AI search guide · Perplexity
How Perplexity finds and cites sources.
What Perplexity documents about its real-time search, which of its crawlers to let in, and what checked studies say about its answers.
Zach ChmaelChecked September 30, 2026 · from Perplexity’s documentation and checked studies
Free AI visibility check
The short answer
Perplexity, in brief.
Perplexity searches the web in real time for each question and answers with citations, so what it can find on the web today shapes the answer. Let PerplexityBot crawl your site: it’s the crawler that surfaces and links sites in Perplexity’s results, and Perplexity says it isn’t used for training. The step-by-step lives in how to get your brand cited on Perplexity.
Sources
Where it finds sources
When you ask Perplexity a question, it searches the internet in real time, gathers sources, and returns a cited, conversational answer written with models such as GPT-5 and Claude.
Perplexity, How does Perplexity work? · read September 30, 2026PerplexityBot is the crawler that surfaces and links websites in Perplexity’s search results. Perplexity says it isn’t used to crawl content for AI foundation models.
Perplexity, Perplexity Crawlers · read September 30, 2026
Crawlers
The crawlers to know
| User agent | What it does | robots.txt |
|---|---|---|
PerplexityBot | Surfaces and links websites in Perplexity’s search results; not used for training | Obeys it. Perplexity recommends allowing it, and its published IP ranges. |
Perplexity-User | Visits a page when a user’s question needs it, and may link it in the answer | Generally ignores it, since a user asked for the visit. |
Source: Perplexity, Perplexity Crawlers · read September 30, 2026
Each setting works independently, and changes can take up to 24 hours. If a firewall sits in front of your site, Perplexity’s documentation shows how to allow both agents by user agent and IP range.
Perplexity, Perplexity Crawlers · read September 30, 2026Citations
What it tends to cite
No checked study isolates Perplexity’s citations yet. This one pools eight engines, Perplexity among them; the line under the number says what was measured.
Stability
How much its answers change
- Preprint0.3–0.5
In repeated runs of the same query, the sites two answers cited overlapped by a median of about 0.3 on Gemini, 0.33–0.40 on SearchGPT and 0.5 on Perplexity, on a scale where 1 means the same sites.
Measured by domain (the Jaccard index). The author works at IQRush, which sells measurement verification for AI search.
Ronald Sielinski, arXiv, Quantifying Uncertainty in AI Visibility: A Statistical Framework for Generative Search Measurement · Mar 9, 2026
Repeated queries on three consumer topics through the Perplexity, SearchGPT and Gemini APIs: daily for nine days, plus a run every ten minutes.
First steps
What to fix first
- 01
Allow PerplexityBot in robots.txt, and let its published IP ranges through your CDN or firewall.
- 02
If your firewall challenges bots, add a rule for PerplexityBot and Perplexity-User, as Perplexity’s documentation describes.
- 03
Put what matters in the HTML: PerplexityBot was among the seven major AI crawlers that didn’t run JavaScript in Vercel and MERJ’s test.
- 04
Answer one question per page, plainly, with the evidence on the page: Perplexity writes cited answers from the pages it finds.
- 05
Earn mentions on the sites answers draw on: in AirOps’ B2B test, 85% of brand mentions came from third-party sites.
Your company
See what AI says about you
Trovance sweeps Perplexity for your buyer questions every week on every plan. See the plans
Go deeper
Read next
- How to Get Your Brand Cited on PerplexityThe engine that shows its sources, and the four steps worth taking because of it.SEO/GEO11 min read
- ChatGPT vs Perplexity vs Google AI Mode: one gate firstThe engines retrieve differently, but they all fail you the same way first. Diagnose the shared gate before you fund three playbooks.How-to11 min read
- How to Track AI Citations Across ChatGPT, Perplexity, and ClaudeOne answer is noise. A frozen question set, a few phrasings run weekly on every engine, and a log that separates mention from citation turn it into a measurement.SEO/GEO11 min read
FAQ
Questions, answered.
How do I get cited by Perplexity?
Let PerplexityBot crawl you, keep your key facts in the page’s HTML, and earn coverage on the sites it cites. Perplexity searches in real time, so check its answers again after a change, more than once. The full walkthrough has the steps.
Does blocking PerplexityBot stop Perplexity from reading my pages?
Not entirely. PerplexityBot is the crawler Perplexity uses to surface and link sites in its search results. Perplexity-User, which visits a page when a user asks, generally ignores robots.txt, Perplexity says, and may link that page in its answer.
Does Perplexity train its models on my site?
Perplexity says PerplexityBot isn’t used to crawl content for AI foundation models, and that Perplexity-User isn’t used for training either.
Rather ask a person? Text us.
Get understood. Get cited. Get chosen.
Text Trovance
Or, in iMessage, send this note to +1 (839) 205-9508:
Hi Trovance, show me how AI sees my company.
You choose to send it. Trovance replies, and sends the updates you ask for, over iMessage through our messaging provider. Reply STOP anytime. Tapping or sending never bills you.