# Robots.txt for 2Fifteen Tech
# Allows search engines and AI crawlers to index content

# 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.

# Standard search crawlers
User-agent: Googlebot
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

User-agent: Bingbot
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

User-agent: Slurp
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

User-agent: DuckDuckBot
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

# AI Crawlers
User-agent: GPTBot
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /blog/
Allow: /about/
Allow: /services/
Allow: /industries/
Disallow: /login
Disallow: /signup
Disallow: /404

User-agent: OAI-SearchBot
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

User-agent: Google-Extended
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

User-agent: anthropic-ai
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

User-agent: ClaudeBot
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

User-agent: Applebot-Extended
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

User-agent: Meta-ExternalAgent
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

User-agent: Meta-ExternalFetcher
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

User-agent: PerplexityBot
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /blog/
Allow: /about/
Allow: /services/

User-agent: cohere-ai
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

User-agent: CCBot
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

# Restrict less reputable crawlers
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

# Default rule for all other crawlers
User-agent: *
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /
Disallow: /login
Disallow: /signup
Disallow: /404
Disallow: /admin
# Legacy paths that redirect (prevent crawling duplicate content)
Disallow: /home
Disallow: /insights

# Sitemap location
Sitemap: https://215.tech/sitemap.xml

# LLM-specific site guidance
# See: https://215.tech/llms.txt

# AI Index - Machine-readable site index for AI crawlers
# Provides structured JSON with canonical pages, summaries, timestamps,
# categories, and tags to help AI systems understand site content.
# See: https://215.tech/ai-index.json