AI engines · Perplexity

Perplexity: the engine that searches and cites in every answer

Perplexity is an assistant built like a search engine: it answers from real-time web results and links the sources it uses. To show up, PerplexityBot must be able to crawl your site and your brand must be on the pages it finds. GeoRush queries its Sonar model, which searches on its own, and measures how often Perplexity names and cites you.

Updated on

Young man looking through binoculars with a desert landscape behind him

How Perplexity builds its answers

Unlike assistants that decide whether to search, Perplexity is built around search: its answer rests on web results and links to them. Its developer model, Sonar, returns a citations list with source URLs plus a search_results list with each result’s title, URL, date and snippet, according to Perplexity’s documentation.

Which sites can appear depends on its crawlers. Perplexity’s bots documentation says PerplexityBot is designed to surface and link websites in Perplexity’s search results, is not used to crawl content for AI foundation models and, to appear, recommends allowing it in robots.txt and permitting its published IP ranges. Perplexity-User visits pages when a user asks, to improve an answer; because a person triggers it, Perplexity says it generally ignores robots.txt rules.

Perplexity in GeoRush: fact sheet

FactPerplexity
CompanyPerplexity AI
How GeoRush queries itPerplexity’s Sonar model via API, which always uses Perplexity’s own search
Web searchPerplexity’s own: Sonar searches by itself on every question
Credits per answer1 (Claude analysis included)
Cites sources?Yes, on every web-backed answer. GeoRush stores every cited URL
Key crawlersPerplexityBot (search results) and Perplexity-User (user-triggered visits)

GeoRush configuration as of November 2026. The exact model that answered is stored with each answer.

What it means for your brand

For GEO (generative engine optimization) in Perplexity, what matters is:

  • Sources weigh more here than anywhere. Since every answer starts with a search, what today’s pages say matters more than what the model learned months ago.
  • Blocking PerplexityBot takes you off the shelf. According to Perplexity, it is the bot that lets your site appear and be linked in its results.
  • Changes show up sooner. A new page or a mention on a reference site can be reflected as soon as Perplexity finds it, without waiting for retraining.
  • Citations are visible to users. Being a cited source brings clicks and credibility, not just a mention, so citation rate matters as much as mention rate.
  • Dates and freshness count. Results carry dates; updated content with dated facts is easier to use as a source.

How to become more visible in Perplexity

  1. 1

    Allow PerplexityBot

    In robots.txt and in your firewall. The guide robots.txt for AI bots explains how to separate search bots from training bots.

  2. 2

    Build pages that each answer one question

    Honest comparisons, pricing, alternatives and use cases, with concrete facts and an update date.

  3. 3

    Appear on the sources it cites

    Perplexity links its sources, so it is easy to see which ones matter in your category. Sources and citations groups them by type and Get cited helps you reach out.

  4. 4

    Keep information current

    Up-to-date pricing, plans and company facts on your site and in directories. An old source can get cited with old facts.

  5. 5

    Follow the dedicated guide

    The guide how to show up in Perplexity covers each step.

How GeoRush measures your Perplexity visibility

  • It asks Perplexity the questions you track, in your brand’s language and country, instructing it to answer as it would for a user in that country and to name specific products when relevant.
  • It repeats each question several times (3 by default, up to 5) to measure real frequency.
  • Claude reads every answer: brands and order, tone, claims about you checked against your official facts, and newly recommended brands.
  • It calculates Perplexity on its own: mention rate (with a 95% confidence range), share of voice, citation rate (whether your domain is among the sources), average position and sentiment.
  • It stores every URL Perplexity cited, which feeds Sources and citations and the opportunities in Get cited.
  • Each Perplexity answer costs 1 credit. Example: 20 questions × 3 runs = 60 credits per sweep.

Does Perplexity cite you?

Run the free check, or start free to track Perplexity and the other eight engines.

Frequently asked questions

Perplexity is designed to answer from web searches and link its sources; its Sonar API returns the cited URLs alongside the answer.

According to Perplexity, PerplexityBot is the bot that surfaces and links websites in its results, so blocking it reduces your chances of appearing as a source.

According to its documentation, neither PerplexityBot nor Perplexity-User is used to collect content for training AI foundation models.

1 credit per answer, Claude analysis included.

Sonar, Perplexity’s model with built-in web search. The exact model is stored with each answer.

Keep reading