What's the difference between PerplexityBot and Perplexity-User?

PerplexityBot is an indexing crawler that Perplexity recommends allowing in robots.txt, while Perplexity-User is a separate agent that fetches pages in real time when a user asks a question and typically does not follow robots.txt rules. Each has its own User-Agent string and public IP range.

Can I stop my site from being cited by Perplexity?

Blocking the indexing crawler with 'User-agent: PerplexityBot / Disallow: /' in robots.txt keeps new content out of Perplexity's index. Already-indexed pages may remain visible for a while, and real-time Perplexity-User requests are not controlled by robots.txt.

What sources does Perplexity cite?

Perplexity selects sources from web results that best match the query and shows them as clickable [1][2] footnotes. A RAG pipeline searches and reranks candidates, with the indexing crawler PerplexityBot and the real-time agent Perplexity-User each handling part of that process.

Updated 2026-07-07

Frequently asked questions

What sources does Perplexity cite?: Perplexity selects sources from web results that best match the query and shows them as clickable [1][2] footnotes. A RAG pipeline searches and reranks candidates, with the indexing crawler PerplexityBot and the real-time agent Perplexity-User each handling part of that process.
What's the difference between PerplexityBot and Perplexity-User?: PerplexityBot is an indexing crawler that Perplexity recommends allowing in robots.txt, while Perplexity-User is a separate agent that fetches pages in real time when a user asks a question and typically does not follow robots.txt rules. Each has its own User-Agent string and public IP range.
Can I stop my site from being cited by Perplexity?: Blocking the indexing crawler with 'User-agent: PerplexityBot / Disallow: /' in robots.txt keeps new content out of Perplexity's index. Already-indexed pages may remain visible for a while, and real-time Perplexity-User requests are not controlled by robots.txt.