19 November 2026Explainers with cited sources
OmnistuNews
Tech & AI

Perplexity adds a Multiagent level to Computer, where AI agents on different models check each other

It is available to Perplexity Max subscribers on the web. The capabilities described are Perplexity's own.

AI-assisted summary of linked sources · 19 November 2026 · How we report

Graphic: Perplexity adds a Multiagent level to Computer, where AI agents on different models check each other

On 17 November 2026 Perplexity launched Multiagent, a new effort level for its Computer agent platform, above the existing Ultra setting. Perplexity says it is meant for complex work with several connected parts.

How it works, per Perplexity

A lead agent plans the task and runs a team of agents on different frontier models. They work in parallel, share findings directly, and check each other's work. Perplexity says this helps surface conflicting assumptions before everything is combined into one answer. The lead can assign up to 16 agents. The default team combines Claude Opus 5.5, GPT 6.1 Sol and Gemini 4 Carbon, and users can name the models they want.

Examples and availability

Perplexity's examples include financial forecasting, annual report review, deal data room diligence and year-end tax planning, where it says the output is meant to support questions for an auditor or tax professional. Multiagent is available to all Perplexity Max subscribers on the web, selected from Computer's effort slider.

What to keep in mind

This is a vendor announcement. Perplexity gives no benchmark results for Multiagent in the post, and we have not tested it. Cross-checking between models can catch some errors but does not guarantee correct answers, so important numbers still need human review.

SourcesChecked against these sources on 19 November 2026. Spot an error? team@omnistu.com. See corrections.
More from Omnistu News