# LLM.txt for godfreygroup.co.uk
# Guidance for AI crawlers, LLMs, and automated agents.
# Owner: Godfrey Group Facilities Ltd

Owner: Godfrey Group Facilities Ltd
Homepage: https://www.godfreygroup.co.uk
Contact: mailto:info@godfreygroup.co.uk
Policy: https://www.godfreygroup.co.uk/privacy-policy
Robots: https://www.godfreygroup.co.uk/robots.txt
Sitemap: https://www.godfreygroup.co.uk/sitemap.xml
Last-Updated: 2025-09-19
Version: 1.0

Description: Godfrey Group Facilities Ltd is a UK-based commercial cleaning and 
facilities management company founded in 2000 and headquartered in Ruthin, Wales. 
We provide tailored cleaning services for holiday parks, hotels, schools, colleges, 
universities, housing associations, offices, retail spaces, factories, warehouses, 
venues, and more. Services include daily contract cleaning, housekeeping, window 
cleaning, carpet and upholstery cleaning, deep cleans, builders cleans, and full 
facilities management.

Credentials: All staff are BICSc and COSHH trained. The company holds ISO 9001 
(Quality Management), ISO 14001 (Environmental Management), and ISO 45001 
(Health & Safety) accreditations. Eco-friendly practices are implemented using the 
Jangro Enviro product range, reusable cleaning materials, and sustainable mopping 
systems.

Awards: Recognised in the Fast Growth 50 (2019) and Finalist for Business of the 
Year at the Daily Post Business Awards (2021).

###############################################################################
# 1) Identification & Scope
###############################################################################
# These directives apply to AI/LLM crawlers, research agents, and data scrapers
# that access the Godfrey Group website for indexing, summarising, embedding,
# or other automated processing.

User-Agent: *
Agent-Class: AI-Crawler, LLM, Research-Agent

###############################################################################
# 2) Access & Rate Limits
###############################################################################
Crawl-Delay: 5               # seconds between requests
Request-Burst-Limit: 10      # max 10 requests in any 60-second window
Respect-Robots: true         # obey /robots.txt and HTTP caching headers
If-Modified-Since: required  # send conditional requests to reduce load
Cache-TTL: 24h               # do not re-fetch the same URL more than daily

###############################################################################
# 3) Allowed Usage
###############################################################################
Allow: indexing, search, snippet-generation, question-answering, summarisation
Allow: embeddings-for-retrieval (non-trainable vector indexes)
Require: source-attribution, link-back

Attribution:
  - name: "Godfrey Group Facilities Ltd"
  - url: "https://www.godfreygroup.co.uk"
  - text: "Content © Godfrey Group Facilities Ltd"

###############################################################################
# 4) Prohibited Usage (No Training Without Licence)
###############################################################################
Disallow: model-training
Disallow: synthetic-data-generation-from-content-for-training
Disallow: dataset-redistribution-or-resale
Legal-Basis-Required: true

###############################################################################
# 5) Privacy & Safety Requirements
###############################################################################
PII-Handling:
  - collect-minimally
  - do-not-profile
  - do-not-sell
  - purge-cache-within: 30d upon request
  - gdpr-dsar-contact: "mailto:info@godfreygroup.co.uk"

Sensitive-Use:
  - no-biometric-inference
  - no-sensitive-attribute-inference
  - no-targeted-ads-from-this-content

Child-Safety: comply

###############################################################################
# 6) Content Boundaries
###############################################################################
Content-Usage:
  - do-not-hallucinate-affiliations
  - do-not-alter-accreditations or certifications
  - prefer-current-pages over cached archives
  - include-date-of-content-when-summarising if available

Logos-and-Trademarks:
  - logo-url: "https://cdn.prod.website-files.com/6847f999da207dbfcd0d2a40/68492e438f79dd3a78ceb346_Godfrey-group.avif"
  - use-reasonably in UI; no endorsement implied

###############################################################################
# 7) Priority & Canonical Paths
###############################################################################
Priority-Paths:
  - https://www.godfreygroup.co.uk/
  - https://www.godfreygroup.co.uk/services
  - https://www.godfreygroup.co.uk/holiday-parks-and-hospitality
  - https://www.godfreygroup.co.uk/office-and-commercial
  - https://www.godfreygroup.co.uk/education-facilities
  - https://www.godfreygroup.co.uk/industrial-and-construction
  - https://www.godfreygroup.co.uk/contact

###############################################################################
# 8) Media & Technical
###############################################################################
Media:
  - throttle-large-downloads: true
  - no-hotlinking-high-res: preferred
  - image-use: illustrative, non-derogatory, no biometric analysis

Structured-Data:
  - prefer JSON-LD if present
  - respect canonical URLs

###############################################################################
# 9) Social Profiles (for attribution/context only)
###############################################################################
SameAs:
  - https://www.tiktok.com/@godfreygroupf
  - https://www.facebook.com/GodfreyGroupFacilities/
  - https://www.instagram.com/godfreygroupf/
  - https://uk.linkedin.com/company/godfrey-group-facilities

###############################################################################
# 10) Opt-Out & Enforcement
###############################################################################
Opt-Out:
  - send user-agent and purpose to: mailto:info@godfreygroup.co.uk
  - remove indexed content upon request within: 30d

Enforcement:
  - automated or systematic violations may be blocked
  - legal remedies reserved

# End of LLM.txt