--- title: From Systems of Record to Systems of Context — Omri... description: Engineers from monday.com describe their architectural approach to building an AI personal assistant called Sidekick that goes beyond data retrieval to achieve... canonical: https://daily.dev/posts/from-systems-of-record-to-systems-of-context-omri-bruchim-monday-com-j1hoononh twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: From Systems of Record to Systems of Context — Omri Bruchim, monday.com | daily.dev og:description: Engineers from monday.com describe their architectural approach to building an AI personal assistant called Sidekick that goes beyond data retrieval to achieve... og:url: https://daily.dev/posts/from-systems-of-record-to-systems-of-context-omri-bruchim-monday-com-j1hoononh og:image: https://api.daily.dev/og/posts/J1HOononH.png og:image:alt: From Systems of Record to Systems of Context — Omri Bruchim, monday.com 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. # From Systems of Record to Systems of Context — Omri Bruchim, monday.com **[AI Engineer](https://daily.dev/sources/aidotengineer)** · 15 min read · 1 upvotes · 0 comments ## Summary Engineers from monday.com describe their architectural approach to building an AI personal assistant called Sidekick that goes beyond data retrieval to achieve genuine understanding of how users work. The core insight is that AI assistants fail at questions like 'what should I focus on?' not because they lack data, but because they lack understanding of relationships between data points. Their solution, the 'Monday World Model,' uses two processing engines inspired by neuroscience's complementary learning systems and data engineering's lambda architecture: a slow engine that builds a durable user profile over weeks, and a fast engine that computes live signals over recent activity. Both run offline and ahead of time, so when a user queries Sidekick, rich pre-computed context is already available for the agent to reason over. The system compounds over time, gracefully degrades when data sources fail, and is unique to each user's work patterns. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Why do AI assistants like Claude or GPT fail to prioritize my tasks even when connected to all my work data? They have access to the data but lack understanding of how the pieces connect to each other and to the user's actual priorities. Connecting Slack, email, and task boards gives an assistant all the records, but without pre-built understanding of relationships between entities, it can only guess at what matters, producing generic disconnected bullet-point answers rather than a real prioritized recommendation. _daily.dev helps developers building AI agent context layers track approaches like this to the same problem._ ### What is the difference between a fast engine and a slow engine in an AI context model? A slow engine processes weeks of user activity to build a durable profile of who a person is, their role, routines, and collaborators, reinforced over time. A fast engine processes only a short recent window, like the last day, to compute live signals such as overdue items, urgent commitments, and current collaborators. The two combine to give an assistant both long-term knowledge and up-to-date awareness. _engineers designing agent memory systems can follow patterns like this one on daily.dev._ ### What is the lambda architecture pattern and how does it relate to AI context modeling? Lambda architecture is a data processing pattern combining a fast speed layer over a recent real-time window with a slow batch layer over full history, merged into a single served view. It parallels complementary learning systems in neuroscience, where the hippocampus captures experiences instantly while the neocortex distills them into durable lessons over time; both ideas were applied to structure an AI assistant's dual-engine context model. _daily.dev surfaces architectural patterns like this for teams building resilient AI context pipelines._ ## Similar posts on daily.dev - [HubSpot’s Sidekick: Multi-Model AI Code Review with 90% Faster Feedback and 80% Engineer Approval](https://daily.dev/posts/hubspot-s-sidekick-multi-model-ai-code-review-with-90-faster-feedback-and-80-engineer-approval-zmnpc7psj) · InfoQ · 0 upvotes · 0 comments - [An architecture for engineering AI context](https://daily.dev/posts/an-architecture-for-engineering-ai-context-seinqdexr) · InfoWorld · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents) [View this post on daily.dev](https://daily.dev/posts/from-systems-of-record-to-systems-of-context-omri-bruchim-monday-com-j1hoononh) ```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":"From Systems of Record to Systems of Context — Omri Bruchim, monday.com","url":"https://daily.dev/posts/from-systems-of-record-to-systems-of-context-omri-bruchim-monday-com-j1hoononh","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/from-systems-of-record-to-systems-of-context-omri-bruchim-monday-com-j1hoononh"},"datePublished":"2026-07-22T23:21:33.711Z","dateModified":"2026-09-14T08:46:18.666Z","description":"Engineers from monday.com describe their architectural approach to building an AI personal assistant called Sidekick that goes beyond data retrieval to achieve...","image":"https://i.ytimg.com/vi/Btk8wDUVs74/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/Btk8wDUVs74/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","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":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/from-systems-of-record-to-systems-of-context-omri-bruchim-monday-com-j1hoononh","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents","timeRequired":"PT15M","video":{"@type":"VideoObject","name":"From Systems of Record to Systems of Context — Omri Bruchim, monday.com","description":"Engineers from monday.com describe their architectural approach to building an AI personal assistant called Sidekick that goes beyond data retrieval to achieve...","thumbnailUrl":"https://i.ytimg.com/vi/Btk8wDUVs74/sddefault.jpg","uploadDate":"2026-07-22T23:21:33.711Z","duration":"PT15M","url":"https://api.daily.dev/r/J1HOononH","embedUrl":"https://www.youtube.com/embed/Btk8wDUVs74"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"From Systems of Record to Systems of Context — Omri Bruchim, monday.com"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/from-systems-of-record-to-systems-of-context-omri-bruchim-monday-com-j1hoononh#faq","mainEntity":[{"@type":"Question","name":"Why do AI assistants like Claude or GPT fail to prioritize my tasks even when connected to all my work data?","acceptedAnswer":{"@type":"Answer","text":"They have access to the data but lack understanding of how the pieces connect to each other and to the user's actual priorities. Connecting Slack, email, and task boards gives an assistant all the records, but without pre-built understanding of relationships between entities, it can only guess at what matters, producing generic disconnected bullet-point answers rather than a real prioritized recommendation. daily.dev helps developers building AI agent context layers track approaches like this to the same problem."}},{"@type":"Question","name":"What is the difference between a fast engine and a slow engine in an AI context model?","acceptedAnswer":{"@type":"Answer","text":"A slow engine processes weeks of user activity to build a durable profile of who a person is, their role, routines, and collaborators, reinforced over time. A fast engine processes only a short recent window, like the last day, to compute live signals such as overdue items, urgent commitments, and current collaborators. The two combine to give an assistant both long-term knowledge and up-to-date awareness. engineers designing agent memory systems can follow patterns like this one on daily.dev."}},{"@type":"Question","name":"What is the lambda architecture pattern and how does it relate to AI context modeling?","acceptedAnswer":{"@type":"Answer","text":"Lambda architecture is a data processing pattern combining a fast speed layer over a recent real-time window with a slow batch layer over full history, merged into a single served view. It parallels complementary learning systems in neuroscience, where the hippocampus captures experiences instantly while the neocortex distills them into durable lessons over time; both ideas were applied to structure an AI assistant's dual-engine context model. daily.dev surfaces architectural patterns like this for teams building resilient AI context pipelines."}}]} ```