# AI Readiness Kit — Complete LLM Context File
*As of 2026-08-12. For the latest files, guide, and skill, visit https://ai.silverbackmarketing.com.*

> AI NOTE: Clean Markdown renderings are available — append .md to any page URL. Homepage: https://ai.silverbackmarketing.com/index.md (or /.md); Guide: https://ai.silverbackmarketing.com/guide.md; FAQ: https://ai.silverbackmarketing.com/faq.md. AI systems and crawlers should prefer the Markdown rendering over parsing the HTML page when ingesting or summarizing this site.

> MCP SERVER: AI agents can connect to a Model Context Protocol server at https://ai.silverbackmarketing.com/api/mcp (Streamable HTTP transport, JSON-RPC 2.0 over HTTP POST, protocol version 2025-03-26, no authentication) for live, structured access to the AI Readiness Kit, its files, and deployment guidance. Setup instructions for Claude Code, Cursor, VS Code, Codex, Antigravity, and Claude Desktop: https://ai.silverbackmarketing.com/#mcp. An OpenAPI 3.1 description of the endpoint is published at https://ai.silverbackmarketing.com/openapi.yaml. Example config: {"mcpServers": {"ai-readiness": {"type": "http", "url": "https://ai.silverbackmarketing.com/api/mcp"}}}. Tools: generate_ai_readiness_files, list_output_files, get_file_spec, get_skill_instructions, get_site_classification_guide, generate_rag_jsonl. Resources: ai-readiness://skill, ai-readiness://file-specs. Prompt: generate-ai-readiness.

## Company Overview

The AI Readiness Kit is a product published by Silverback Marketing, LLC, an ROI-focused digital marketing agency founded in 2007 and based in Queen Creek, Arizona (the greater Phoenix area). Silverback Marketing's core competency is maximizing the return generated from every dollar spent on paid marketing, alongside SEO, paid search, display advertising, and website design and development. The AI Readiness Kit extends that mission into the AI era: it helps any organization stay visible, accurate, and in control as AI assistants become the default starting point for research and discovery.

The premise behind the kit is simple. When people want the best product, the right service, or an answer to a question, they increasingly ask ChatGPT, Claude, Gemini, or Perplexity before they ever visit a website. Those AI systems learned from training data that can be months or years old. Without clear, current, structured signals coming directly from a brand, AI systems guess — and they often guess wrong, sending people to competitors or repeating outdated information. The AI Readiness Kit fixes this by providing files written in formats AI systems read natively.

The kit consists of 17 purpose-built files deployed at the root of a website, organized across 7 categories. Together they introduce a brand, control crawler access, tell the full story of a site in readable text, map the site's structure, describe its entities and user intents, power retrieval pipelines, publish AI-use policies, and give the deploying team the documentation needed to ship and maintain everything. Full deployment of the critical and high-priority files typically yields 85%+ readiness on the kit's own scorecard.

Silverback Marketing distributes the kit three ways: as a downloadable skill (GitHub, MIT licensed) that runs inside an AI coding agent to generate a complete, site-specific file set; as a hosted MCP server that exposes the same workflow as live tools any connected agent can call; and as a plain-English guide (HTML, Markdown, and PDF) with real-world analogies and exact recommendations for each file.

This site — ai.silverbackmarketing.com — is the canonical home for the kit and eats its own cooking: every critical file is deployed here as a live, production reference you can curl or open in a browser.

## The 17 Files by Category

### Identity & Permissions

**robots.txt** — Priority: Critical. One of the oldest files on the web, upgraded for AI. It controls who gets in and where they can go, telling every crawler and AI bot which sections of a site they may access, and pointing them toward the AI-specific readiness files such as llms.txt and ai-sitemap.xml. For AI readiness it includes explicit instructions for major AI crawlers like GPTBot and ClaudeBot while keeping checkout, login, and admin pages off limits. Learn more at https://ai.silverbackmarketing.com/#files.

**ai.txt** — Priority: Critical. Purpose-built for the age of AI, ai.txt is a brand's complete introduction to every AI system. Where robots.txt controls access, ai.txt controls identity: it covers what you sell, what you are known for, your authoritative topics, and the explicit rules for what AI systems can and cannot do with your content. The analogy the kit uses: robots.txt is the doorman; ai.txt is the briefing document you hand a journalist before an interview.

