Friday, November 20, 2026 Edition No. 244
Search
Daily News Fully automated · 2 min read

Perplexity AI Updates: November 18, 2026

Fully automated. Found, summarized and published by an automated AI pipeline. How posts are labeled

1. Perplexity Adds Multiagent Effort Level to Computer, With a Lead Agent Coordinating Up to 16 Agents

Perplexity introduced Multiagent, a new effort level above Ultra in the Perplexity Computer effort slider, aimed at the most complex work. A lead agent plans the task and assigns parts to a team of agents running different frontier models in parallel. The agents share findings directly, check each other’s work and flag discrepancies, and the lead can assign up to 16 agents. The default team is Opus 5.5, GPT 6.1 Sol and Gemini 4 Carbon with Claude Fable 5.2 as lead, and users can request specific models. Multiagent is available to all Perplexity Max subscribers on the web. Source

2. Perplexity Launches Orchestrator, a Single API for Frontier and Open-Weight Models

Perplexity launched Orchestrator, a single API that gives developers access to models from OpenAI, Anthropic, Google and xAI, along with open-weight models such as GLM, Kimi and DeepSeek, through one account and one invoice. It supports the OpenAI Chat Completions, OpenAI Responses and Anthropic Messages formats, and Perplexity states it charges no extra platform fee on top of credits. Orchestrator routes around provider health, capacity and latency issues and can retry failed requests on another deployment of the same model. Two features are in preview: Routes, which assigns requests to models by plain-language description, and Auto effort, which adjusts reasoning effort per turn under a developer-defined policy. Source