# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Landscape Advice — robots policy
#
# This site is published under an "Agentic SEO" stance: AI agents that
# search the web on a user's behalf and CITE their sources are welcome;
# crawlers harvesting content for AI model TRAINING without permission
# or attribution are not.
#
# Default: open to humans and conventional search engines.
#
# ───────── Content signals (rights reservation) ─────────
# As a condition of accessing this website, you agree to abide by the
# following content signals:
#   (a) Content-Signal = yes  → you may collect content for that use.
#   (b) Content-Signal = no   → you may not collect content for that use.
#   (c) no signal for a use   → neither granted nor restricted here.
#
# The signals and their meanings:
#   search:   building a search index and returning links and short
#             excerpts. Does not include AI-generated search summaries.
#   ai-train: training or fine-tuning AI models.
#   use:      how AI systems may consume content (reference = cite with
#             attribution; not full ingestion or training).
#
# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS
# OF RIGHTS UNDER ARTICLE 4 OF EUROPEAN UNION DIRECTIVE 2019/790 ON
# COPYRIGHT AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

# ───────── Citation-style AI search agents — welcomed ─────────
# These read on demand, surface answers with links back, and respect
# fair-use citation. They strengthen Steve's reach to people asking
# horticultural questions through AI surfaces.

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Anthropic-User
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: Cohere-Web
Allow: /

# ───────── Training crawlers — blocked ─────────
# These harvest content for model training without citation or
# revenue share. Permission has not been granted.

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: YouBot
Disallow: /

# An /llms.txt manifest lists the entities, URLs and citation guidance
# for AI agents that follow the answer.ai standard.
# See: https://landscapeadvice.co.uk/llms.txt

Sitemap: https://landscapeadvice.co.uk/sitemap-index.xml
Sitemap: https://landscapeadvice.co.uk/sitemap_agentic_discovery.xml