Knowledge catalogue
The Perplexity Agent API documentation includes a 'Search as Code' feature accessible through the sandbox tools section, enabling developers to integrate search functionality programmatically within a
WANDR is our in-house wide benchmark, built to mirror real professional research workloads. Search as Code scores 0.386 to the next best system's 0.152, and the benchmark is far from saturated. We're
Claude Opus 4.8 has been made available to Max subscribers on the Perplexity platform and Computer application. This release expands access to Anthropic's Claude model through Perplexity's subscriptio
Computer runs on the same secure infrastructure as the rest of Perplexity. The enterprise-grade security layer includes SAML SSO, audit logs, and granular admin controls. Read more: https://www.perple
Perplexity Computer is now available inside Microsoft Excel, Word, PowerPoint, and Outlook. Orchestrate across work with Computer directly in the side panel of your app to draft documents, model, buil
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 alloca
Perplexity published a blog article detailing methods to improve the CPU performance of Unigram tokenizers, addressing computational efficiency in natural language processing. The article explores opt
We're open-sourcing the Unigram tokenizer we rebuilt to reduce CPU utilization by 5-6x. Small rerankers and embedders run in single-digit milliseconds on GPU, making CPU tokenization a meaningful shar
This post demonstrates how Perplexity AI can assist e-commerce store owners by automating multiple tasks simultaneously, including market research, AI-generated product imagery, and store design. The
Bumblebee started as an internal tool. Making Perplexity products more secure for users starts with protecting the developer systems we use to build them. Read the full blog: https://www.perplexity.ai
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 de
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: https://research.perplexity.ai/art
Less noise = more signal. Vital content per snippet is up 63%. Ads, navigation, metadata, and unhelpful content are culled before handoff to the answer model. On SimpleQA, we achieve a 50x compression
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 qual
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 sav
Build dashboards and automations from your Snowflake data for pipeline analysis, product usage, customer segments, and more. Admins maintain control over access, business definitions, and shared data
Computer 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
Computer is secure by default. Every task runs in its own hardware-isolated sandbox with VPC-level storage and compute separation. Agents are authenticated with short-lived proxy tokens instead of raw
External content is scanned in parallel by ML classifiers and the BrowseSafe model before agents act on it. File connector data is encrypted in transit and at rest, uploaded files automatically delete
PayPal runs 74,000 weekly tasks in Perplexity Enterprise. Teams use it for model validation, channel performance, market trend research, competitive intelligence, and product analysis. Read the custom
The benchmarks show the gap. NVLS all-reduce latency drops from 586.1µs on H200 to 313.3µs on GB200. In MoE prefill at EP=4, combine falls from 730.1µs to 438.5µs. For decode, GB200 sustains much high
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 faste
We published new research on how we serve post-trained Qwen3 235B models on NVIDIA GB200 NVL72 Blackwell racks. GB200 is a major step up over Hopper for high-throughput inference on large MoE models,
We've published our internal manual for building agent skills. Skills require a new way of thinking for developers. https://research.perplexity.ai/articles/designing-refining-and-maintaining-agent-ski
This post draws a parallel between Python's design philosophy (from 'The Zen of Python') and machine learning model capabilities, suggesting that if a skill or implementation can be easily explained,
This post contrasts two philosophical approaches: Python's 'Zen of Python' principle that special cases shouldn't violate general rules, versus a 'Zen of Skills' perspective arguing that gotchas and e
Perplexity has released a new Mac application for its Personal Computer feature, which users can download from perplexity.ai/personal-computer. The company is discontinuing support for the older versi
Personal Computer is built for the Mac ecosystem, so you can manage it from anywhere. Start tasks from your iPhone with local files on your Mac. Add a Mac mini for full continuity and always-on agents
Personal Computer is now available to all users in a new Perplexity Mac app. Personal Computer is an advanced version of Perplexity Computer. It operates on any Mac, running tasks across your local fi
Finance Search is now available in the Perplexity Agent API. In one tool call, developers can now retrieve licensed financial datasets, real-time market data, and cited web sources for agents that nee
