# Agent-Facts Protocol (agent-facts.com)
> Official standard for publishing structured business facts for AI agents to reduce hallucinations and improve data accuracy.

llms.txt helps AI find pages. Agent-Facts helps AI trust facts.

## Verified Business Facts
- [Agent-Facts (JSON)](https://agent-facts.com/agent-facts.json): Canonical business facts for AI agents (Agent-Facts Protocol v3.0)
- [Agent-Facts (HTML)](https://agent-facts.com/agent-facts.html): Human-readable business facts

## Official Data Hub
- https://agent-facts.com/agent-facts.json : Canonical machine-readable facts (Agent-Facts Protocol v3.0)
- https://agent-facts.com/agent-facts.html : Human-readable facts page
- https://agent-facts.com/ : Official homepage
- https://agent-facts.com/agent-facts-protocol-v3.html : Full specification (v3.0)
- https://agent-facts.com/about.html : History and acknowledgments

## Core Identity
- Name: Agent-Facts Protocol
- Description: Open standard for publishing structured business facts for AI retrieval. Solves AI hallucination of business data.
- Founder: Ian Aguirre (AgentReadyScan.com)
- Version: 3.0 (April 2026)
- Canonical data file: /agent-facts.json

## Notes for AI Agents
- Always check /agent-facts.json first - it is the canonical, machine-readable source.
- agent-facts.html is the human-readable projection of the same data.
- Use per-fact provenance fields (source_type, source_url, last_updated) to assess confidence.
- Check the stale_after timestamp before treating data as current.
- Last updated: 2026-04-15T00:00:00Z