The Perplexity Blog


Featured
IdeasNov 1, 2026The Knowledge Talk
NewsOct 15, 2026Open-sourcing SPACE, the sandbox platform behind ComputerPerplexity open-sources SPACE, the sandbox platform behind Computer, to help developers build safer autonomous AI agents
DevelopersSep 28, 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
Perplexity DeciderHow we train, evaluate, and use it.
Escaping SPACE: Part IIModel behavior in red-teaming experiments.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.
Recently published
233 posts found
Introducing Perplexity Frontier ResearchOur mission and research agenda in advancing autonomous discovery.
Introducing Perplexity’s Monitor APITrack web developments and page changes with Perplexity’s Monitor API. Get relevant updates delivered through a webhook.
AGI vs. AI: Key differences and how to evaluate AGI claimsCompare AI and AGI, explore competing definitions and learn how to assess benchmarks and claims of general intelligence.
Types of search engines: crawlers, meta search, and AI answer enginesHow crawler-based, meta search, and AI answer engines find and return results, plus the other types of search engine, from privacy-focused and paid to vertical, regional, and enterprise.
Context window: what it is and how it affects everyday AI useA guide to the context window in AI models, covering how it's measured in tokens, what fills it during a conversation, how large it is in current models, what happens when a conversation passes the limit, and everyday habits for working within it.
Perplexity DeciderHow we train, evaluate, and use it.
Escaping SPACE: Part IIModel behavior in red-teaming experiments.
AI compliance: governing AI systems and using AI for compliance workA guide to AI compliance covering the risks it addresses, the EU AI Act, NIST AI RMF, and ISO/IEC 42001, how to build a compliance program, controls for AI agents, and how compliance teams use AI.
MCP Architecture: Full Technical Breakdown With DiagramsA technical breakdown of MCP architecture covering hosts, clients, and servers, the JSON-RPC data layer, transport options, multi-tenant setups, security risks, and an eight-step request walkthrough with diagrams.
AI memory: what it is, how it works, and what it storesA guide to AI memory: how AI assistants save and recall details from past conversations, what they store, where memory goes wrong, and how to view, edit, or turn it off.