{
  "id": 2028290,
  "title": "Company Enrichment Without the Per-Credit Tax: Website to Firmographics JSON With an LLM",
  "url": "https://urgent.news/2026/08/19/company-enrichment-without-the-per-credit-tax-website-to",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-19T22:08:44.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/benedictmendoza/company-enrichment-without-the-per-credit-tax-website-to-firmographics-json-with-an-llm-4b0j"
  },
  "original_language": "en",
  "account": "Most B2B enrichment vendors provide information that companies publish about themselves for free on their own websites. Customers pay per-credit prices for the reading, rather than the valuable data that would have disqualified non-fits in seconds. Using an LLM on company websites to fill out a fixed schema can extract firmographics, business models, pricing models, ICP summaries, tech stack hints, hiring signals, contacts, and social links for around a cent per company. The extraction process involves fetching the homepage, parsing internal links, selecting useful pages, stripping HTML, and making a single LLM call with a strict JSON schema. This approach can save significant costs compared to credit-based AI enrichment plans, which can cost $0.75–1.50 per row. However, there are failure modes to consider, such as hallucinated firmographics, issues with JS-only websites, personal data temptation, and URL normalization challenges. The author has packaged this process as an Apify Actor for easy integration into existing workflows.",
  "summary": "Most of what B2B enrichment vendors sell is information companies publish about themselves, for free, on their own websites. What you're paying per-credit prices for is mostly the reading. I noticed this while burning through enrichment credits on accounts that turned out to be obvious non-fits — agencies when I needed SaaS, enterprise when I needed SMB. The data that would have disqualified them…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}