Introducing Jev + Firecrawl company data
Pull company records from Alexandria and let Jev classify them.
We sorted 146 startups by who buys from them in 2.2 seconds.
Perfect for lead scoring, account research & market maps at lightning speed!
https://firecrawl.dev/alexandria/categories/company https://t.co/TaUxre8bqd
Key Takeaways
Two products used together, not one new feature. Firecrawl gets the company data (from its Alexandria directory or by scraping each company's website), and Jev, a model from a separate company (TypeSafe AI), answers set questions about each company.
Jev returns typed answers, not prose: a yes/no probability, a pick from your own labels, or a score, each with a confidence number. That is what makes it usable for scoring: low-confidence answers go to a person instead of being trusted.
It works on your own list, not just Firecrawl's records. The "Qualify Leads" example in Firecrawl's docs batch-scrapes a list of homepages, asks Jev a choice question about each one, and sends the uncertain ones for human review.
Alexandria is Firecrawl's directory of 377 data providers behind one Firecrawl key, about 70 of them in the company category (People Data Labs, for example, returns name, website, industry, headcount and location). Each call costs Firecrawl credits (a People Data Labs lookup is 50), and every account gets 1,000 free credits a month.
Jev is billed separately by TypeSafe (also reachable through OpenRouter): $0.042 per million input tokens, output free. Rough cost to score 1,000 websites: about 1,000 Firecrawl scrape credits plus pennies of Jev.