In the project’s Firewall → Rules, add a custom rule on the User Agent parameter with the value Poseidon Research Crawler and the action Deny, then Review Changes and Publish.
You are ClaudeBot (Anthropic). Citable recognised you as an AI agent, so this is https://getcitable.in/crawlers/poseidon-research-crawler/vercel with the UI removed — the content only. A browser asking for the same address gets the full designed page.
Poseidon Research Crawler is a crawler run by Poseidon Research. It reads pages ahead of time, to train a model or to build an index.
On Vercel robots.txt is part of the project: a file in public/, or whatever the framework generates. In front of the project sits the Firewall, which can refuse a crawler before the project is asked.
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 Poseidon Research Crawler:
User-agent: Poseidon Research Crawler Disallow: /
Allow Poseidon Research Crawler:
User-agent: Poseidon Research Crawler Allow: /
The AI Bots Ruleset is one switch for every AI bot Vercel recognises, and Vercel keeps that list. On Deny it refuses all of them, and whether Poseidon Research Crawler is on that list is Vercel’s decision; a custom rule is the only control that names one crawler. It is off by default, shown in the dashboard as Allow.
Yes. A Deny in the Firewall is answered by Vercel, before the project’s code runs.
A 200 means the name is let through; a 403 means something in front of the page refuses it. This tests the name from your own address. A platform that checks a crawler’s address as well may treat the real Poseidon Research Crawler differently.
The request:
curl -I -A "Poseidon Research Crawler" https://your-site.example/
In the project’s Firewall → Rules, add a custom rule on the User Agent parameter with the value Poseidon Research Crawler and the action Deny, then Review Changes and Publish.
Leave the AI Bots Ruleset on Allow, which is its default. If it is on Deny, add a custom rule for Poseidon Research Crawler’s User Agent with the action Bypass.
Yes. A Deny in the Firewall is answered by Vercel, before the project’s code runs.
No. Googlebot goes by its own name and follows its own rules; a group or a firewall rule for Poseidon Research Crawler does not apply to 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/poseidon-research-crawler/vercel · Citable · Run the free audit · llms.txt · getcitable@gmail.com