Platform guide
How Perplexity chooses and cites sources
Perplexity shows numbered citations with every answer. Its documented crawler, PerplexityBot, indexes sites for Perplexity search and respects robots.txt; Perplexity-User fetches pages live when a user asks. Perplexity does not publish how it ranks sources, so precise figures you may read about its retrieval are estimates.
Documented
- PerplexityBot surfaces and links websites in Perplexity search and follows robots.txt.
- Perplexity-User fetches pages for live questions; Perplexity’s documentation describes how it treats robots.txt.
- The Publishers Program (announced July 2024) shares revenue with partner publishers; it is not required to be cited.
Not documented
- How many pages it retrieves or cites per answer.
- How sources are reranked.
- Any weighting for freshness or domain.
Checklist
- Allow PerplexityBot in robots.txt.
- Keep important pages current and dated where dates matter.
- Give direct answers with sources, so a short excerpt makes sense alone.
Checked against the company’s own documentation on 16 November 2026. Ranking methods are not published by any of these companies; anything beyond the documented controls is informed estimation, not fact.
Related services
Sources
Primary references this guide relies on. Provider documentation changes, so check the source before acting.
Questions
No. It is a commercial programme for publishers; ordinary sites are cited without it.
Ready to talk through your project?
Send a voice note, spreadsheet or a plain description of where your business is struggling. We’ll help you find the right next step.

