Description

Search and research assistant that answers questions using web sources and citations.

AI-native score

How ready this product is for agents to use, on a 0–100 scale across four weighted dimensions. Security is one of them, so a high score is not a substitute for your own security or vendor-risk review. How is this scored?

Research coverage: 69% of the scored decision fields carry a confirmed value. Unresearched fields score zero in the grade above.

Component	Raw	Weight	Contribution
Integration	4/10	35%	14.0
Trust	2/6	30%	10.0
Portability	4/4	20%	20.0
Security	3/4	15%	11.2

Signals that fired

Integration: MCP server (+2) ; API spec, OpenAPI / gRPC / GraphQL (+1) ; Agent skill (+1)
Trust: No generative AI training (available, +1) ; Sandbox environment (available, +1)
Portability: Data export (partial, +1) ; Data import (partial, +1) ; Open standards (+1) ; Standard protocol access (+1) ; No proprietary-SDK lock-in (+1) ; Self-hostable (+1)
Security: MFA available (+1) ; Compliance certifications (+1) ; Access controls — RBAC / ABAC (+1)

Signals not researched

These gaps cover the fields used in the AI-native score.

Integration surfaces: llms.txt, Headless signup, Native connectors, Developer kits
Trust & data policy: Trust center, Zero data retention, Hard budget caps, Documented provider swap

Trust & data policy

Multi-factor authentication: Available
No generative AI training: Available
Sandbox environment: Available
Data export: Partial
Data import: Partial
Open standards: Yes
Standard protocol access: Yes
No proprietary-SDK lock-in: Yes
Self-hostable: Yes
Open source: No

Not yet researched Trust center, Zero data retention, Hard budget caps, Documented provider swap

Security & compliance

Certifications and access controls this product reports on its own pages. We confirm the vendor lists each one; for certifications we don't audit the underlying report. Part of the 15% security score.

A shared trust or security page can support several certifications. We do not require separate public report links because reports may require login, vendor approval, or a nondisclosure agreement. Ask the vendor for reports and applicable coverage before a procurement decision. These listings expose no per-claim check date; the entry's updated date does not date the supporting evidence.

Compliance certifications

SOC 2

Access controls

RBAC

What it does

Capabilities

Multi-step research

Conduct iterative research across multiple sources and synthesize findings with citations.

View 4 products

Jobs to be done

Research a topic in depth

Investigate a topic or complex question and receive a detailed report backed by source citations.

View 4 products
Search the web

Find web pages relevant to a query.

View 10 products

Integration surfaces

How an agent connects to this product and finds its documentation. The largest dimension of the AI-native score (35%).

WebMCP: No

MCP servers

Model Context Protocol endpoints an AI agent can connect to for this product's tools and data.

Perplexity Computer MCP Server

API specs

Perplexity Enterprise Usage Analytics OpenAPI
OpenAPI

Agent skills

Packaged skills an agent can load to operate this product.

Perplexity Computer Research

Confirmed absent Agent2Agent (A2A) servers , Command-line interfaces

Not yet researched llms.txt, Headless signup, Native connectors, Developer kits

Offers

Full pricing page

Pro

$17/mo

Advanced answers and top AI models

$17 per month when billed annually.

View offer

Max

$167/mo

$167 per month when billed annually.

View offer

Reviews

No approved reviews yet.

RSS: approved reviews

Catalog activity

Track how this entry changes as proposals are opened and merged.

RSS: merged changes · RSS: open proposals

More from Perplexity

Other products from this publisher. Confirm you are viewing the one you want.

Perplexity API Platform Unrated

Products from other publishers that share a job-to-be-done or category, most-shared first.

You.com by You.com Tier B

Same job: Research a topic in depth (not assessed), Search the web (not assessed)
Parallel by Parallel Tier B

Same job: Research a topic in depth (not assessed), Search the web (not assessed)
Tavily by Tavily Tier B

Same job: Research a topic in depth Finishes end to end, Search the web Finishes end to end
Exa by Exa Tier B

Same job: Search the web Finishes end to end
Firecrawl by Firecrawl Tier A

Same job: Search the web (not assessed)
Brave Search API by Brave Tier B

Same job: Search the web Finishes end to end

Own this product? Add a verified badge to your site

Show visitors and crawling agents your verified AI-native grade. The badge stays current as your entry is verified, and links back to this page.

Perplexity — AI-native Tier B (55/100) on Open Agent Guide

HTML

<a href="https://www.openagentguide.com/organizations/perplexity/products/perplexity/?utm_source=badge&amp;utm_medium=referral">
  <img src="https://www.openagentguide.com/organizations/perplexity/products/perplexity/badge.svg" alt="Perplexity — AI-native Tier B (55/100) on Open Agent Guide" height="64" />
</a>

Markdown

[![Perplexity — AI-native Tier B (55/100) on Open Agent Guide](https://www.openagentguide.com/organizations/perplexity/products/perplexity/badge.svg?style=flat)](https://www.openagentguide.com/organizations/perplexity/products/perplexity/?utm_source=badge&utm_medium=referral)

Make it agent-readable (optional JSON-LD)

Paste this schema.org Review beside the badge so agents resolve the grade to its source record, not just a picture.

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Review",
  "itemReviewed": {
    "@type": "SoftwareApplication",
    "name": "Perplexity",
    "url": "https://www.perplexity.ai"
  },
  "author": {
    "@type": "Organization",
    "name": "Open Agent Guide",
    "url": "https://openagentguide.com"
  },
  "reviewRating": {
    "@type": "Rating",
    "ratingValue": 55,
    "bestRating": 100,
    "worstRating": 0,
    "alternateName": "Tier B"
  },
  "url": "https://www.openagentguide.com/organizations/perplexity/products/perplexity/"
}
</script>

The badge reflects only the verified tier and can’t be self-set. How scoring works