Perplexity Computer
A cloud "digital worker" that splits a goal into subtasks and hands them to a team of sub-agents running different models.
By Perplexity · launched 2026-02-25 · last checked 2026-11-02
Why 4: it breaks an outcome into tasks, spins up sub-agents and runs for long periods in isolated environments, only checking in when it truly needs you; it acts on request, not continuously.
What it does. Computer breaks an outcome into tasks and spins up sub-agents for web research, documents, data processing and calls to connected services. Each task runs in an isolated environment with a file system and browser. At launch Claude Opus 4.6 coordinated sub-agents using Gemini, Nano Banana, Veo 3.1, Grok and GPT-5.2, and it can run for long periods and in parallel.
Where it falls short. Perplexity says it will "check in" when it truly needs you, but describes few other safeguards. We found no independent evaluation of how well it finishes work.
What it can do
Incidents
- None logged.
Closest fiction
Moon — Each copy wakes, does its part and reports back.
Related general assistant agents
- ChatGPT Work OpenAI · autonomy 4/5
- Claude Cowork Anthropic · autonomy 4/5
- Gemini Spark (Gemini Agent) Google · autonomy 4/5
- Genspark Super Agent Genspark (MainFunc) · autonomy 4/5
- Grok Bot xAI · autonomy 4/5
- Manus Butterfly Effect · autonomy 4/5
History
- 2026-11-01 Added to the index.
- 2026-11-02 Re-checked, no change.
Sources
- Introducing Perplexity Computer Perplexity, 2026-02-25
- Perplexity's new Computer agent will run other agents for you Computerworld, 2026-02-27
- Perplexity Computer expands access to Pro subscribers Createwith, 2026-03-12
← All agents in the index · Autonomy is rated on what the product does today, on a 1–5 scale. Every fact links to a source.