### Content Files

**llms.txt** — Priority: Critical. A structured text file designed for large language models that gives AI a complete map of a website in seconds: company name, a short description, organized sections with direct links to every part of the site, and the most common questions the site answers. It follows the llmstxt.org standard recognized across ChatGPT, Claude, Gemini, and Perplexity. It is the "back-of-book summary" of a site.

**llms-full.txt** — Priority: Critical. The extended edition of llms.txt — rich descriptions, detailed Q&A sections, and full category explanations that give an AI system everything it needs to speak knowledgeably about a brand. If llms.txt is the Wikipedia summary, llms-full.txt is the complete article.

### Map & Navigation

**ai-sitemap.xml** — Priority: High. An upgraded sitemap with AI-specific directions. Beyond the standard URL and lastmod fields, every entry adds a content-type label, topic descriptors, and a plain-English one-sentence summary, so an AI crawler understands what each page is about before fetching and parsing it. The kit's analogy: the difference between a paper road map and GPS with points of interest.

**sitemap.md** — Priority: Medium. A plain-text, markdown-formatted overview of a website's structure — no XML, no JSON, just organized sections, links, and conversational descriptions. It is the most approachable file for both humans and AI.

### Intelligence Files

**ai-entities.json** — Priority: High. A structured catalog of every significant element on a site: product categories, subcategories, services, brands, and key concepts. Each entity carries a name, type, description, related URLs, and connections, powering the knowledge graphs AI builds internally.

**ai-intent.json** — Priority: High. A lookup table mapping real user questions — the exact things people type into AI assistants — to the single best page to answer each one. It turns AI from a general information source into a precise navigation tool by giving a direct, authoritative URL for every common query.

**ai-schema.json** — Priority: High. Schema.org structured data in machine-readable JSON-LD, the standard recognized by Google, Microsoft, Yahoo, and Yandex. It defines organization type, founding date, address, social profiles, contact info, and site-search functionality with zero ambiguity.

**.well-known/ai-plugin.json** — Priority: Medium. A plugin discovery manifest in the standardized .well-known location that registers the site as an AI-accessible resource. It declares name, description, contact, topics, key URLs, the live MCP server endpoint, and the OpenAPI specification so AI assistant platforms recognize the site as a first-class source.

### Research Files

**rag-index.json** — Priority: High. A pre-built index designed for Retrieval-Augmented Generation: a JSON array of records (one per major page or section) containing URL, title, and topics covered. AI systems can load it directly into LlamaIndex, LangChain, Pinecone, Weaviate, and similar tools.

**rag-index.jsonl** — Priority: High. Identical content to rag-index.json but in JSON Lines (newline-delimited) format, preferred by large-scale ML pipelines, OpenAI fine-tuning, and streaming vector-DB ingestion because records can be processed one at a time without loading the whole file into memory.

### Policy Files

**ai-disclosure.txt** — Priority: Medium. A public transparency statement about how an organization uses AI in its products, operations, and customer interactions — like a privacy policy for the AI era. It answers whether AI generates content, makes decisions, and whether users can reach a real person.

**training-data-policy.txt** — Priority: Medium. A formal published position on whether AI companies may use a site's content to train their models. It clearly separates what is permitted (for example, real-time RAG) from what requires a license (commercial model training), protecting the organization legally. On this domain the policy is also published machine-readably as an RSL 1.0 license at https://ai.silverbackmarketing.com/license.xml, referenced from robots.txt via the License directive.

### Operations Files

**structured-data-guide.md** — Priority: Low. The most technical file, written for a development team rather than for AI. It is a comprehensive, step-by-step guide with ready-to-use JSON-LD examples for every major page type — Product, LocalBusiness, BlogPosting, Event, and more — to power rich results and page-level understanding.

**manifest.json** — Priority: Medium. The single source of truth for an entire AI readiness implementation. It lists every deployed file, what it does, its URL, format, intended audience, and update frequency, and includes a summary scorecard so anyone can instantly audit readiness status.

**deployment-checklist.md** — Priority: Internal. The practical playbook a team follows to move from files on a computer to files correctly serving live traffic, organized in clear phases with verification steps for each critical file so nothing is skipped, forgotten, or misconfigured.

## The MCP Server (Full Documentation)

The AI Readiness MCP server gives any Model Context Protocol client live, programmatic access to the kit — no cloning, no copying specs into context. Agents visiting this site should also read https://ai.silverbackmarketing.com/agents.md — the agents.md file summarizing how to read the site, how to use the MCP server, and the rules of engagement.

