Perplexity Research
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 by Agentic.ai on our published 36-point rubric. Rubric and rules by David Kooi, Skylark Creations. See full rubric → Last re-evaluated 20 November 2026.
Is this your tool? Claim this listing to manage your content and analytics.
What's happened with Perplexity Research lately
- Current score
Agenticness score 11/36
The score shown at the top of this page. Entries marked “Score then” show the score recorded for that entry.
- Can Perplexity's new Teammates agents prove their value as investors erase $2 trillion from Nasdaq stocks?News
Perplexity announced Teammates this week, a set of persistent AI agents with assigned roles that can remember past projects and work through individual threads. The launch comes as investors question whether heavy AI spending is delivering returns, amid a roughly $2 trillion wipeout in Nasdaq value. For those tracking agentic AI products, Teammates puts role-based agents inside workplace workflows, including Slack. The unanswered test is whether these agents can handle ongoing company jobs well enough to justify their cost.
via Startup Fortune
- How far do Perplexity’s always-on Teammates go beyond Computer, and what lets them coordinate ongoing work?News
Perplexity launched Teammates, always-on AI agents that can take on different roles in a workspace and work simultaneously. The agents draw on existing projects, skills and memory, and build on Perplexity Computer, which can deploy agents on a user’s device. For those tracking agentic AI launches, this brings collaborative, ongoing work into Perplexity’s product lineup. The story leaves a key detail to explore: how Teammates handle large-scale work beyond Computer’s task completion.
via The Verge AI
- Score thentriggered by newsAgenticness score 9 → 7 ↓9 → 7/36(-2)
Score re-evaluated after: Can Perplexity's Computer for Counsel really beat Westlaw? Gunderson Dettmer says 80% of attorneys already use it.
See the news that prompted this - Can Perplexity's Computer for Counsel really beat Westlaw? Gunderson Dettmer says 80% of attorneys already use it.News
Perplexity launched Computer for Counsel on June 24, a legal-focused agentic platform that routes tasks across more than 20 frontier AI models. The system connects with document management tools, contract software, and legal research databases lawyers already use. For those tracking AI workflow automation, this shows how vendors are moving deeper into full work handling, not just search or chat. The catch is that one firm says adoption hit 80% after rollout in May 2025, but the bigger test is whether it can displace entrenched legal tools.
via Tech Times
News mentions sourced from our news feed; score changes from periodic re-evaluations.
Ask about Perplexity Research
Get answers based on Perplexity Research's actual documentation
Try asking:
About
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...
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...
Executes tasks you assign, one step at a time, within narrow domains.
Dimension Breakdown
Categories
Ask about Perplexity Research
Try asking:
- Free: 1 Research query per month
- Pro: monthly Research limits (average use)
- Max: monthly Research limits (advanced use)
Plan prices are on the Perplexity listing. Checked 2026-11-19 on Perplexity's help centre.