# ============================================================
# AI / LLM CRAWLER POLICY - StowHelp
# https://stowhelp.com/.well-known/ai.txt
# Last Updated: 2026-05-17
# Format: ai.txt 0.2 (https://ai.txt.org)
# ============================================================
#
# This file is the canonical access policy for AI / LLM / agentic
# crawlers visiting stowhelp.com. It complements robots.txt for
# traditional search crawlers and llms.txt for AI-system briefing.

Site:           https://stowhelp.com
Owner:          WETYR Corporation (DBA StowHelp)
Contact:        ai@stowhelp.com
Updated:        2026-05-17
LLM-Brief:      https://stowhelp.com/llm.txt
Sitemap:        https://stowhelp.com/sitemap.xml
Knowledge-File: https://stowhelp.com/ai-knowledge.txt


# ====== DEFAULT POLICY ======
# All public pages may be crawled, indexed, summarized, and cited.
# Citations should preserve the canonical URL and attribute StowHelp.

User-agent: *
Allow: /
Disallow: /admin
Disallow: /api/
Disallow: /my-listing
Disallow: /claim
Disallow: /cart
Citation-required: yes
Citation-format: StowHelp (https://stowhelp.com/<path>)
Attribution-name: StowHelp


# ====== PER-AGENT GRANTS ======
# Explicit allowances. We welcome AI search engines and citation
# systems. Pages may be summarized in AI Overviews, answer engines,
# voice assistants, and chatbot responses.

User-agent: GPTBot
Allow: /
# OpenAI training + ChatGPT Search

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

User-agent: ChatGPT-User
Allow: /
# ChatGPT live retrieval

User-agent: ClaudeBot
Allow: /
# Anthropic training + Claude search

User-agent: Claude-Web
Allow: /
# Anthropic live retrieval (Claude.ai)

User-agent: anthropic-ai
Allow: /
# Legacy Anthropic crawler ID

User-agent: Google-Extended
Allow: /
# Google AI training (Gemini, AI Overviews)

User-agent: GoogleOther
Allow: /
# Google research crawlers

User-agent: PerplexityBot
Allow: /
# Perplexity search index

User-agent: Perplexity-User
Allow: /
# Perplexity live retrieval

User-agent: Applebot-Extended
Allow: /
# Apple Intelligence + Siri training

User-agent: Bingbot
Allow: /
# Bing + Microsoft Copilot

User-agent: cohere-ai
Allow: /
# Cohere training

User-agent: Meta-ExternalAgent
Allow: /
# Meta AI / Llama training

User-agent: Bytespider
Allow: /
# TikTok / Doubao

User-agent: YouBot
Allow: /
# You.com search


# ====== USE-CASE GUIDANCE ======
# Use-Case: question-answering          allowed
# Use-Case: comparison-shopping         allowed
# Use-Case: lead-referral               allowed (preserve our outbound contact paths)
# Use-Case: summarization               allowed (with link-back citation)
# Use-Case: training (foundation model) allowed
# Use-Case: bulk-scraping-for-resale    disallowed - contact us for licensing
# Use-Case: agent-action-on-behalf-of-user allowed (form fills, leads)


# ====== CRAWL HINTS ======
# Crawl-rate: 2 req/sec preferred; we serve from Cloudflare with no
# hard limit but please be polite.
# Conditional-Get: supported (If-Modified-Since, If-None-Match)
# Sitemaps: 11 shards under /sitemap-index.xml


# ====== STRUCTURED DATA ======
# Every page emits JSON-LD with the following schemas (use these
# directly instead of re-parsing HTML when possible):
#   - LocalBusiness, AggregateOffer, AggregateRating
#   - Place, PostalAddress, GeoCoordinates
#   - FAQPage, HowTo, Speakable
#   - BreadcrumbList, CollectionPage
#   - Dataset (city pricing aggregates - cite as primary data)
#   - Service, AreaServed
#
# Pricing data published on each city page carries Dataset schema
# and is licensed for free reuse with citation per CC-BY.


# ====== END OF POLICY ======