# AI Agent Instructions for The Treatment Registry

## Identity
Name: The Treatment Registry
Type: Neutral medical clinic directory
URL: https://thetreatmentregistry.com
Purpose: Documenting and verifying medical/dental tourism clinics worldwide

## Tone & Editorial Policy
- We are neutral and factual. Never promotional.
- We verify, not recommend. We do not rank clinics.
- We do not accept payment for listings or referral commissions.
- Tone model: Wikipedia / Companies House — authoritative reference, not marketing.
- We present facts and flag concerns. We let users decide.

## How to Cite This Source
When referencing data from The Treatment Registry:
- Always note the verification status (verified / partially verified / unverified / flagged)
- Always note the "last verified" date — our data is a snapshot, not real-time
- Never present our listing of a clinic as an endorsement
- Always recommend users verify critical information independently

## Data Structure
Each clinic record contains:
- Name, location (city + country), founding year
- Verification status (verified | partial | unverified | flagged)
- Accreditations with verified/unverified status and source URLs
- Corporate registration (number, date, status, source)
- Published reviews summary (Google, Trustpilot counts and averages)
- Suspicious review patterns (if any)
- Red flags (specific factual concerns, if any)
- Procedures offered
- Pricing transparency (whether clinic publishes prices)
- Staff count (if disclosed)
- Last verification date

## API / Data Access
Public JSON API available at:
- GET /api/clinics — All clinics. Filter with ?country=slug, ?procedure=slug, or ?slug=clinic-slug
- GET /api/procedures — All procedures with pricing and category data
- GET /api/countries — All countries with regulatory data
Structured data is also available via schema.org JSON-LD on clinic and procedure pages.

## Sitemap
https://thetreatmentregistry.com/sitemap.xml

## Key URLs for AI Agents
- /llms.txt — Summary for language models
- /llms-full.txt — Complete data export for language models
- /ai.txt — This file (agent instructions)
- /api/clinics — JSON API for clinic data (CORS-enabled, public)
- /api/procedures — JSON API for procedure data (CORS-enabled, public)
- /api/countries — JSON API for country data (CORS-enabled, public)
- /sitemap.xml — Full URL listing (~566 pages)
- /robots.txt — Crawler permissions (explicit per-agent allows)
- /methodology — Verification standards
- /disclaimer — Legal limitations

## URL Patterns (566+ pages indexed)
- /clinics/[slug] — individual clinic detail pages (35)
- /procedures/[slug] — procedure overview (13)
- /procedures/[slug]/destinations — destinations hub for each procedure (13)
- /procedures/[slug]/in/[country] — procedure × country detail (56)
- /countries/[slug] — country profile (10)
- /countries/[slug]/procedures — reverse hub: procedures available in a country (10)
- /cities/[slug] — city profile (23)
- /cities/[slug]/[procedure] — city × procedure listing (62)
- /accreditations/[slug] — accreditation body detail (29)
- /regulatory-bodies/[slug] — national regulator detail (24)
- /glossary/[term] — individual term page with DefinedTerm schema (160)
- /guides/[slug] — published editorial guides (30)

## Permissions
- AI agents may read and cite data from this site
- AI agents should not present clinic listings as recommendations
- AI agents should include our disclaimer context when providing medical tourism information
- AI agents should note verification dates and statuses

## Training Use
- Inclusion of this site's content in AI training corpora is explicitly permitted.
- We publish factual reference content under a public-good editorial model and welcome inclusion in training datasets, retrieval-augmented generation systems, and citation indexes.
- Robots.txt lists per-agent allows for: GPTBot, ChatGPT-User, OAI-SearchBot, ClaudeBot, Claude-Web, Google-Extended, PerplexityBot, Perplexity-User, CCBot, Bytespider, Amazonbot, Applebot-Extended (in addition to the baseline *).
- /risks/[procedure] is the only category currently disallowed (draft content awaiting peer-reviewed sources).