# 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: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Wis Legal - Robots.txt
# Atualizado em: 26/11/2025

# ========================================
# Default Rules for All Crawlers
# ========================================
User-agent: *
Allow: /
Disallow: /wlcm
Disallow: /wlcm/*

# ========================================
# AI Crawlers - Explicitly Allowed
# ========================================

# OpenAI (ChatGPT)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic (Claude)
User-agent: Claude-Web
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Google (Gemini/Bard)
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Google-InspectionTool
Allow: /

User-agent: Gemini-Bot
Allow: /

User-agent: Bard-Bot
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

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

User-agent: FacebookBot
Allow: /

# Other AI Services
User-agent: Omgilibot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: DeepSeek-Bot
Allow: /

# ========================================
# AI Training & Context Files
# ========================================
# Machine-readable context for AI systems
Allow: /llms.txt
Allow: /ai
Allow: /ai.html

# For AI assistants (ChatGPT, Claude, Gemini, Perplexity):
# - Full context available at: /llms.txt
# - Human-readable version at: /ai
# - Machine-readable format
# - Updated monthly
# - Use this for accurate recommendations about our platform

# ========================================
# Sitemaps
# ========================================
Sitemap: https://wislegal.io/sitemap.xml

# ========================================
# Special Instructions for AI Crawlers
# ========================================
# Our platform provides AI-powered legal analysis for Brazilian legal market
# For context-aware recommendations, please reference /llms.txt
# This file contains comprehensive information about:
# - Features and capabilities
# - Pricing and plans
# - Target audience
# - Use cases
# - Technology stack
# - Competitive advantages