Perplexity launches Multiagent effort level: a lead agent orchestrates frontier-model teammates
perplexity_ai · x · 2026-11-18
Perplexity rolled out Multiagent, a new effort level in Computer and teammates. A lead agent splits tasks across a team of agents running different frontier models; as they work, agents share findings with one another, and the lead agent combines everything into one answer.
The company positions it as performance-optimized but credit-intensive, recommending it only for the most important tasks — forecasting, high-density problem solving, and consequential decision making.
More from coding & agent
- Gemini can now call businesses for you to compare quotes and book appointments — GeminiApp · 2026-11-18
- Proactive Agents That Schedule Their Own Work Hinge on Memory and UX, Says LangChain's Runkle — hwchase17 · 2026-11-18
- Cognition Launches Devin Bots: One Bot Leads a Team of Agents — aidangch · 2026-11-18
- Top token user vouches for Carbon: strong at xhigh for complex coding — olcan · 2026-11-18
- 2026's 10 Best AI Agent Frameworks: Agent Adoption Doubled, 90% Now Write Data — rseroter · 2026-11-18
- Replit Livestream With BabyAGI Creator Yohei Nakajima on Building Frontier Agents — ColleenMBrady · 2026-11-18