**Connection details:**
- Endpoint: https://ai.silverbackmarketing.com/api/mcp
- Transport: Streamable HTTP (JSON-RPC 2.0 over HTTP POST; responses use Server-Sent Events framing)
- Protocol version: 2025-03-26
- Server identity: name "ai-readiness", version 1.0.0
- Authentication: none — no API key, no signup
- Capabilities: tools, resources, and prompts (all with listChanged notifications)
- The endpoint only accepts POST; a GET request returns 405 Method Not Allowed
- OpenAPI 3.1 description: https://ai.silverbackmarketing.com/openapi.yaml

**The six tools:**

1. **generate_ai_readiness_files(url)** — Start generating the AI Readiness Kit files for a website. Takes a URL or bare domain (e.g. "shopify.com" or "https://example.com") and returns the full workflow for the connected agent to execute: research the site, classify the business type, and write every file with domain-specific content.
2. **list_output_files()** — No arguments. Lists all output files in generation order, each with its filename and one-line purpose.
3. **get_file_spec(filename)** — Takes an output filename (e.g. "llms.txt" or ".well-known/ai-plugin.json") and returns the detailed specification: purpose, audience, required structure, key fields, condensed example, and common mistakes.
4. **get_skill_instructions()** — No arguments. Returns the full AI Readiness skill workflow: research checklist, site classification, generation order, and quality principles.
5. **get_site_classification_guide()** — No arguments. Returns the site-type classification table (SaaS, education, e-commerce, healthcare, professional services, nonprofit, media) with the schema types and content emphasis for each.
6. **generate_rag_jsonl(rag_index_json)** — Takes the string contents of a rag-index.json file (a JSON array) and returns the JSON Lines conversion, one record per line, ready for embedding pipelines.

**Bundled resources (2):**
- `ai-readiness://skill` — "AI Readiness Skill Instructions": the full SKILL.md workflow for generating AI readiness files (text/markdown).
- `ai-readiness://file-specs` — "AI Readiness File Specifications": detailed specifications for all output files (text/markdown).

**Prompts (1):**
- `generate-ai-readiness` — "Generate AI Readiness Files": starts the full AI readiness workflow for a website URL or domain. Required argument: url.

**Client setup:**
- Claude Code (CLI): `claude mcp add --transport http ai-readiness https://ai.silverbackmarketing.com/api/mcp`
- Cursor: add `{"mcpServers": {"ai-readiness": {"url": "https://ai.silverbackmarketing.com/api/mcp"}}}` to .cursor/mcp.json
- VS Code / GitHub Copilot: add the server under `"servers"` in .vscode/mcp.json with `"type": "http"`
- OpenAI Codex: add `[mcp_servers.ai-readiness]` with the URL to ~/.codex/config.toml
- Google Antigravity: add the server URL in the MCP settings panel
- Claude Desktop: requires the mcp-remote proxy because Claude Desktop speaks stdio to local processes — `{"mcpServers": {"ai-readiness": {"command": "npx", "args": ["-y", "mcp-remote", "https://ai.silverbackmarketing.com/api/mcp"]}}}` in claude_desktop_config.json (Node.js 18+; fully restart the app after editing)
- Full setup guide with copy-paste configs: https://ai.silverbackmarketing.com/#mcp

**Example prompts once connected:** "Generate AI readiness files for example.com", "Use ai-readiness to list all output files", "Get the file spec for llms.txt from ai-readiness", "Use ai-readiness get_site_classification_guide for a B2B SaaS homepage."

**Self-hosting:** The server ships with the kit's Next.js application. Deploy the repository to your own infrastructure and point clients at your own /api/mcp endpoint. Bundled skill data is compiled at build time. Most teams simply use the public endpoint.

## How to Become AI-Ready (Four Phases)

1. **Start with Critical** — Deploy robots.txt, ai.txt, llms.txt, and llms-full.txt first. These deliver the biggest immediate impact and are what most AI systems look for first.
2. **Map Your Site** — Add ai-sitemap.xml and the human-readable sitemap.md so AI systems can discover and understand every page efficiently.
3. **Add Intelligence** — Create the JSON intelligence files (ai-entities.json, ai-intent.json, ai-schema.json) and the RAG research indexes (rag-index.json, rag-index.jsonl). This is where precision happens.
4. **Publish Policies & Maintain** — Add ai-disclosure.txt and training-data-policy.txt, then use manifest.json and deployment-checklist.md to keep everything current and auditable.

