--- title: LLM Observability, Evaluation, Experimentation Platform... description: A talk by an AI architect at Arize AI covering three pillars of making LLM-based systems work in production: observability, evaluation, and experimentation.... canonical: https://daily.dev/posts/llm-observability-evaluation-experimentation-platform-dat-ngo-arize-7lhucsvga twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: LLM Observability, Evaluation, Experimentation Platform — Dat Ngo, Arize | daily.dev og:description: A talk by an AI architect at Arize AI covering three pillars of making LLM-based systems work in production: observability, evaluation, and experimentation.... og:url: https://daily.dev/posts/llm-observability-evaluation-experimentation-platform-dat-ngo-arize-7lhucsvga og:image: https://api.daily.dev/og/posts/7LhuCsvga.png og:image:alt: LLM Observability, Evaluation, Experimentation Platform — Dat Ngo, Arize 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. # LLM Observability, Evaluation, Experimentation Platform — Dat Ngo, Arize **[AI Engineer](https://daily.dev/sources/aidotengineer)** · 16 min read · 1 upvotes · 0 comments ## Summary A talk by an AI architect at Arize AI covering three pillars of making LLM-based systems work in production: observability, evaluation, and experimentation. Observability is built on OpenTelemetry traces and spans, with views into sessions, runs, and distributional agent behavior. Evaluation is broken into five signal types (LLM-as-judge, human feedback, golden datasets, deterministic checks, business metrics) and can be scoped at span, multi-span, trajectory, or session level. Experimentation involves collecting datasets from traces and running prompt/model/config changes. Arize offers two products: open-source Arize Phoenix (single container, no Kubernetes) and enterprise Arize AX. The company's stated goal is to automate the entire observability-eval-experimentation flywheel via an AI assistant called Alex. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [LLM Observability Tools for Reliable AI Applications](https://daily.dev/posts/llm-observability-tools-for-reliable-ai-applications-oy255bw6k) · Machine Learning Mastery · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#llm](https://daily.dev/tags/llm), [#llm-observability](https://daily.dev/tags/llm-observability), [#opentelemetry](https://daily.dev/tags/opentelemetry) [View this post on daily.dev](https://daily.dev/posts/llm-observability-evaluation-experimentation-platform-dat-ngo-arize-7lhucsvga) ```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":"LLM Observability, Evaluation, Experimentation Platform — Dat Ngo, Arize","url":"https://daily.dev/posts/llm-observability-evaluation-experimentation-platform-dat-ngo-arize-7lhucsvga","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/llm-observability-evaluation-experimentation-platform-dat-ngo-arize-7lhucsvga"},"datePublished":"2026-06-07T18:05:06.690Z","dateModified":"2026-07-16T02:13:08.737Z","description":"A talk by an AI architect at Arize AI covering three pillars of making LLM-based systems work in production: observability, evaluation, and experimentation....","image":"https://i.ytimg.com/vi/JsCCrBF7F1g/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/JsCCrBF7F1g/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/llm-observability-evaluation-experimentation-platform-dat-ngo-arize-7lhucsvga","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,llm,llm-observability,opentelemetry","timeRequired":"PT16M","video":{"@type":"VideoObject","name":"LLM Observability, Evaluation, Experimentation Platform — Dat Ngo, Arize","description":"A talk by an AI architect at Arize AI covering three pillars of making LLM-based systems work in production: observability, evaluation, and experimentation....","thumbnailUrl":"https://i.ytimg.com/vi/JsCCrBF7F1g/sddefault.jpg","uploadDate":"2026-06-07T18:05:06.690Z","duration":"PT16M","url":"https://api.daily.dev/r/7LhuCsvga","embedUrl":"https://www.youtube.com/embed/JsCCrBF7F1g"}} {"@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":"LLM Observability, Evaluation, Experimentation Platform — Dat Ngo, Arize"}]} ```