# AI Readiness Files — Example Analytics
## https://exampleanalytics.com

---

## What Is This?

This folder contains a complete set of AI readiness files for Example Analytics. These files make the website and brand legible to AI systems — including ChatGPT, Claude, Gemini, Perplexity, and RAG-based enterprise search tools — so that AI assistants can accurately answer questions about the company, its products, pricing, and integrations.

These files follow open standards including [llmstxt.org](https://llmstxt.org), [aitxt.org](https://aitxt.org), and [Schema.org](https://schema.org).

---

## Why AI Readiness Matters

When someone asks an AI assistant "What does Example Analytics do?" or "How much does it cost?", the AI pulls from:

1. Its training data (static, may be outdated)
2. Live web search results (if available)
3. RAG pipelines that have indexed the site

These files ensure that when AI systems crawl, index, or reason about Example Analytics, they have accurate, structured, complete information — not guesses from noisy web pages.

---

## File Inventory

| File | URL | Priority | Purpose |
|------|-----|----------|---------|
| `ai.txt` | `/ai.txt` | Critical | Crawler permissions, brand identity, topic authority, training policy |
| `llms.txt` | `/llms.txt` | Critical | Concise LLM site index (llmstxt.org standard) |
| `llms-full.txt` | `/llms-full.txt` | Critical | Extended context for RAG pipelines |
| `ai-sitemap.xml` | `/ai-sitemap.xml` | Critical | XML sitemap with AI topic metadata |
| `robots.txt` | `/robots.txt` | Critical | AI crawler permission blocks (merge into live file) |
| `sitemap.md` | `/sitemap.md` | High | Human-readable markdown site map |
| `ai-entities.json` | `/ai-entities.json` | High | Structured entity declarations (org, product, pricing, compliance) |
| `ai-intent.json` | `/ai-intent.json` | High | 22 user query intents mapped to preferred URLs |
| `ai-schema.json` | `/ai-schema.json` | High | JSON-LD Schema.org graph |
| `rag-index.json` | `/rag-index.json` | High | RAG-ready page index (JSON array, 32 records) |
| `rag-index.jsonl` | `/rag-index.jsonl` | High | RAG-ready page index (JSONL format) |
| `ai-disclosure.txt` | `/ai-disclosure.txt` | Medium | AI usage transparency disclosure |
| `training-data-policy.txt` | `/training-data-policy.txt` | Medium | Policy for AI training use of site content |
| `.well-known/ai-plugin.json` | `/.well-known/ai-plugin.json` | Medium | AI plugin discovery manifest |
| `structured-data-guide.md` | `/structured-data-guide.md` | Medium | Developer guide for Schema.org JSON-LD |
| `manifest.json` | `/manifest.json` | Medium | Machine-readable file inventory (this package) |

---

## Key Queries These Files Help Answer

- "What is Example Analytics?" → Product Overview, About page
- "How much does Example Analytics cost?" → Pricing (Starter $49, Growth $149, Business $399)
- "Can Example Analytics connect to Salesforce / Stripe / Snowflake?" → Integration pages
- "Does Example Analytics have AI features?" → AI Insights module
- "Is Example Analytics SOC 2 certified?" → Security page
- "Does Example Analytics have embedded analytics?" → Embedded Analytics (Business plan+)
- "What is MRR / churn rate / LTV?" → SaaS Metrics Glossary
- "Is there a free trial?" → 14-day Growth trial, no credit card required

---

## Coverage

- **Company & leadership:** ✅ Full (CEO, CTO, Head of Product, founding date, HQ, contact)
- **Product modules:** ✅ All 7 modules covered with feature-level detail
- **Pricing:** ✅ All 4 tiers with prices, users, connector limits, key features
- **Integrations:** ✅ 20+ specific connectors documented; 200+ referenced
- **Solutions:** ✅ All 7 team-specific solutions covered
- **Compliance:** ✅ SOC 2 Type II, GDPR, HIPAA, SSO, encryption details
- **Educational resources:** ✅ Glossary, templates, benchmark report, blog
- **Query intent mapping:** ✅ 22 intents with preferred URL routing

---

## How Each File Works

**`llms.txt`** — The primary file AI systems look for. It's a concise, annotated index of the site in Markdown format. Any AI assistant that fetches this file gets an accurate overview of everything Example Analytics offers, in a format designed to fit in a single context window.

**`llms-full.txt`** — The extended version. Used by RAG pipelines that can handle longer documents. Contains complete product descriptions, pricing tables, integration specs, and query routing guidance.

**`ai.txt`** — Functions like robots.txt but for AI systems specifically. Declares what crawlers are allowed to index, establishes brand identity, lists authoritative topics, and summarizes training data policy.

**`ai-sitemap.xml`** — An XML sitemap extended with AI-specific metadata tags (`ai:content-type`, `ai:topic`, `ai:summary`) on every URL. Helps AI crawlers understand what each page covers before visiting it.

**`ai-entities.json`** — A structured data declaration file covering the company entity, product modules, pricing tiers, leadership, integrations, compliance certifications, and priority URLs. Used by knowledge graph systems and entity-aware AI tools.

**`ai-intent.json`** — Maps real user questions (22 intents) to the best URL to send someone to. AI assistants can use this to route users accurately rather than guessing.

**`ai-schema.json`** — Full JSON-LD structured data graph. Can be deployed as a standalone file or copied into individual page `<head>` blocks.

**`rag-index.json` / `rag-index.jsonl`** — Page index in formats optimized for RAG pipelines. Each record has a URL, title, and topic array. Import into any vector database or embedding pipeline.

**`.well-known/ai-plugin.json`** — AI plugin discovery metadata. AI systems that support plugin discovery use this to understand what the site covers and how to route queries.

---

## Deployment Quick Start

1. Upload all files to web root (see `deployment-checklist.md` for the full 10-phase process)
2. Merge AI crawler blocks from `robots.txt` into your live robots.txt
3. Add JSON-LD from `ai-schema.json` to key page `<head>` sections
4. Add `<link rel="llms-txt">` and `<link rel="ai-content-declaration">` to all page heads
5. Submit `ai-sitemap.xml` to Google Search Console

---

## Verification

After deployment, run the batch curl script from `deployment-checklist.md`, or verify manually:

```bash
# Quick spot check — 5 critical files
curl -I https://exampleanalytics.com/llms.txt
curl -I https://exampleanalytics.com/ai.txt
curl -I https://exampleanalytics.com/llms-full.txt
curl -I https://exampleanalytics.com/ai-sitemap.xml
curl -I https://exampleanalytics.com/.well-known/ai-plugin.json
```

All should return `HTTP/2 200`.

---

## Maintenance

Update `llms.txt`, `llms-full.txt`, `ai-sitemap.xml`, and `rag-index.*` monthly or whenever significant new pages are added. See `deployment-checklist.md` for the full maintenance schedule.

---

## Standards Referenced

- [llmstxt.org](https://llmstxt.org) — LLM site index standard (llms.txt and llms-full.txt)
- [aitxt.org](https://aitxt.org) — AI permissions standard (ai.txt and ai-sitemap.xml extensions)
- [Schema.org](https://schema.org) — Structured data vocabulary (ai-schema.json)
- [sitemaps.org](https://sitemaps.org) — Sitemap protocol (ai-sitemap.xml base format)
- [robots.txt standard](https://www.rfc-editor.org/rfc/rfc9309) — Crawler control

---

*Generated 2026-06-16 | Contact: hello@exampleanalytics.com*
