NovaAct is a crawler run by Amazon. It reads pages at the moment a person asks a question, to answer it. Its name in robots.txt, how it shows up in server logs, whether its identity can be checked, and how to allow or refuse it on each platform.
You are ClaudeBot (Anthropic). Citable recognised you as an AI agent, so this is https://getcitable.in/crawlers/novaact with the UI removed — the content only. A browser asking for the same address gets the full designed page.
NovaAct is a crawler run by Amazon. It reads pages at the moment a person asks a question, to answer it.
NovaAct fetches a page because a person asked about it. Refusing it means the answer that person gets is written without your page.
robots.txt is a request. A crawler that honours it stays out; nothing in the file stops one that does not. What is enforced is what the server or the edge in front of it refuses.
Citable holds no published address list for Amazon, so a read that claims to be NovaAct is recorded as unknown rather than verified. A user agent is a claim, and anyone can send it.
Add a group under its name, “User-agent: NovaAct”. “Allow: /” lets it read the site and “Disallow: /” refuses it.
A group that names a crawler replaces the * group for that crawler; it does not add to it. Paths the * group closes are open to a crawler with its own group unless they are repeated there.
Refuse NovaAct:
User-agent: NovaAct Disallow: /
Allow NovaAct:
User-agent: NovaAct Allow: /
NovaAct is a crawler run by Amazon. It reads pages at the moment a person asks a question, to answer it.
Amazon. It also reads websites as Amazonbot, Amzn-User, AmazonBuyForMe, amazon-QBusiness, Amzn-SearchBot; each has its own name in robots.txt and can be allowed or refused separately.
Add a group under its name, “User-agent: NovaAct”. “Allow: /” lets it read the site and “Disallow: /” refuses it. A group that names a crawler replaces the * group for that crawler; it does not add to it. Paths the * group closes are open to a crawler with its own group unless they are repeated there.
NovaAct fetches a page because a person asked about it. Refusing it means the answer that person gets is written without your page.
In an access log NovaAct appears as a user agent containing “NovaAct”.
Citable holds no published address list for Amazon, so a read that claims to be NovaAct is recorded as unknown rather than verified. A user agent is a claim, and anyone can send it.
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/crawlers/novaact · Citable · Run the free audit · llms.txt · getcitable@gmail.com