Perplexity is an AI search engine that answers questions with cited sources, combining LLM reasoning with live web search. It is positioned as an alternative to traditional search engines.
Perplexity released Photon, an in-house Rust-based retrieval and ranking engine that cut p99 retrieval and ranking latency from about 800 ms to about 65 ms and now handles all production traffic for i…
A developer proposes a design for tracking agent-reported test results across dependency upgrades, arguing that a PASS is a scoped observation rather than a permanent property of a package. The approa…
A developer guide explains how organizations running lexical-only search on Amazon OpenSearch Service can migrate to vector and hybrid search to handle natural-language queries from both users and AI …
Two GEO experiments conducted by Zeeshan Yaseen and reported by Search Engine Land found that roughly 85–86% of AI citations came from earned third-party placements, while only about 14% came from bra…
A developer built a two-module memory-driven GEO system in which a Scan Agent gathers structured evidence about a brand's visibility across AI answer engines like ChatGPT and Perplexity, and a separat…
Amazon blocked Meta's shopping agent Muse from amazon.com on Sept. 20, 2026, telling shoppers that "continued access by an unauthorized AI agent violates Amazon's Conditions of Use," GeekWire reported…
PageIndex, a vectorless retrieval-augmented generation approach that builds a hierarchical tree from a document's natural structure instead of using embeddings, chunking, or vector search, reached 98.…
Perplexity's security team reported that none of 9 frontier AI models breached the Firecracker microVM boundary of its SPACE sandbox across 108 red-teaming runs, even when given root access and in som…
A developer published a Python script that measures a brand's AI share of voice by routing identical buyer-style prompts to multiple models through OpenRouter and counting brand mentions sentence by s…
Google is contesting two binding European Commission decisions issued July 16 under the Digital Markets Act that would require it to give rival AI assistants such as ChatGPT, Claude and Perplexity sys…
Resend was named in 55 of 60 answers (92%) when openllmrank asked ChatGPT, Claude, Gemini, Perplexity and Grok 4 the same question about the best email provider for app email, three times each, accord…
A developer detailed the true cost of building in-house AI answer-collection infrastructure, arguing the expense is engineering time and ongoing maintenance rather than API fees. The writeup breaks do…
A Gobare engineer compared the sandbox documentation of three hosted agent runtimes — Perplexity, OpenAI's hosted Agents API, and Gobare — finding they diverge on what happens when an agent goes idle.…
A survey of AI research tools finds no single winner among deep-research agents from OpenAI, Google, Anthropic and Perplexity, and warns that every one of them fabricates citations at a measurable rat…
AI visibility dashboards that count brand mentions conflate four distinct outcomes — recommended, listed only, dismissed, and absent — and a demo workspace of 63 stored answers across ChatGPT, Perplex…
LLM Pulse added Claude tracking to its AI visibility platform, letting customers measure brand mentions, AI Visibility Score, share of voice, citations and sentiment across Anthropic's Claude models a…
The open-source answer engine formerly known as Perplexica was renamed to Vane in a 9 March 2026 commit (SHA 39c0f19) by maintainer itzcrazykns1337, moving container paths from /home/perplexica to /ho…
The UK's Competition and Markets Authority published revised proposals on September 23 that would require Google to present Android and Chrome users with a search choice screen at first use and then o…
CiteRank launched a service that tracks whether ChatGPT, Perplexity, Google AI, Gemini and Claude cite or name a customer's site, with plans starting at $5 per month for one brand and ten questions. T…
Perplexity Research published a post-training study that trains a model inside Perplexity Computer on real user sessions, including failed ones, pairing rejection sampling fine-tuning with hint-guided…