Finance Search supports questions that use live market data: prices, fundamentals, earnings, filings, and market context. Agents can run valuation lookups, earnings recaps, and market monitors without
@PPLXfinance @PPLXDevs On FinSearchComp T1, Finance Search delivered the highest accuracy for live financial data and the lowest cost per correct answer in the cohort. Every result includes citations,
We’ve developed our own inference engine Runtime-Optimized Serving Engine (ROSE) to serve models ranging from embeddings to trillion-parameter LLMs. With CuTeDSL integrated into our inference engine,
Available to all Max and Enterprise subscribers in Perplexity and Computer. Available only in Computer for Pro subscribers. Read about premium health sources in Perplexity and Computer in our blog: ht
Every output is traceable. Computer shows where the data came from and links directly to the source behind key numbers. Click any citation or hyperlinked number to open the underlying SEC filing, earn
Perplexity and Computer now connect to premium health sources, starting with NEJM and BMJ Group, with 9 more medical journals and clinical databases on the way. Ask health questions and get answers ci
Perplexity offers a sourcing screen feature that allows users to input target criteria and receive a filtered list of companies matching those specifications. The tool provides transparency by explain
Today we're launching Perplexity Computer for Professional Finance. Finance teams can bring licensed data from providers like Morningstar, PitchBook, Daloopa, and Carbon Arc into Computer. We’ve also
Perplexity announced the availability of its AI-powered search and research tool in the Microsoft Marketplace, allowing enterprise users to integrate Perplexity Computer directly into their Microsoft
Perplexity has launched an integration with Microsoft Teams, enabling users to conduct research, perform analysis, and create documents directly within the Teams workspace. This integration allows Tea
Perplexity has made GPT-5.5 available to Max subscribers and is rolling it out as the default orchestration model in Perplexity Computer. The announcement indicates expanded access to OpenAI's GPT-5.5
Moonshot has released Kimi K2.6, an open-weight language model that represents a new advancement in the field, now made available to Pro and Max tier subscribers on Perplexity. The model's open-weight
Perplexity's reward design system prioritizes correctness as a foundational requirement, then evaluates user preference and efficiency only when answers meet correctness standards. This hierarchical a
This pipeline is why the same base model produces more accurate, better-cited, and more efficient answers inside Perplexity than out of the box. Read our research: https://research.perplexity.ai/artic
We've published new research on how we post-train models for accurate search-augmented answers. Our SFT + RL pipeline improves search, citation quality, instruction following, and efficiency. With Qwe
Claude Opus 4.7 has been set as the default orchestration model for Anthropic's Computer product. The model is also available to Max subscribers on Perplexity's web platform and iOS application.
Perplexity has released an updated Mac application featuring a Personal Computer feature that allows users to download the latest version. The update appears to enable enhanced AI capabilities directl
Today we're releasing Personal Computer. Personal Computer integrates with the Perplexity Mac App for secure orchestration across your local files, native apps, and browser. We’re rolling this out to
When set up on a Mac mini, Personal Computer can run 24/7 in the background across all your apps and files. Start a task from your iPhone, and Personal Computer can operate on your desktop and local f
Over the past two weeks, students researched and prepared stock pitches with Perplexity Computer. Now the top 5 finalists will present live for $17,500 in prizes to our panel of judges. Watch today’s
Perplexity AI shared a link to a live YouTube stream, likely featuring a product announcement, demonstration, or event hosted by or related to Perplexity AI. The post was shared via Perplexity's offic
All users can link their accounts, access the portfolio page, and ask Perplexity about their finances. Computer tasks are exclusive to Pro and Max subscribers. Read more: https://www.perplexity.ai/hub
Computer now connects with Plaid to link bank accounts, credit cards, and loans. Track spending in detail, build custom budget tools, and visualize your net worth alongside your investment portfolio.
Today we're announcing the Billion Dollar Build. An 8-week competition where teams will use Perplexity Computer to build a company with a path to $1B. Finalists have the opportunity to secure up to $1
Perplexity AI has launched the 'Billion Dollar Build,' an eight-week competition inviting founders to use its agentic AI system, Perplexity Computer, to build a company with a path to a $1 billion...