The Perplexity Blog

OG card: chart-to-art exploded axonometric of the JOLT training figure: one set of weights at the base, the Teacher and Student roles above it, six generations per role on top, with crossing dashed paths for each role scoring the other
Research21 Oct 2026A good teacher meets the student where they areA new self-distillation method that jointly trains teacher and student to improve model performance and training efficiency on complex reasoning and agentic tasks.
People working on laptops with the U.S. Capitol visible through a window at dusk.
News28 Oct 2026New FedRAMP certification brings Perplexity to more government workflowsFederal agencies can search the live web with Perplexity and get cited answers as part of a new FedRAMP certification.

Featured

  1. A white shield and keyhole on a translucent glass tile against a teal landscape.
    Ideas29 Sept 2026How we engineer safer agentsLayered safeguards, independent monitoring, and human oversight across Perplexity’s cloud, browser, local, and endpoint agents.
  2. Abstract glass panel with illuminated edges separating light and shadow against a dark background.
    News15 Oct 2026Open-sourcing SPACE, the sandbox platform behind ComputerPerplexity open-sources SPACE, the sandbox platform behind Computer, to help developers build safer autonomous AI agents
  3. Two people working at separate desks in a dimly lit office.
    Developers28 Sept 2026Agent API now supports reusable agentsTeams create reusable agents with versioned Profiles, Skills, and managed connectors they can share across applications.

More from the Perplexity Research team

  1. Escaping SPACE: Part IRed-teaming VM isolation and network confinement for AI agents.
  2. Building shared workspaces for people and agentsHow Perplexity Projects keep long-running work persistent, concurrent, and traceable.
  3. Multimodal embeddings beyond a single vectorA new family of late-interaction models for text and image retrieval, with a shared embedding space across model sizes.
All research

Recently published

211 posts found

  1. Text embeddings explained: how they work [+examples]This guide explains what text embeddings are, how they turn text into vectors that capture meaning, and how to choose, evaluate, and apply embedding models to search, RAG, and other real-world use cases.
  2. New FedRAMP certification brings Perplexity to more government workflowsFederal agencies can search the live web with Perplexity and get cited answers as part of a new FedRAMP certification.
  3. Basic RAG Implementation: A Step-by-Step TutorialThis beginner-friendly tutorial explains how a basic RAG implementation works, covers best practices, and walks through building a working command-line RAG system with Python, ChromaDB, and Perplexity's embedding and language models.
  4. How does an LLM gateway work? A practical guide for engineering teamsAn LLM gateway is a reverse proxy that routes, authenticates, caches and logs your model calls; this guide follows a request through one, covers the security and reliability risks to plan for, and compares building, self-hosting, managed and API-gateway options.
  5. What Is RAG Architecture? A Full Definition With Detailed Practical ExamplesRAG architecture is the set of components that stores, retrieves, and feeds external information to an LLM; this guide breaks down 10 types, from basic and hybrid RAG to agentic RAG and GraphRAG, with two step-by-step examples.
  6. How to evaluate AI agents: test sets, graders and regression checksA practical six-step guide to evaluating AI agents, from defining success and building test sets from real failures to choosing graders, running regression checks and monitoring in production.
  7. How to track and control team token spendHow teams can see their token usage in dashboards and reports, which kinds of AI work use the most tokens, and how to use controls to reduce it.
  8. A good teacher meets the student where they areA new self-distillation method that jointly trains teacher and student to improve model performance and training efficiency on complex reasoning and agentic tasks.
  9. What Is an AI Gateway? A Guide to Routing, Cost Control, and Governance for LLM and Agent TrafficAn AI gateway is a central proxy between your applications or AI agents and the models they call, handling routing, cost control, security, and observability in one place.
  10. Perplexity brings Computer to enterprise infrastructure with ValarianPerplexity and Valarian bring Computer to institutional infrastructure with controls for sensitive data and regulated workloads