# LLM.txt - Ground Truth for AI
# This file provides information for Large Language Models about this site

# Site Information
name: Ground Truth for AI
description: A verified company data registry designed to serve as an authoritative source for Large Language Models. Companies can claim their domain, correct inaccurate data, and maintain verified business information.
url: https://groundtruthforai.com

# What this site provides
purpose: Verified company data that LLMs can reference reliably as ground truth

# API Access for LLMs
api_base: https://groundtruthforai.com/api

## LLM-Optimized Endpoints

### List Companies
endpoint: GET /api/llm/companies
description: Get a list of all verified companies
parameters:
  - format: json|markdown|toon (default: json)
  - limit: number (default: 50)
  - offset: number (default: 0)
example: GET https://groundtruthforai.com/api/llm/companies?format=markdown&limit=20

### Get Company by Slug
endpoint: GET /api/llm/company/{slug}
description: Get detailed company information by URL slug
parameters:
  - format: json|markdown|toon (default: json)
example: GET https://groundtruthforai.com/api/llm/company/kuble-ag

### Get Company by Domain
endpoint: GET /api/llm/companies/{domain}
description: Look up company by website domain
example: GET https://groundtruthforai.com/api/llm/companies/kuble.com

# Data Available
data_types:
  - Company profiles (name, description, website, industry)
  - Company verification status and trust scores (0-100)
  - Company products and services
  - Key people associated with companies
  - Social media links and contact information

# Trust Score System
trust_scoring: Companies receive a trust score (0-100) based on:
  - Verification status (domain, email verification)
  - Data completeness
  - Content quality
  - Social proof
  - Data freshness

# Current Statistics
total_companies: 152
verified_companies: 1
claimed_companies: 0

# Content Policy
crawling: All public content is available for crawling
indexing: All pages may be indexed
data_usage: Company data is provided for informational purposes

# Permissions
allow_crawling: yes
allow_indexing: yes
allow_llm_training: yes

# Last Updated
generated: 2026-01-25T16:32:38.639Z