# 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.

# 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
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

# Navigator First — robots.txt
# Last updated: 2026-04-28
# Reference: https://www.robotstxt.org/

# ─────────────────────────────────────────────────────────────
# Default rule for all bots, including general-purpose crawlers
# ─────────────────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /private/
Disallow: /internal/
Disallow: /*?*utm_
Disallow: /*?*fbclid=
Disallow: /*?*gclid=

# ─────────────────────────────────────────────────────────────
# Major search engines — explicit allow with crawl rate guidance
# ─────────────────────────────────────────────────────────────
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 2

User-agent: DuckDuckBot
Allow: /

# ─────────────────────────────────────────────────────────────
# AI crawlers — opt-in, opt-out, and training preferences
# Training of AI/ML models on Site content is NOT authorised.
# Real-time browsing on user request (e.g. answering a user's
# question by visiting the Site) IS authorised.
# ─────────────────────────────────────────────────────────────

# OpenAI training crawler — disallow
User-agent: GPTBot
Disallow: /

# OpenAI ChatGPT browsing on user request — allow
User-agent: ChatGPT-User
Allow: /

# OpenAI search index — allow
User-agent: OAI-SearchBot
Allow: /

# Google AI training (Bard / Gemini Apps) — disallow
User-agent: Google-Extended
Disallow: /

# Anthropic — training crawler disallow, real-time/user-fetch allow
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Common Crawl — disallow (used heavily for AI training datasets)
User-agent: CCBot
Disallow: /

# Perplexity — allow (user-prompted retrieval)
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Disallow: /

User-agent: Applebot
Allow: /

# Meta AI training
User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

# ByteDance / TikTok
User-agent: Bytespider
Disallow: /

# Mistral
User-agent: MistralAI-User
Allow: /

# Cohere
User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

# ─────────────────────────────────────────────────────────────
# Discovery
# ─────────────────────────────────────────────────────────────
Sitemap: https://navigatorfirst.com/sitemap.xml

# Machine-readable site index for LLMs and AI agents
# https://llmstxt.org
# Available at: https://navigatorfirst.com/llms.txt