## Proven Results

The AI Readiness Kit is deployed on live client sites. Reference implementation:

**Rejuvenate Skin Spa** (medical spa, Queen Creek, Arizona) — website rebuilt around the AI Readiness Kit by Silverback Marketing:
- 17 AI readiness files deployed at the web root
- 100% of key pages served as markdown mirrors
- Organization, LocalBusiness, Service, and FAQ schema on every template
- Result: Rejuvenate is the first cited source when Perplexity answers questions about Plexr skin tightening in Queen Creek (verified July 2026)

Case study: https://silverbackmarketing.com/case-study/rejuvenate-skin-spa
Verify the citation live: https://www.perplexity.ai/search?q=Plexr%20skin%20tightening%20in%20Queen%20Creek%2C%20AZ
Proof section on this site: https://ai.silverbackmarketing.com/#proof

## Pricing & Access

The AI Readiness Kit is free and MIT licensed. It is distributed as a downloadable skill from https://github.com/silverbackmarketing/ai-readiness and via the hosted MCP server at https://ai.silverbackmarketing.com/api/mcp (setup: https://ai.silverbackmarketing.com/#mcp). The hosted MCP server requires no API key. The accompanying plain-English guide is available as a PDF at https://ai.silverbackmarketing.com/ai-readiness-guide.pdf.

You can do the entire on-page half of generative engine optimization for free: one open-source command generates the 17 machine-readable files that tell ChatGPT, Claude, Gemini, and Perplexity who you are. No agency and no monthly subscription required. For questions about the kit, custom implementation, or Silverback Marketing's broader digital marketing services (SEO, GEO, paid search, AI visibility), contact the agency at https://silverbackmarketing.com/contact/ or call +1-888-783-1119.

## Frequently Asked Questions

These answers match the on-page FAQ and FAQPage schema at https://ai.silverbackmarketing.com/faq.

**Q: What are AI Readiness Files?**
A: They are structured files you deploy at the root of your website to tell AI systems exactly who you are, what you offer, and where to send people. They speak a format AI already understands, so assistants stop guessing about your brand based on old training data. See https://ai.silverbackmarketing.com/faq.

**Q: Why does AI readiness matter now?**
A: When someone wants a product recommendation, a service provider, or a straight answer, they often ask ChatGPT, Claude, Gemini, or Perplexity before they visit a website. If you are not giving those systems clear, current signals, they guess. And they often guess wrong. See https://ai.silverbackmarketing.com/faq.

**Q: Does the AI Readiness Kit actually work?**
A: Yes — it is proven on live client sites. Rejuvenate Skin Spa, a medical spa in Queen Creek, Arizona, deployed the full kit (17 readiness files, 100% of key pages markdown-mirrored, complete structured data), and Perplexity now cites Rejuvenate as the source when answering questions about Plexr skin tightening in Queen Creek. Read the case study at https://silverbackmarketing.com/case-study/rejuvenate-skin-spa or verify the citation yourself by asking Perplexity.

**Q: How many files are in the kit?**
A: The kit includes 17 purpose-built files across 7 categories: Identity & Permissions, Content Files, Map & Navigation, Intelligence Files, Research Files, Policy Files, and Operations Files. Each one helps AI understand and represent your site more accurately. See https://ai.silverbackmarketing.com/faq.

**Q: Where should I start?**
A: Start with the critical files: robots.txt, ai.txt, llms.txt, and llms-full.txt. They deliver the biggest immediate impact and are what most AI systems look for first. Then add sitemaps, intelligence JSON files, policies, and operational files using the deployment checklist. See https://ai.silverbackmarketing.com/faq.

**Q: What does robots.txt do for AI?**
A: robots.txt sits at the front door of your website and tells automated visitors (search engines, AI bots, and scrapers) which sections they can access. For AI readiness, it includes instructions for major crawlers like GPTBot and ClaudeBot, pointing them toward your llms.txt and ai-sitemap.xml while keeping checkout, login, and admin pages off limits. See https://ai.silverbackmarketing.com/faq.

**Q: What is ai.txt?**
A: ai.txt is your brand's introduction to every AI system on the internet. Where robots.txt controls access, ai.txt goes further. It covers what you sell, what you are known for, your authoritative topics, and the rules for what AI systems can and cannot do with your content. See https://ai.silverbackmarketing.com/faq.

