User-agent: *
Disallow: /404.html

Sitemap: https://remoteintech.company/sitemap.xml

# =============================================================================
# AI Search Bots - ALLOWED
# These power AI-assisted search features that help users discover content
# =============================================================================

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: PhindBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Applebot
Allow: /

# =============================================================================
# AI Training & Scraping Bots - BLOCKED
# These crawl content for AI model training without user intent
# https://github.com/ai-robots-txt/ai.robots.txt
# =============================================================================

User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
User-agent: Amazonbot
User-agent: Andibot
User-agent: anthropic-ai
User-agent: Applebot-Extended
User-agent: bedrockbot
User-agent: Brightbot 1.0
User-agent: Bytespider
User-agent: CCBot
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: Crawlspace
User-agent: Diffbot
User-agent: EchoboxBot
User-agent: FacebookBot
User-agent: facebookexternalhit
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
User-agent: Google-CloudVertexBot
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: GPTBot
User-agent: iaskspider/2.0
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: meta-externalagent
User-agent: Meta-ExternalAgent
User-agent: meta-externalfetcher
User-agent: Meta-ExternalFetcher
User-agent: MistralAI-User/1.0
User-agent: MyCentralAIScraperBot
User-agent: NovaAct
User-agent: omgili
User-agent: omgilibot
User-agent: Operator
User-agent: PanguBot
User-agent: Panscient
User-agent: panscient.com
User-agent: PetalBot
User-agent: Poseidon Research Crawler
User-agent: QualifiedBot
User-agent: QuillBot
User-agent: quillbot.com
User-agent: SBIntuitionsBot
User-agent: Scrapy
User-agent: SemrushBot
User-agent: SemrushBot-BA
User-agent: SemrushBot-CT
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SI
User-agent: SemrushBot-SWA
User-agent: Sidetrade indexer bot
User-agent: TikTokSpider
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: wpbot
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
Disallow: /