---
title: "Perplexity Computer can run up to 16 cross-checking agents"
url: https://www.parallelquant.com/posts/perplexity-computer-can-run-up-to-16-cross-checking-agents-85bf87
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/11/17/perplexity-computer-multiagent-effort-level/
published: 2026-11-17T22:52:04.000Z
topics: ["agents", "products"]
publisher: "Parallel Quant"
---

# Perplexity Computer can run up to 16 cross-checking agents

*2026-11-17 · Source: [MarkTechPost](https://www.marktechpost.com/2026/11/17/perplexity-computer-multiagent-effort-level/)*

Perplexity added a Multiagent mode to its Computer product, an effort level above Ultra. A lead agent coordinates up to 16 agents running on Claude, GPT and Gemini models, which share findings and check each other's work.

**Why it matters:** Mixing models from different labs is a practical way to catch errors, because models from different labs tend to fail in different ways. It also shows that companies building apps on top of frontier models treat those models as interchangeable parts, which weakens the pricing power of any single lab.

**Topics:** agents, products

---
Read the original: https://www.marktechpost.com/2026/11/17/perplexity-computer-multiagent-effort-level/
Canonical: https://www.parallelquant.com/posts/perplexity-computer-can-run-up-to-16-cross-checking-agents-85bf87
Published by Parallel Quant — https://www.parallelquant.com
