We have found that more autonomy with autonomous agents like Computer results in better quality tracking and greater satisfaction.
@perplexity_ai
-
Cost Comparison of Human and Computer Research
By
–
Research is cheap to start but costly per step, since the human executes each one. Computing costs more upfront to delegate and verify, but little per step, since the agent executes the steps. It is worth it once a task
-
Perplexity and Harvard Research: Autonomous Agents 87% Faster, 94% Cheaper
By
–
We have published new research with Harvard on the transition from chat interfaces to autonomous agents like Computer. Over 3 months, the results show that workers using Computer complete tasks in 87% less time and at 94% less cost.
-
Hybrid agentic inference in Perplexity Computer
By
–
Read more about hybrid agentic inference in Perplexity Computer:
-
Perplexity Computer announces hybrid agentic inference with local and cloud
By
–
Today we're announcing that hybrid agentic inference is coming to Perplexity Computer.
— Perplexity (@perplexity_ai) 2 juin 2026
Computer can split tasks between a local model running on your machine and frontier models in the cloud. This keeps private data on your device and maximizes token efficiency.
Coming soon. pic.twitter.com/6t3PrmI1FXToday we're announcing that hybrid agentic inference is coming to Perplexity Computer. Computer can split tasks between a local model running on your machine and frontier models in the cloud. This keeps private data on your device and maximizes token efficiency. Coming soon.
-
Perplexity AI achieves new cost-performance frontier, outperforming Anthropic
By
–
It also sets a new cost-performance frontier. On DSQA it scores 0.871, ahead of Anthropic's 0.815, at nearly half the cost per task. On WideSearch it leads on score while running cheaper.
-
Search as Code beats all competitors on five benchmarks
By
–
We tested Search as Code on deep research (DSQA, BrowseComp, HLE) and wide research benchmarks (WideSearch, WANDR). It matches or beats every competing system across all five.
-
Search as Code replaces tool-calling with async search primitives
By
–
The traditional tool-calling approach suffers from high latency, manual control flow, and context pollution. With Search as Code, the model composes search primitives: fanning out queries asynchronously, deduping, filtering, joining, and ranking before results hits its context.
-
Perplexity launches Search as Code for AI agents
By
–
Introducing Search as Code, our new search architecture for AI agents. It writes Python that calls our search stack directly, instead of looping through function calls one at a time. Available in the Perplexity Agent API, and now default in Computer. https://
research.perplexity.ai/articles/rethi
nking-search-as-code-generation
… -
AI Encoder Tokenizer Performance: 5× Latency Improvement
By
–
At production input lengths, the encoder cuts p50 latency by roughly 5× vs. HuggingFace tokenizers, 2× vs. SentencePiece C++, and 1.5× vs. IREE C. At 514 tokens, it runs in 63 µs with zero heap allocations.