Perplexity Computer Adds Multiagent Mode: Up to 16 AI Agents That Cross-Check Each Other's Work
Perplexity has added Multiagent to Computer, its agent platform for research and multistep work. Perplexity Computer Multiagent is a new effort level that sits above Ultra. A lead agent runs a team of agents on different frontier models. Those agents work in parallel, share findings directly, and check each other's work. For developers and analysts, the change is structural: supporting agents no longer report only to a single lead.
TL;DR
- Scale: Up to 16 agents per task, plus the lead. Context length is not disclosed.
- Deployment: Runs on Perplexity's cloud. Web only, on the Perplexity Max plan. No local or quantized option.
- Performance: Not benchmarked. Perplexity published no accuracy or speed numbers.
- Standout feature: A 16-agent cap with direct agent-to-agent verification across three default model families (Claude, GPT, and Gemini).
What Is Perplexity Computer Multiagent?
Multiagent is the highest effort level in Perplexity Computer. It coordinates AI models to analyze complex tasks and cross-check their work, according to Perplexity's announcement.
It builds on effort controls...
via MarkTechPost
