Skip to main content
PR

Deep research reports with citations, web browsing, and file analysis

Perplexity Research helps you turn broad questions into structured, source-backed reports. Advanced Deep Research adds more web coverage, document processing, calculations, and a progress view for longer investigations.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric →

See pricing ↓

Visit Perplexity Research

Is this your tool? Claim this listing to manage your content and analytics.

Ask about Perplexity Research

Get answers based on Perplexity Research's actual documentation

Try asking:

About

What It Is

Perplexity Research is a web-based research and analysis tool inside Perplexity, aimed at knowledge workers, researchers, students, and other users who need more than a quick answer. It is designed to search multiple sources, cross-reference...

What to Know

This is more agentic than a normal chat assistant because it can browse the web, read uploaded documents, run calculations in a code sandbox, and continue a research session with follow-up questions. It also surfaces progress and key findings as it...

Key Features
Searches and cross-references multiple web sources
Produces citation-backed research reports
Processes uploaded documents during research
Runs calculations and data analysis in an improved code sandbox
Browses harder-to-reach web sources
Use Cases
Preparing a market analysis with source citations
Comparing products or vendors across multiple sources
Writing a thesis or literature review
Agenticness: Guided Assistant

Executes tasks you assign, one step at a time, within narrow domains.

High evidence
Last evaluated: Jul 24, 2026

Dimension Breakdown

Action Capability
Autonomy
Adaptation
State & Memory
Safety

Categories

Pricing
  • Pro: Extended access to Deep Research, plus higher research limits and access to Perplexity’s advanced models.
  • Max: Uses Perplexity’s most capable Deep Research model, Opus 4.6 Thinking, with higher compute allocation per session.
Details
AddedJuly 24, 2026
RefreshedJuly 24, 2026
Agenticness
Quick Facts
DeploymentCloud-hosted
AutonomySemi-autonomous
Model supportMulti-model
Open sourceNo
Team supportIndividual only
Pricing modelSubscription
Interfaceweb, gui
Sources
Last updated July 24, 2026
Stay in the loop

Get the weekly agentic AI briefing

New tools, top picks, and trends — delivered every Thursday.

I use AI for: