--- title: HubSpot’s Sidekick: Multi-Model AI Code Review with 90%... description: HubSpot's engineering team built Sidekick, an internal AI-powered code review agent that analyzes pull requests using LLMs and filters feedback through a... canonical: https://daily.dev/posts/hubspot-s-sidekick-multi-model-ai-code-review-with-90-faster-feedback-and-80-engineer-approval-zmnpc7psj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: HubSpot’s Sidekick: Multi-Model AI Code Review with 90% Faster Feedback and 80% Engineer Approval | daily.dev og:description: HubSpot's engineering team built Sidekick, an internal AI-powered code review agent that analyzes pull requests using LLMs and filters feedback through a... og:url: https://daily.dev/posts/hubspot-s-sidekick-multi-model-ai-code-review-with-90-faster-feedback-and-80-engineer-approval-zmnpc7psj og:image: https://api.daily.dev/og/posts/zMNPC7psJ.png og:image:alt: HubSpot’s Sidekick: Multi-Model AI Code Review with 90% Faster Feedback and 80% Engineer Approval 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. # HubSpot’s Sidekick: Multi-Model AI Code Review with 90% Faster Feedback and 80% Engineer Approval **[InfoQ](https://daily.dev/sources/infoq)** · 3 min read · 0 upvotes · 0 comments ## Summary HubSpot's engineering team built Sidekick, an internal AI-powered code review agent that analyzes pull requests using LLMs and filters feedback through a secondary 'judge agent' before posting comments to GitHub. The system migrated from a Kubernetes-based setup to a Java framework called Aviator, which integrates with HubSpot's dev platform and supports multiple model providers (Anthropic, OpenAI, Google). The judge agent pattern significantly reduced low-value comments, resulting in a 90% reduction in time-to-first-feedback and an 80% thumbs-up rate from engineers. Future plans include persistent memory for agents and expanded cross-repository context retrieval. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [AI Code Review at Scale: LinkedIn's Multi-Agent Approach](https://daily.dev/posts/ai-code-review-at-scale-linkedin-s-multi-agent-approach-7lpkuhkzi) · InfoQ · 0 upvotes · 0 comments - [How DoorDash built an AI code reviewer engineers actually listen to](https://daily.dev/posts/how-doordash-built-an-ai-code-reviewer-engineers-actually-listen-to-psc8auyls) · Doordash · 0 upvotes · 0 comments --- Tags: [#github](https://daily.dev/tags/github), [#java](https://daily.dev/tags/java), [#hubspot](https://daily.dev/tags/hubspot) [View this post on daily.dev](https://daily.dev/posts/hubspot-s-sidekick-multi-model-ai-code-review-with-90-faster-feedback-and-80-engineer-approval-zmnpc7psj) ```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":"HubSpot’s Sidekick: Multi-Model AI Code Review with 90% Faster Feedback and 80% Engineer Approval","url":"https://daily.dev/posts/hubspot-s-sidekick-multi-model-ai-code-review-with-90-faster-feedback-and-80-engineer-approval-zmnpc7psj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/hubspot-s-sidekick-multi-model-ai-code-review-with-90-faster-feedback-and-80-engineer-approval-zmnpc7psj"},"datePublished":"2026-03-18T14:42:29.088Z","dateModified":"2026-03-18T14:42:49.477Z","description":"HubSpot's engineering team built Sidekick, an internal AI-powered code review agent that analyzes pull requests using LLMs and filters feedback through a...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1ff8c157e70a5ded58bb329b3fa0f488?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1ff8c157e70a5ded58bb329b3fa0f488?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"InfoQ","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":"InfoQ","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/afc3bced3e1e4b188dd9127017a60e0c","url":"https://daily.dev/sources/infoq"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/hubspot-s-sidekick-multi-model-ai-code-review-with-90-faster-feedback-and-80-engineer-approval-zmnpc7psj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"github,java,hubspot","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"InfoQ","item":"https://daily.dev/sources/infoq"},{"@type":"ListItem","position":3,"name":"HubSpot’s Sidekick: Multi-Model AI Code Review with 90% Faster Feedback and 80% Engineer Approval"}]} ```