Perplexity adds effort controls to Computer, pairing orchestrator models with reasoning depth
perplexity_ai · x · 2026-09-18
Perplexity is rolling out effort controls for its Computer product, now live on web with mobile and desktop coming soon.
- Effort presets combine the orchestrator model with reasoning depth to control how deeply and efficiently Computer works through a task
- Customizable: users can adjust model selection, reasoning level, and speed settings
- Design philosophy: the stated goal is maximum intelligence at minimum cost via multi-model orchestration; Perplexity says it will keep refining the model-agnostic harness and the orchestrator/subagent combinations behind each effort level as frontier models advance
Related event: Perplexity Computer Adds Effort Control for Model Orchestration(2 posts)→
More from coding & agent
- Claude Code 2.1.275 release imminent — ClaudeCodeLog · 2026-09-18
- Legora's take: there is no best model — lawyers write evals and Legora BAR picks the winner — soleio · 2026-09-18
- Research with Agents: reflections and lessons from using AI agents in scientific work — _xiang_chen_ · 2026-09-18
- Addy Osmani: Running Agents in Old Codebases — Brownfield Agentic Engineering — rseroter · 2026-09-18
- Google's Stellar Colosseum: many-agent harness proves new math theorems — IgorCarron · 2026-09-18
- Official MCP extension lets agents discover and load Skills directly from MCP servers — solyarisoftware · 2026-09-18