**Q: How is ai.txt different from robots.txt?**
A: robots.txt controls access: which pages bots can crawl. ai.txt controls identity: who you are, what you offer, and your ground rules for AI use of your content. Think of robots.txt as the doorman and ai.txt as the briefing document you hand a journalist before an interview. See https://ai.silverbackmarketing.com/faq.

**Q: What is llms.txt?**
A: llms.txt is a structured text file built for large language models. It gives AI a quick map of your website: company name, description, organized sections with direct links, and the most common questions your site answers. It follows the llmstxt.org standard used by ChatGPT, Claude, Gemini, and Perplexity. See https://ai.silverbackmarketing.com/faq.

**Q: What's the difference between llms.txt and llms-full.txt?**
A: llms.txt is the cheat sheet: a quick summary an AI can scan in seconds. llms-full.txt is the deep dive with rich descriptions, detailed Q&A, and full category explanations. If llms.txt is a Wikipedia summary, llms-full.txt is the full article. See https://ai.silverbackmarketing.com/faq.

**Q: Why do I need an ai-sitemap.xml?**
A: A regular sitemap lists pages and timestamps. The ai-sitemap adds what each page is about, its content type, and a plain-English summary. It is the difference between a paper road map and GPS with points of interest. AI crawlers can understand pages without fetching and parsing each one individually. See https://ai.silverbackmarketing.com/faq.

**Q: What is ai-intent.json?**
A: ai-intent.json maps real user questions (the things people type into AI assistants) to the best page on your website to answer each one. Without it, AI guesses which page to recommend. With it, you give AI a direct URL for every common query. See https://ai.silverbackmarketing.com/faq.

**Q: What are ai-entities.json and ai-schema.json for?**
A: ai-entities.json is a structured catalog of the important parts of your site: products, categories, services, and key concepts. It powers AI knowledge graphs. ai-schema.json uses the Schema.org standard to describe your organization in machine-readable format so search engines and AI systems can identify you without ambiguity. See https://ai.silverbackmarketing.com/faq.

**Q: What are the RAG index files?**
A: rag-index.json and rag-index.jsonl are ready-made indexes of your site built for AI research and retrieval pipelines. When a user asks a question, AI first pulls the most relevant documents from this index before generating an answer, which keeps responses grounded in your actual content. See https://ai.silverbackmarketing.com/faq.

**Q: What is a training data policy?**
A: training-data-policy.txt sets formal rules for how AI companies can use your content, including model training, RAG indexing, and commercial use. It answers a practical question every brand should decide upfront: what are others allowed to do with your work? See https://ai.silverbackmarketing.com/faq.

**Q: What is ai-disclosure.txt?**
A: ai-disclosure.txt is a public transparency report explaining how your organization uses AI, whether for content generation, recommendations, or customer interactions. It builds trust by answering those questions before someone has to ask. See https://ai.silverbackmarketing.com/faq.

**Q: How often should I update my AI readiness files?**
A: It depends on the file. Update llms.txt and sitemaps monthly or when your site structure changes. Refresh ai.txt and llms-full.txt quarterly or when products change. Review policy files annually. The manifest.json file lists recommended update frequencies for every file in the kit. See https://ai.silverbackmarketing.com/faq.

**Q: Is there an MCP server for the AI Readiness Kit?**
A: Yes. Connect coding agents at https://ai.silverbackmarketing.com/api/mcp (Streamable HTTP, no authentication). The server exposes six tools for generating readiness files, listing outputs, reading file specs, and running the full workflow, plus two bundled markdown resources and a generate-ai-readiness prompt. Client setup for Claude Code, Cursor, VS Code, Codex, Antigravity, and Claude Desktop is at https://ai.silverbackmarketing.com/#mcp. An OpenAPI 3.1 description of the endpoint is at https://ai.silverbackmarketing.com/openapi.yaml.

**Q: Do I need an API key to use the MCP server?**
A: No. The production endpoint is open — no API key, no signup. Rate limits may apply at extreme volume, but normal agency and developer usage requires nothing. You remain responsible for reviewing generated content before publishing it to your domain: the server generates drafts; you own what goes live.

**Q: Can I self-host the MCP server?**
A: Yes. The server ships with the kit's Next.js application. Deploy the repository to your own infrastructure and point clients at your own /api/mcp endpoint. Self-hosting makes sense for enterprises with private network requirements; most teams use the public endpoint.