All articles

sandbox
Jul 15, 2026
Making SPACE: Secure and Efficient Runtimes for Long-Running Agents
SPACE is Perplexity’s secure, efficient sandbox platform powering long‑running agentic workflows and fast, isolated code execution.

Jul 14, 2026
WANDR Benchmark: Evaluating Research Agents That Must Search Wide and Deep
A benchmark for high-volume, evidence-heavy knowledge work

Jun 8, 2026
How AI Agents Reshape Knowledge Work
Computer raises task autonomy, lowers cost, and widens the scope of work users take on.

Jun 1, 2026
Rethinking Search as Code Generation
Evolving search from monolithic services to programmable primitives for the era of agent harnesses.

May 20, 2026
Improving Unigram Tokenizer CPU Performance
We reimplemented our Unigram tokenizer from scratch as a focused performance project.

May 14, 2026
Query-Aware Context Compression for Better Snippets
Improving the quality-efficiency frontier of model context through query-aware context compression models.

research
May 12, 2026
Hosting Qwen on Blackwell

May 6, 2026
CuTeDSL at Perplexity

research
May 1, 2026
Designing, Refining, and Maintaining Agent Skills at Perplexity
Load more

sandbox
Jul 15, 2026
Making SPACE: Secure and Efficient Runtimes for Long-Running Agents
SPACE is Perplexity’s secure, efficient sandbox platform powering long‑running agentic workflows and fast, isolated code execution.

Jul 14, 2026
WANDR Benchmark: Evaluating Research Agents That Must Search Wide and Deep
A benchmark for high-volume, evidence-heavy knowledge work

Jun 8, 2026
How AI Agents Reshape Knowledge Work
Computer raises task autonomy, lowers cost, and widens the scope of work users take on.

Jun 1, 2026
Rethinking Search as Code Generation
Evolving search from monolithic services to programmable primitives for the era of agent harnesses.

May 20, 2026
Improving Unigram Tokenizer CPU Performance
We reimplemented our Unigram tokenizer from scratch as a focused performance project.

May 14, 2026
Query-Aware Context Compression for Better Snippets
Improving the quality-efficiency frontier of model context through query-aware context compression models.

research
May 12, 2026
Hosting Qwen on Blackwell

May 6, 2026
CuTeDSL at Perplexity
Load more

sandbox
Jul 15, 2026
Making SPACE: Secure and Efficient Runtimes for Long-Running Agents
SPACE is Perplexity’s secure, efficient sandbox platform powering long‑running agentic workflows and fast, isolated code execution.

Jul 14, 2026
WANDR Benchmark: Evaluating Research Agents That Must Search Wide and Deep
A benchmark for high-volume, evidence-heavy knowledge work

Jun 8, 2026
How AI Agents Reshape Knowledge Work
Computer raises task autonomy, lowers cost, and widens the scope of work users take on.

Jun 1, 2026
Rethinking Search as Code Generation
Evolving search from monolithic services to programmable primitives for the era of agent harnesses.

May 20, 2026
Improving Unigram Tokenizer CPU Performance
We reimplemented our Unigram tokenizer from scratch as a focused performance project.

May 14, 2026
Query-Aware Context Compression for Better Snippets
Improving the quality-efficiency frontier of model context through query-aware context compression models.
Load more