--- title: Improving Memory Retrieval: How New Computer achieved... description: New Computer, the team behind the personal AI app Dot, used LangSmith to improve their agentic memory retrieval system, achieving 50% higher recall and 40%... canonical: https://daily.dev/posts/improving-memory-retrieval-how-new-computer-achieved-50-higher-recall-with-langsmith-o1b2qypxd twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Improving Memory Retrieval: How New Computer achieved 50% higher recall with LangSmith | daily.dev og:description: New Computer, the team behind the personal AI app Dot, used LangSmith to improve their agentic memory retrieval system, achieving 50% higher recall and 40%... og:url: https://daily.dev/posts/improving-memory-retrieval-how-new-computer-achieved-50-higher-recall-with-langsmith-o1b2qypxd og:image: https://api.daily.dev/og/posts/O1B2QYpxD.png og:image:alt: Improving Memory Retrieval: How New Computer achieved 50% higher recall with LangSmith og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Improving Memory Retrieval: How New Computer achieved 50% higher recall with LangSmith **[LangChain](https://daily.dev/sources/langchain)** · 5 min read · 0 upvotes · 0 comments ## Summary New Computer, the team behind the personal AI app Dot, used LangSmith to improve their agentic memory retrieval system, achieving 50% higher recall and 40% higher precision over a baseline implementation. Their approach involved generating synthetic user data to test multiple retrieval techniques — semantic search, BM25, keyword, and meta-field filtering — and using LangSmith's experiment comparison view to identify regressions from prompt changes. The built-in prompt playground allowed rapid iteration without leaving the UI, significantly speeding up development of Dot's dynamic conversational system. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [LangMem SDK for Agent Long-Term Memory](https://daily.dev/posts/langmem-sdk-for-agent-long-term-memory-whbazr4fo) · DigitalOcean Community · 1 upvotes · 0 comments - [How Podium optimized agent behavior and reduced engineering intervention by 90% with LangSmith](https://daily.dev/posts/how-podium-optimized-agent-behavior-and-reduced-engineering-intervention-by-90-with-langsmith-kkm95atzp) · LangChain · 0 upvotes · 0 comments - [Semantic memory search for AI agents](https://daily.dev/posts/semantic-memory-search-for-ai-agents-rulp67gur) · Redis · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#rag](https://daily.dev/tags/rag), [#langchain](https://daily.dev/tags/langchain), [#langsmith](https://daily.dev/tags/langsmith) [View this post on daily.dev](https://daily.dev/posts/improving-memory-retrieval-how-new-computer-achieved-50-higher-recall-with-langsmith-o1b2qypxd) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Improving Memory Retrieval: How New Computer achieved 50% higher recall with LangSmith","url":"https://daily.dev/posts/improving-memory-retrieval-how-new-computer-achieved-50-higher-recall-with-langsmith-o1b2qypxd","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/improving-memory-retrieval-how-new-computer-achieved-50-higher-recall-with-langsmith-o1b2qypxd"},"datePublished":"2026-07-08T19:22:56.565Z","dateModified":"2026-07-08T19:23:32.255Z","description":"New Computer, the team behind the personal AI app Dot, used LangSmith to improve their agentic memory retrieval system, achieving 50% higher recall and 40%...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f60960d7c3cb84d2701c92c9eb299f87?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f60960d7c3cb84d2701c92c9eb299f87?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"LangChain","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"LangChain","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/0f4f2629e0724a849823f8cd0d913e13","url":"https://daily.dev/sources/langchain"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/improving-memory-retrieval-how-new-computer-achieved-50-higher-recall-with-langsmith-o1b2qypxd","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,rag,langchain,langsmith","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"LangChain","item":"https://daily.dev/sources/langchain"},{"@type":"ListItem","position":3,"name":"Improving Memory Retrieval: How New Computer achieved 50% higher recall with LangSmith"}]} ```