--- format: "aidr-story-markdown/v1" id: "bae760ded5cfc5919a85837e32e86fd3cbb4b8dc8f0c269ae8b8e9603f341ecd" canonical_url: "https://aidr.today/bae760de?lang=en" title: "Perplexity Brain Boosts AI Correctness 9.3 Points in First Self Improving Memory System" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-08-26T16:54:25.000Z" category: "Products" topics: ["perplexity","agent","rag","memory"] source_urls: ["https://huggingnews.com/ai/update-perplexity-brain-boosts-ai-correctness-93-points-in-first-self-im-4b58bfee","https://x.com/perplexity_ai/status/2092634609079218374","https://x.com/perplexity_ai/status/2092634626842112184","https://x.com/perplexity_ai/status/2092634645099856054","https://x.com/perplexity_ai/status/2092634661239603309","https://x.com/perplexity_ai/status/2092634674090914201","https://x.com/AravSrinivas/status/2092637129835003917"] summary: "The company's new memory system compiles user sessions, files, and sources into a structured knowledge wiki to increase the accuracy of its AI agents. Perplexity reported that Brain improves correctness by 9.3 points, recall by 8.9 points, and currentness by 8.0 points while using 15% fewer tokens. The system is provided to Max users as a way to maintain factual consistency and reduce the cost of processing long user histories. The architecture utilizes a filesystem of linked Markdown files to build multi-hop context graphs. Background \"Dream\" agents run offline with specific guardrails to synthesize new information and update the wiki in a continuous loop, allowing the AI to explore history on demand and verify claims against original evidence without loading full datasets into every prompt." --- # Perplexity Brain Boosts AI Correctness 9\.3 Points in First Self Improving Memory System > [Open the canonical story]() **Published:** 2026-08-26T16:54:25.000Z **Category:** Products **Topics:** perplexity, agent, rag, memory ## Summary The company's new memory system compiles user sessions, files, and sources into a structured knowledge wiki to increase the accuracy of its AI agents\. Perplexity reported that Brain improves correctness by 9\.3 points, recall by 8\.9 points, and currentness by 8\.0 points while using 15% fewer tokens\. The system is provided to Max users as a way to maintain factual consistency and reduce the cost of processing long user histories\. The architecture utilizes a filesystem of linked Markdown files to build multi\-hop context graphs\. Background "Dream" agents run offline with specific guardrails to synthesize new information and update the wiki in a continuous loop, allowing the AI to explore history on demand and verify claims against original evidence without loading full datasets into every prompt\. ## Sources - [Story source]() - [Story source]() - [Supporting source]() - [Supporting source]() - [Supporting source]() - [Supporting source]() - [Story source]()