# 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
# robots.txt for Kaiwa
# https://trykaiwa.com
# ============================================
# DEFAULT RULES - All Crawlers
# ============================================
User-agent: *
Allow: /
# Machine-readable surfaces for agents — always allowed
Allow: /llms.txt
Allow: /.well-known/llms.txt
# Disallow private/admin areas
# Note: /api/og/* images are linked via og:image meta tags but should NOT be crawled directly
# They return 302 redirects and waste crawl budget
Disallow: /admin
Disallow: /api/
Disallow: /auth/
Disallow: /ingest/
Disallow: /dev/
Disallow: /e2e/
Disallow: /test-*
Disallow: /profile
Disallow: /dashboard
Disallow: /user/
Disallow: /unsubscribe
# Allow important public pages explicitly
Allow: /privacy
Allow: /terms
Allow: /docs
Allow: /blog
Allow: /about
Allow: /pricing
Allow: /faq
Allow: /changelog
Allow: /scenarios
Allow: /research
Allow: /get-your-guide
Allow: /path
Allow: /program
Allow: /compare
Allow: /learn
# ============================================
# SITEMAP & RSS FEEDS
# ============================================
Sitemap: https://trykaiwa.com/sitemap.xml
# RSS Feed for blog syndication
# Feed URL: https://trykaiwa.com/blog/rss.xml
# ============================================
# SEARCH ENGINE BOTS - ALLOW FOR INDEXING
# ============================================
# Google - Primary search engine
User-agent: Googlebot
Allow: /
# Google Images
User-agent: Googlebot-Image
Allow: /
# Google Mobile
User-agent: Googlebot-Mobile
Allow: /
# Bing - Powers ChatGPT Search
User-agent: Bingbot
Allow: /
# Bing Preview - For rich snippets
User-agent: BingPreview
Allow: /
# Yahoo/Slurp
User-agent: Slurp
Allow: /
# DuckDuckGo
User-agent: DuckDuckBot
Allow: /
# Yandex
User-agent: Yandex
Allow: /
# Baidu
User-agent: Baiduspider
Allow: /
# ============================================
# AI SEARCH BOTS - ALLOW FOR SEARCH VISIBILITY
# ============================================
# These bots power AI-assisted search features
# OpenAI SearchBot - Required for ChatGPT Search visibility
User-agent: OAI-SearchBot
Allow: /
# ChatGPT-User - Processes real-time user queries in ChatGPT
User-agent: ChatGPT-User
Allow: /
# Perplexity AI Bot - For Perplexity search indexing
User-agent: PerplexityBot
Allow: /
# You.com AI search
User-agent: YouBot
Allow: /
# ============================================
# AI TRAINING BOTS - BLOCK TO PREVENT TRAINING
# ============================================
# Note: Blocking these does NOT affect search visibility
# These bots collect data for AI model training only
# OpenAI GPTBot - AI training data collection
User-agent: GPTBot
Disallow: /
# Common Crawl - Used by many AI training datasets
User-agent: CCBot
Disallow: /
# Anthropic bots — split by purpose
# Anthropic runs three distinct crawlers:
# - ClaudeBot → training data collection (block)
# - Claude-Web → real-time user queries, equivalent to ChatGPT-User (allow)
# - anthropic-ai → legacy umbrella, also used for user-query web fetches (allow on marketing surfaces)
# Private areas (/api/, /admin, /auth/, /dashboard, /profile, /user/) remain blocked by the default
# User-agent: * rules. See https://docs.anthropic.com/en/docs/agents-and-tools/web-fetch-tool
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /
# ClaudeBot is the training crawler — keep blocked
User-agent: ClaudeBot
Disallow: /
# Google AI training bots
User-agent: Google-Extended
Disallow: /
# Cohere AI training
User-agent: cohere-ai
Disallow: /
# Meta/Facebook AI training
User-agent: FacebookBot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /
# ByteDance/TikTok AI training
User-agent: Bytespider
Disallow: /
# Apple AI training
User-agent: Applebot-Extended
Disallow: /
# Amazon AI training
User-agent: Amazonbot
Disallow: /
# Other AI scrapers
User-agent: AI2Bot
Disallow: /
User-agent: Ai2Bot-Dolma
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: Omgili
Disallow: /
User-agent: Scrapy
Disallow: /