AI Discovery File Specifications
Comprehensive format documentation for all 10 core AI Discovery Files
These specifications define the canonical structure, required and optional fields, validation rules, and implementation guidance for each AI Discovery File format. Each specification includes machine-readable versions (JSON and YAML) and links to canonical examples.
The specification defines three conformance classes: Essential (2 files), Recommended (6 files), and Complete (all 10 files). Each individual specification page lists the classes that include the file.
For tools and validators: the Specification Registry (registry.json) is the machine-readable single source of truth listing every file with its media type, paired files, precedence rules, and schema URL.
Start with the Quick Start Guide to implement AI Visibility in as little as 30 minutes with just 2 files. The Quick Start tiers map directly to the formal conformance classes.
AI Discovery Files Specification on GitHub
The complete normative specification for all 10 file types, published as an open RFC-style document under CC BY 4.0. Includes JSON Schemas, a command-line validator, example files, and test vectors.
- RFC 2119 Keywords
- JSON Schemas
- CLI Validator
- Test Vectors
- CC BY 4.0
Core Specifications
llms.txt
AI-readable business identity and context using Markdown format (llmstxt.org convention)
llm.txt
Compatibility variant — should redirect (301) to llms.txt
llms.html
Human-readable HTML presentation with Schema.org structured data
ai.txt
AI usage permissions, restrictions, and attribution requirements
ai.json
Machine-parseable AI interaction guidance with JSON Schema validation
identity.json
Structured canonical identity data aligned with Schema.org Organization
brand.txt
Brand naming conventions and representation guidance
faq-ai.txt
Structured Q&A content optimised for AI consumption
developer-ai.txt
Technical context for AI systems assisting developers
robots-ai.txt
AI crawler-specific access directives using robots.txt syntax
Implementation Guides
Quick Start Guide
Implement AI Discovery Files in three progressive tiers: Essential, Recommended, and Complete
Interoperability Guide
Conflict resolution rules and precedence hierarchy when files contain contradictory information
Validation Framework
Test prompts and scoring methodology to verify AI systems interpret your files correctly
AI Discovery Files vs Web Standards
How AI Discovery Files compare to robots.txt, Schema.org, security.txt, humans.txt, and ads.txt
Standards Framework
The framework pages document how the AI Discovery Files specification behaves as a standard: how to conform, how it is versioned and governed, what implementations exist, and how it relates to neighbouring standards.
Conformance
Conformance classes (Essential, Recommended, Complete) and the rules for claiming conformance.
Conventions
RFC 2119 + RFC 8174 requirement keywords, document statuses, anchor naming, language declarations.
Specification Registry
Machine-readable single source of truth for all 10 files: paths, media types, paired files, precedence, schema URLs.
Versioning & Deprecation
SemVer commitments, deprecation timelines, lifecycle.
Governance
Editorial process, proposal lifecycle (Proposed → Accepted → Published → Stable → Deprecated), working principles.
Security & Privacy
Trust model, content-injection patterns, GDPR considerations, access-control boundary.
HTTP Behaviour
Status codes, redirect handling, soft-404 detection, caching, rate limits, CORS.
Processing Model
The 7-stage algorithm a consumer or validator MUST follow: discover, fetch, validate, resolve, detect contradictions, emit summary.
AI Consumer Guidance
What AI systems SHOULD do with AI Discovery Files at training time, retrieval time, and citation time.
Test Vectors
Framing for the canonical test suite published in the spec repository.
Relationship to Other Standards
How AI Discovery Files positions relative to llmstxt.org, IETF AI Preferences, robots.txt, Schema.org, BCP 14, JSON Schema, SemVer.
Implementations
Public record of conformant implementations: WordPress plugin, AI Visibility Checker, AI Visible Directory, templates, Service Pack.
The Conformance Registry
The AI Visible Directory's formal role as canonical conformance registry: verification process, re-check cadence, disputes, and the relationship to self-declared conformance.
Certification Badges
The three Directory-issued conformance certification badges (Essential, Recommended, Complete) with embed snippets and display rules.
Extensions
Rules for experimental x--prefixed files, third-party extensions, and the path from experiment to core.
i18n & Accessibility
Multi-language publication, locale-tagged identity fields, RTL languages, accessibility of llms.html.
Roadmap
Public theme-pegged forward plan. Status flags (Active, Next, Future, On hold) reflect current intent without committing to specific dates or version numbers.
Additional Resources
Canonical Examples
- View all example files
- Uses fictional business: Horizon Strategic Consulting
- Demonstrates best practices for each format
JSON Schemas
- ai.json Schema
- identity.json Schema
- Use for validation and IDE support
Generate AI Discovery Files from your dashboard
Using WordPress? Install the plugin and create all 10 files in minutes — no coding, no configuration files to edit manually.
Get the PluginRegister in the AI Visibility Directory
Once your AI Discovery Files are published, register your website in the AI Visibility Directory — the verified registry of websites implementing AI Discovery Files. Registration validates your implementation and lists your site for AI systems and industry peers to discover.
Card entry in the directory with automated file validation. Open to any site with a valid llms.txt file. No cost.
Dedicated profile page on the directory with dofollow backlinks to your website — a genuine SEO authority signal from a topically relevant, verified source. Includes an attribution badge and enhanced visibility.