# VertoDigital - robots.txt
# Every page has a clean Markdown mirror at /markdown/[path].md (also reachable
# at /[path].md, and via `Accept: text/markdown` on the page URL itself). GPTBot,
# ClaudeBot and AI agents fetching a page for a user (ChatGPT-User, Claude-User,
# Perplexity-User, MistralAI-User, DuckAssistBot) get it on the page URL itself;
# add ?format=html for the HTML. AI search crawlers and search engines get HTML.
# Full site index: https://vertodigital.com/llms.txt
# Full index with page summaries & agent tooling: https://vertodigital.com/llms-full.txt
# Section indexes: https://vertodigital.com/content-hub/llms.txt, https://vertodigital.com/case-studies/llms.txt

User-agent: *
Allow: /
# /a/ - private account diagnostic pages. Unlinked, noindex, reached only from an ad.
Disallow: /a/
# /lp/ - account-based ad landing pages. Unlinked, noindex, reached only from an ad.
Disallow: /lp/

Content-Signal: ai-train=yes, search=yes, ai-input=yes, use=full

# ─── Google agents ────────────────────────────────────────────────────────────
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: Mediapartners-Google
User-agent: APIs-Google
Allow: /
Disallow: /a/
Disallow: /lp/
Content-Signal: ai-train=yes, search=yes, ai-input=yes, use=full

# ─── AI & LLM agents ──────────────────────────────────────────────────────────
User-agent: AddSearchBot
User-agent: AgentTimes
User-agent: AI2Bot
User-agent: AI2Bot-DeepResearchEval
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
User-agent: AIWebIndex
User-agent: amazon-kendra
User-agent: amazon-QBusiness
User-agent: Amazonbot
User-agent: AmazonBuyForMe
User-agent: Amzn-SearchBot
User-agent: Amzn-User
User-agent: Andibot
User-agent: Anomura
User-agent: anthropic-ai
User-agent: ApifyBot
User-agent: ApifyWebsiteContentCrawler
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Aranet-SearchBot
User-agent: atlassian-bot
User-agent: Awario
User-agent: AzureAI-SearchBot
User-agent: bedrockbot
User-agent: bigsur.ai
User-agent: Bravebot
User-agent: Brightbot
User-agent: BuddyBot
User-agent: Bytespider
User-agent: CCBot
User-agent: Channel3Bot
User-agent: ChatGLM-Spider
User-agent: ChatGPT Agent
User-agent: ChatGPT-User
User-agent: Claude-Code
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Cloudflare-AutoRAG
User-agent: CloudVertexBot
User-agent: Code
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: CragCrawler
User-agent: Crawl4AI
User-agent: Crawlspace
User-agent: Cursor
User-agent: Datenbank Crawler
User-agent: DeepSeekBot
User-agent: Devin
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: Echobot Bot
User-agent: EchoboxBot
User-agent: ExaBot
User-agent: FacebookBot
User-agent: facebookexternalhit
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: FriendlyCrawler
User-agent: GeistHaus-PageFetcher
User-agent: Gemini-Deep-Research
User-agent: Google-Agent
User-agent: Google-CloudVertexBot
User-agent: Google-Extended
User-agent: Google-Firebase
User-agent: Google-Gemini-CLI
User-agent: Google-NotebookLM
User-agent: GoogleAgent-Mariner
User-agent: GoogleAgent-URLContext
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: GPTBot
User-agent: HenkBot
User-agent: iAskBot
User-agent: iaskspider
User-agent: IbouBot
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: imageSpider
User-agent: img2dataset
User-agent: ISSCyberRiskCrawler
User-agent: kagi-fetcher
User-agent: Kangaroo Bot
User-agent: Kimi-User
User-agent: KlaviyoAIBot
User-agent: KunatoCrawler
User-agent: laion-huggingface-processor
User-agent: LAIONDownloader
User-agent: LCC
User-agent: LinerBot
User-agent: Linguee Bot
User-agent: LinkupBot
User-agent: Manus-User
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-agent: meta-webindexer
User-agent: MistralAI-User
User-agent: Mozilla-Tabstack
User-agent: MyCentralAIScraperBot
User-agent: NagetBot
User-agent: netEstate Imprint Crawler
User-agent: newsai
User-agent: NotebookLM
User-agent: NovaAct
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: OpenAI
User-agent: opencode
User-agent: Operator
User-agent: PanguBot
User-agent: Panscient
User-agent: panscient.com
User-agent: Perplexity-User
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: PhindBot
User-agent: Poggio-Citations
User-agent: Poseidon Research Crawler
User-agent: QualifiedBot
User-agent: Querit-SearchBot
User-agent: QueritBot
User-agent: QuillBot
User-agent: quillbot.com
User-agent: SBIntuitionsBot
User-agent: Scrapy
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SWA
User-agent: Shap-User
User-agent: ShapBot
User-agent: Sidetrade indexer bot
User-agent: Spider
User-agent: TavilyBot
User-agent: Terra Cotta
User-agent: TerraCotta
User-agent: Thinkbot
User-agent: TikTokSpider
User-agent: Timpibot
User-agent: TongyiBot
User-agent: Trae
User-agent: TwinAgent
User-agent: UseAI
User-agent: VelenPublicWebCrawler
User-agent: WARDBot
User-agent: Webzio-Extended
User-agent: wpbot
User-agent: WRTNBot
User-agent: YaK
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
User-agent: YiyanBot
User-agent: YouBot
User-agent: ZanistaBot
Allow: /
Disallow: /a/
Disallow: /lp/
Content-Signal: ai-train=yes, search=yes, ai-input=yes, use=full

# ─── Sitemaps ─────────────────────────────────────────────────────────────────
Sitemap: https://vertodigital.com/sitemap.xml
Sitemap: https://vertodigital.com/sitemap-images.xml
Sitemap: https://vertodigital.com/sitemap-videos.xml
Sitemap: https://vertodigital.com/content-hub/rss.xml

# ─── NLWeb Schema Feeds ──────────────────────────────────────────────────────
# Points NLWeb consumers at the Schema Map of structured-data feeds. Unlike the
# omitted "Agentmap:" below, this one is kept on purpose: NLWeb defines no other
# discovery path for it. Cost: Lighthouse's robots.txt audit doesn't know the
# directive and reports "Unknown directive" (its SEO score drops a few points;
# Google Search ignores unknown lines). Delete the line to restore that pass.
schemamap: https://vertodigital.com/schemamap.xml

# ─── ARD (Agentic Resource Discovery) ────────────────────────────────────────
# No "Agentmap:" directive on purpose: Lighthouse's robots.txt audit fails any
# directive it doesn't know ("Unknown directive"), and agents already find the
# ARD manifest at /.well-known/ard.json (the path ARD consumers MUST check),
# via <link rel="ard"> and the rel="ard" Link header, and via the
# _catalog._agents DNS TXT record.