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.
@perplexity_ai
-
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.
-
Bumblebee scanner for AI tool configs on developer machines
By
–
Today we're open-sourcing Bumblebee, a read-only scanner for macOS and Linux. It checks developer machines for risky packages, extensions, and AI tool configs. Connected to Computer, it can trigger deeper scans whenever a new supply-chain risk emerges. https://
github.com/perplexityai/b
umblebee
… -
Query-Aware Context Compression in RAG Systems
By
–
Context compression isn't new in RAG. Our contribution is making it query-aware, citation-preserving, and fast enough for orchestration. Read the full research blog:
-
AI-Powered Query-Aware Compression for Enhanced Search Accuracy
By
–
We've productionized query-aware compression for faster, cleaner, more-accurate search. Better context is better than more context. Our system cuts context tokens up to 70% while improving answer quality.
-
AI Tool Saves 120 Work Hours by Automating Task Management
By
–
Rho cut weekly meeting time by 90% with Perplexity Computer. Computer checks Slack, Notion, Jira, Figma, and Google Docs, then flags missing tasks and changes the team needs to see. 120 work hours saved during a 12-week project. Read the customer story:
-
AI Agent Integration Enables Automated Data Analysis with Snowflake
By
–
Computer now connects to Snowflake.
— Perplexity (@perplexity_ai) 14 mai 2026
Run end-to-end work against live warehouse data and get answers with SQL, source tables, filters, and metrics.
It’s like a personal data science team, on call with accurate answers from live company data. pic.twitter.com/L1uQC6u5zZComputer now connects to Snowflake. Run end-to-end work against live warehouse data and get answers with SQL, source tables, filters, and metrics. It’s like a personal data science team, on call with accurate answers from live company data.
-
NVIDIA GB200 Architecture Optimized for Large-Model Inference
By
–
This NVIDIA remains the strongest platform for large-model inference at scale. Prefill/decode disaggregation, Blackwell-native quantization, custom kernels, and rack-scale NVLink turn GB200 into faster answers lower serving cost. Read the full paper here