NORAD.io
OVERVIEWCOUNTRIESBOTSTHREATS

PERPLEXITY-USER

LOW RISK🤖 AI ASSISTANT BROWSER

Perplexity's real-time page fetcher — retrieves content during user search sessions

ORGANIZATION
Perplexity AI
FIRST SEEN
2024-01
RESPECTS ROBOTS.TXT
✓ YES
DOCUMENTATION
docs.perplexity.ai
—
DAILY VISITS
—
COUNTRIES ACTIVE
TRACKING
STATUS
—
LAST SEEN

📡 PERPLEXITY-USER USER-AGENT STRING

Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Perplexity-User/1.0; +https://perplexity.ai)

This is the User-Agent header sent by Perplexity-User in HTTP requests. Use this to identify Perplexity-User in your server access logs.

📋 ABOUT PERPLEXITY-USER

Perplexity-User is the real-time page fetcher used by Perplexity AI during active user search sessions. While PerplexityBot indexes content for Perplexity's search corpus, Perplexity-User fetches specific pages on-demand when generating cited answers for user queries.

This bot represents the growing category of 'AI assistant browsers' — bots that fetch web content in real-time to ground AI responses in current information. Each Perplexity-User request corresponds to a real user search where Perplexity's AI is pulling information from web sources to construct a cited, conversational answer.

NORAD.io tracks Perplexity-User to help site operators understand their content's role in Perplexity's answer generation. Sites that appear frequently in Perplexity-User fetches are being actively cited in AI-generated answers, providing visibility similar to search engine referral traffic but through an AI-intermediated channel.

🎯 HOW TO DETECT PERPLEXITY-USER

  • ▸User-Agent contains 'Perplexity-User' — distinct from 'PerplexityBot'
  • ▸Sporadic, user-driven request patterns
  • ▸Single page fetches rather than site-wide crawling
  • ▸Often fetches pages that rank for current trending topics
  • ▸Similar concept to ChatGPT-User for OpenAI

🔄 CRAWL BEHAVIOR

On-demand fetching triggered by user search queries. Single-page requests rather than systematic crawling. Fetches pages cited in Perplexity's AI-generated answers. No JavaScript execution.

PURPOSE

Fetches web pages in real-time during Perplexity search sessions to provide cited, up-to-date answers. Each request corresponds to a user query where Perplexity's AI is synthesizing information from web sources.

🤖 ROBOTS.TXT CONFIGURATION

User-agent: Perplexity-User
Allow: /

# Separate from PerplexityBot (indexing crawler)
# Blocking this prevents real-time citations from your site

Perplexity-User respects robots.txt directives. Add this to your robots.txt file at the root of your domain.

→ Complete Guide: robots.txt for AI Bots

🗺️ WHERE IS PERPLEXITY-USER ACTIVE?

🇺🇸
United States
🇨🇦
Canada
🇲🇽
Mexico
🇬🇹
Guatemala
🇨🇺
Cuba
🇭🇹
Haiti
🇩🇴
Dominican Republic
🇭🇳
Honduras
🇳🇮
Nicaragua
🇸🇻
El Salvador
🇨🇷
Costa Rica
🇵🇦
Panama

⚠️ RELATED THREATS

Prompt Injection

Attempts to override bot instructions via malicious content embedded in web pages

Data Exfiltration

Bots attempting to extract sensitive data from websites including PII and credentials

Credential Stuffing

Automated login attempts using leaked credentials from data breaches

Aggressive Content Scraping

Bots aggressively scraping content beyond robots.txt limits and ToS

🔗 RELATED BOTS

PerplexityBotLOW

Perplexity AI · Perplexity AI's web indexing crawler for its AI-powered search engine

📂 MORE 🤖 AI ASSISTANT BROWSERS

ChatGPT-UserOpenAIPerplexityBotPerplexity AIAnthropic-AIAnthropicClaude-WebAnthropic

📚 RELATED GUIDES

How to Detect AI Bots →robots.txt for AI Bots →NORAD API Docs →

PROTECT YOUR WEBSITE

Deploy SiteTrust to monitor and control AI bot access to your site with the Agent Passport Standard.

INSTALL SITETRUST →