, and which pages it read

Who is this for?

• Clay users: call this Actor via HTTP API from a Clay table and enrich rows at a fraction of AI-agent credit costs
• n8n / Make / Zapier builders: drop it into automations as the enrichment step
• Sales & GTM teams: qualify inbound leads or build account lists with fresh firmographics and ICP fit
• Agencies: enrich prospect lists per client without per-seat data subscriptions
• AI agents: use it as a tool via MCP — structured JSON out, no parsing needed

How to use it

1. Paste company websites or domains (one per line)
2. Run — each company's homepage plus about/pricing/careers/contact pages are read and extracted
3. Export the dataset as JSON/CSV/Excel, or fetch it via API

Works with bare domains (stripe.com) or full URLs. Failed sites are reported as error rows and never charged.

Pricing

Pay per company enriched — a small Actor start fee plus a fixed price per successful enrichment. No subscription, no credits system, no seat licenses. Compare with AI enrichment credits elsewhere at $0.75–1.50 per row.

FAQ

How is this different from enrichment databases (Clearbit, Apollo)? Databases return what they crawled months ago. This reads the live website at run time — new pricing, current hiring, latest positioning — and tells you which pages it read.

Is this GDPR-safe? It extracts company-level data only. Contact emails are restricted to generic addresses (info@, sales@, hello@) — personal emails are never extracted.

Can I bring my own LLM key? Yes — add your OpenRouter API key in the input and extraction runs on your own account.

What if a website blocks the request or is down? You get an error row for that company and are not charged for it.

Can AI agents use this? Yes — it's exposed via Apify's MCP integration and returns strict JSON, so it works as an agent tool out of the box.

Support

Bugs, field requests, or a data source you want added? Open an issue in the Issues tab — issues are answered fast and feature requests shape the roadmap.