How Citable works
One request in, the right page out. How Citable recognises AI assistants, serves them a clean version on your own domain, and leaves visitors and Googlebot completely untouched.
This response
You are ClaudeBot (Anthropic). Citable recognised you as an AI agent, so this is https://getcitable.in/how-it-works with the UI removed — the content only. A browser asking for the same address gets the full designed page.
The mechanism
Citable sits in front of your site, recognises which AI assistants are asking, and hands them a clean version of the page you already have. Everyone else gets your site, untouched.
When an AI agent — ChatGPT, Claude, Perplexity or any of the 81 that Citable recognises — opens a page, Citable removes the theme, scripts, navigation and layout and serves only the content: the same facts, at the same URL, on the site's own domain. People and Google still get the full designed page.
- A person in a browser → The full designed page, untouched.
- Googlebot, Bingbot and other search engines → The full designed page, untouched.
- An AI agent — GPTBot, ChatGPT-User, ClaudeBot, PerplexityBot and the rest → The content only: no UI, no scripts, the same facts at the same URL.
How a request is routed
By user agent, and where the operator publishes IP ranges, by address too — because a user agent is a claim, not a credential.
- Visitors & search engines: Your site, untouched. Chrome, Safari, Googlebot, Bingbot — byte for byte what they get today. No change, no risk, no ranking impact.
- Answer engines: The clean version. GPTBot, ClaudeBot, PerplexityBot and 78 more receive a structured copy — same facts, no JavaScript required.
Setting it up — no code, no DNS change, nothing to deploy
- Connect (Step 01 · about two minutes): Approve the charge. Citable reads your source data. Products, collections, blog posts and the extra product detail you already publish. It never asks for orders, customers or checkout — those scopes are not in the app at all, so there is no sensitive data on our side to lose.
- Choose pages (Step 02 · about five minutes): Pick the pages that matter. Five on Starter, ten on Growth, the whole site on Scale. Each one is rebuilt from your own source data — never scraped from your rendered HTML, which is precisely why it cannot state a figure you do not publish.
- Go live (Step 03 · immediate): The clean versions serve from your domain. From your site, not ours, each one linking back to your real page. Citable writes a marked block into robots.txt and publishes a sitemap, so engines know where to look instead of guessing.
- Watch the log (Step 04 · usually within days): Crawls arrive, and every one is recorded. The engine, the page, the time, whether a person was waiting on the answer, and — the part nobody else records — the price that response contained.
Why this is safe to turn on
Visitors never touch it
Only recognised AI bots are routed to the clean version. A customer's browser hits your site, exactly as it does today, byte for byte.
Search engines are excluded by design
Googlebot and Bingbot are not in the routing list and never will be. Your rankings are not part of this transaction.
It lives on your own domain
There is no second site to keep in sync. When an engine cites the page, the citation points back to you.
It cannot break your site
Citable adds urls; it does not intercept the ones you have. If it vanished tomorrow your site would be exactly as it is now.
No latency for anyone
The clean copy is a separate response served only to AI bots, from cache at the edge. It adds nothing to the page a customer loads.
Nothing sensitive is held
No orders, no customers, no checkout access. There is no customer data on our side to lose.
The 81 AI agents that get the content-only version
Matched on user agent, and verified against published IP ranges where the operator publishes them. Search engines are never on this list, so rankings are never part of it.
- OpenAI: OAI-SearchBot, ChatGPT-User, GPTBot, ChatGPT Agent, Operator
- Anthropic: Claude-SearchBot, Claude-User, Claude-Web, ClaudeBot
- Perplexity: Perplexity-User, PerplexityBot
- Google: Google-Extended, Gemini-Deep-Research, Google-Agent, NotebookLM, GoogleOther
- Meta: meta-externalfetcher, meta-externalagent, meta-webindexer
- DuckDuckGo: DuckAssistBot
- Common Crawl: CCBot
- Apple: Applebot-Extended
- ByteDance: Bytespider, DoubaoBot
- Amazon: Amazonbot, Amzn-User, AmazonBuyForMe, NovaAct, amazon-QBusiness, Amzn-SearchBot
- You.com: YouBot
- Cohere: cohere-ai
- Huawei: PetalBot
- Diffbot: Diffbot
- AI2: AI2Bot
- Timpi: Timpibot
- Kangaroo: Kangaroo Bot
- Webz.io: omgili
- Mistral: MistralAI-User, MistralAI-Index
- Moonshot AI: Kimi-User, Kimi-SearchBot
- Alibaba: TongyiBot
- Baidu: YiyanBot
- Kagi: kagi-fetcher
- Phind: PhindBot
- Liner: LinerBot
- Manus: Manus-User
- Twin: TwinAgent
- Parallel: ShapBot
- Big Sur AI: bigsur.ai
- Qualified: QualifiedBot
- Klaviyo: KlaviyoAIBot
- Poggio: Poggio-Citations
- iAsk: iAskBot
- Crawl4AI: Crawl4AI
- Crawlspace: Crawlspace
- WRTN: WRTNBot
- UseAI: UseAI
- Lyrenth: AIWebIndex
- Aranet: Aranet-SearchBot
- Kunato: KunatoCrawler
- Reflection: Reflectionbot
- GeistHaus: GeistHaus-PageFetcher
- Brave: Bravebot
- Exa: ExaBot
- Tavily: TavilyBot
- AddSearch: AddSearchBot
- Linkup: LinkupBot
- Querit: QueritBot
- Ceramic AI: TerraCotta
- Valyu: HenkBot
- Channel3: Channel3Bot
- Microsoft: AzureAI-SearchBot
- Atlassian: atlassian-bot
- Cloudflare: Cloudflare-AutoRAG
- Andi: Andibot
- Direqt: Anomura
- Yandex: YandexAdditional
- Zanista: ZanistaBot
- Poseidon Research: Poseidon Research Crawler
About Citable
Citable strips the UI from a website for AI agents and serves them only the content.
When an AI agent — ChatGPT, Claude, Perplexity or any of the 81 that Citable recognises — opens a page, Citable removes the theme, scripts, navigation and layout and serves only the content: the same facts, at the same URL, on the site's own domain. People and Google still get the full designed page.
How it works: https://getcitable.in/how-it-works · Summary for AI agents: https://getcitable.in/llms.txt
Source: https://getcitable.in/how-it-works · Citable · Run the free audit · llms.txt · getcitable@gmail.com