Catalog Systems Use-case-specific agent harnesses Perplexity Deep Research

Perplexity Deep Research

https://www.perplexity.ai/hub/blog/introducing-perplexity-deep-research

Perplexity's autonomous-research mode, launched Feb-2025 — multi-step research agent inside Perplexity. Perplexity parent: $9B val Dec-2024 ($500M round; IVP + NEA + Andreessen Horowitz).

Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 43 cited facts, 2 with a third-party source · Suggest a correction

At a glance

Type
Autonomous research agent (Perplexity) vendor fix
Tier
T1
Section
Use-case-specific agent harnesses
Created
2025-02 (Deep Research launched) vendor fix
Latest release
not applicable — wrong section fix
License
not applicable — not OSS fix
GitHub
not applicable — no GitHub repo fix
Pricing
Pro $20/mo (unlimited); free 5/day vendor fix
Funding
Perplexity: $9B val Dec-2024 ($500M round; IVP + NEA + a16z) vendor fix
Freshness
2026-10-29 fix
Layer
agent-infra repo fix
Licensing
commercial vendor fix
Deployment locus
cloud vendor fix
Platform vs product
both vendor fix
Accelerator
ai-grant third-party fix
SDK languages
python, rest, typescript vendor fix
Protocols
mcp-server, openai-compatible vendor fix
Compliance
fedramp, gdpr, hipaa, iso27001, pci-dss, soc2-type2 vendor fix

When to use

Optimised for: not applicable — wrong section

Anti-fit: not applicable — wrong section

Pros & cons

Pros

$9B val parent; free-tier access to research-agent (5/day); broader-than-OpenAI source coverage.

Cons

Output quality polarising vs OpenAI; less benchmark dominance.

Claims & capabilities

Deep Research launched Feb-2025; Perplexity $9B val Dec-2024 ($500M round)

Technical surface

API surface
not applicable — wrong section
Backend storage
not applicable — wrong section
Deployment
not applicable — wrong section
Embedding model
not applicable — not a memory product
Multi-tenancy
not applicable — wrong section
MCP
not applicable — wrong section
A2A
not applicable — wrong section
OpenTelemetry
not applicable — wrong section

Alternatives to Perplexity Deep Research → live options ranked by shared design, licence, hosting and MCP support

Similar systems

Other use-case-specific agent harnesses in the catalog, ranked by inbound references.

  • Calypso AI (now F5 AI Guardrails) T2

    Dublin / NYC founded 2018; GenAI security and content scanning. $23M Series A-1 Aug-2024 (Paladin Capital + Lockheed Martin Ventures). Pivoted from defence ML to enterprise GenAI guardrails 2023-24.

  • Salesforce Agentforce T1

    Cross-listing: Salesforce Agentforce already exists under Vertical / Customer-support / voice memory; this row is the Agent-harness framing — Agentforce as the consumer-facing agent IDE / builder on Data Cloud. Agentforce launched Sep-2024; Agentforce 2.0 announced Dec-2024.

  • Lasso Security T2

    Tel-Aviv-founded LLM security platform — adversarial testing, prompt-injection defence, data-leakage prevention. $6M seed Nov-2023 (Entrée Capital + Samsung Next).

  • Pillar Security T2

    Tel-Aviv-founded (Dor Sarig + Ziv Karliner, both ex-IDF cyber); end-to-end LLM security platform — discovery, red-teaming, runtime guardrails. $9M seed Apr-2024 (Shield Capital + Greenfield).

  • Promptfoo T2

    OSS (MIT) prompt-engineering eval and red-team CLI; supports OWASP LLM Top-10 vulnerability tests, jailbreak generation, and CI/CD pipeline integration. $5M seed Mar-2024 (Andreessen Horowitz). Founders ex-Discord + ex-Smile Identity.

  • Protect AI T2

    Founded 2022 by Ian Swanson + Daryan Dehghanpisheh (ex-AWS); AI/ML supply-chain + GenAI security. Acquired by Palo Alto Networks (2025-07-22; announced Apr-2025, reported $700M); its capabilities now ship in Prisma AIRS. Products: Recon (red-team), ModelScan (model artifact scanner), Sightline (vulnerability DB).

Sources (42 cited facts, 2 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).