Perplexity on Tuesday expanded its five-month-old Model Council to its cloud-based Computer platform, allowing users to configure multi-model queries. The Model Council, described as a skill that tells an orchestrator model to spin up parallel subagents, lets users “build a board of top models for a single issue.” Models assigned to a council tackle a problem independently, resulting in a synthesis report explaining where conclusions agree and diverge. Originally launched in February with three models and no user choice, the expanded version lets users choose from two to eight models, including options from OpenAI, Anthropic, Google, and open-weight models like GLM and Kimi. Analysis depth can be customized, and Computer can turn the synthesis into “reports, board decks, and other work-ready assets.” Perplexity said the tool is ideal for ambiguous questions involving “judgment calls, tradeoffs, assessing risks or other situations where there’s no one right answer,” as model-to-model dialogue “shows where there’s consensus and where there’s conflict.” Intended use cases include legal questions, financial queries, corporate decision making, business growth modeling, and engineering. Users can ask for additional details to “sharpen the answer” and request confidence levels to see what different models think of their collective answer.