--- title: Why AI code optimization needs production-grounded... description: Datadog engineers built DODO (Datadog Observability-Driven Optimizer), a system that grounds AI-driven code optimization in live production telemetry rather... canonical: https://daily.dev/posts/why-ai-code-optimization-needs-production-grounded-benchmarks-sedbelbxu twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Why AI code optimization needs production-grounded benchmarks | daily.dev og:description: Datadog engineers built DODO (Datadog Observability-Driven Optimizer), a system that grounds AI-driven code optimization in live production telemetry rather... og:url: https://daily.dev/posts/why-ai-code-optimization-needs-production-grounded-benchmarks-sedbelbxu og:image: https://api.daily.dev/og/posts/SEDBeLBxu.png og:image:alt: Why AI code optimization needs production-grounded benchmarks 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. # Why AI code optimization needs production-grounded benchmarks **[Datadog](https://daily.dev/sources/datadog)** · 10 min read · 1 upvotes · 0 comments ## Summary Datadog engineers built DODO (Datadog Observability-Driven Optimizer), a system that grounds AI-driven code optimization in live production telemetry rather than synthetic benchmarks. It uses two signals — CPU profiles from Continuous Profiler and real function invocations from Live Debugger — to generate Go micro-benchmarks that match production execution shape with ≥98% similarity. A benchmark agent iteratively tunes the benchmark until it mirrors production, then a separate optimization agent proposes code changes scored against that benchmark. Applied to a mature, heavily-optimized Go service, DODO found optimizations cutting over 8% of total CPU cost (roughly 10,000 cores saved continuously). Key examples include replacing linear filter-rule scans with O(1) lookups and replacing tag sorting with bitset iteration. The approach highlights how production data patterns (e.g., 25% of tags containing uppercase characters) surface optimization opportunities that synthetic benchmarks would miss entirely. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How Datadog uses AI to build internal software delivery tools and improve system performance](https://daily.dev/posts/how-datadog-uses-ai-to-build-internal-software-delivery-tools-and-improve-system-performance-1mupjofm5) · Datadog · 3 upvotes · 0 comments - [Turn Datadog findings into automated code fixes with Bits Code](https://daily.dev/posts/turn-datadog-findings-into-automated-code-fixes-with-bits-code-xhqssnjkw) · Datadog · 0 upvotes · 0 comments - [Debug and evaluate your AI app from your coding agent with Datadog Agent Observability](https://daily.dev/posts/debug-and-evaluate-your-ai-app-from-your-coding-agent-with-datadog-agent-observability-uwbwi17jy) · Datadog · 0 upvotes · 0 comments - [Automatically optimize database queries with Datadog Database Monitoring](https://daily.dev/posts/automatically-optimize-database-queries-with-datadog-database-monitoring-zigejizsa) · Datadog · 0 upvotes · 0 comments --- Tags: [#devops](https://daily.dev/tags/devops), [#golang](https://daily.dev/tags/golang), [#observability](https://daily.dev/tags/observability) [View this post on daily.dev](https://daily.dev/posts/why-ai-code-optimization-needs-production-grounded-benchmarks-sedbelbxu) ```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":"Why AI code optimization needs production-grounded benchmarks","url":"https://daily.dev/posts/why-ai-code-optimization-needs-production-grounded-benchmarks-sedbelbxu","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/why-ai-code-optimization-needs-production-grounded-benchmarks-sedbelbxu"},"datePublished":"2026-06-09T11:57:54.875Z","dateModified":"2026-06-09T14:19:43.197Z","description":"Datadog engineers built DODO (Datadog Observability-Driven Optimizer), a system that grounds AI-driven code optimization in live production telemetry rather...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7bde858700334da858f4177228347829?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7bde858700334da858f4177228347829?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Datadog","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":"Datadog","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/8f9d7e3e4bd64bd7b9db9b2ea83e0c6a","url":"https://daily.dev/sources/datadog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/why-ai-code-optimization-needs-production-grounded-benchmarks-sedbelbxu","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"devops,golang,observability","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Datadog","item":"https://daily.dev/sources/datadog"},{"@type":"ListItem","position":3,"name":"Why AI code optimization needs production-grounded benchmarks"}]} ```