--- title: Using AI to generate Kubernetes configuration | daily.dev description: An exploration of using AI (specifically Claude Code) to generate Kubernetes configuration, comparing different approaches: naive prompting, agent skills with... canonical: https://daily.dev/posts/using-ai-to-generate-kubernetes-configuration-eb1sciy6b twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Using AI to generate Kubernetes configuration | daily.dev og:description: An exploration of using AI (specifically Claude Code) to generate Kubernetes configuration, comparing different approaches: naive prompting, agent skills with... og:url: https://daily.dev/posts/using-ai-to-generate-kubernetes-configuration-eb1sciy6b og:image: https://api.daily.dev/og/posts/eb1ScIY6b.png og:image:alt: Using AI to generate Kubernetes configuration 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. # Using AI to generate Kubernetes configuration **[Medium](https://daily.dev/sources/medium_js)** · 10 min read · 5 upvotes · 0 comments ## Summary An exploration of using AI (specifically Claude Code) to generate Kubernetes configuration, comparing different approaches: naive prompting, agent skills with example resources, interactive 20-questions-style generation, and providing application interface specifications upfront. The most effective approach was supplying detailed application specs (commands, env vars, ports, probe endpoints, filesystem paths) along with agent skills, which produced a comprehensive, security-hardened Kubernetes configuration including NetworkPolicy, security contexts, probes, and resource limits with minimal back-and-forth. The author concludes that combining application source context, architectural documents, infrastructure context, and agent skills yields the best results, while noting the field is still early in developing best practices. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Is using Claude Code to generate Kubernetes Deployment and Service YAML better than just running kubectl create? Not by default. Asking Claude Code directly to generate a Kubernetes Service and Deployment produced a minimalistic pair of resources filled with dummy values that still needed manual editing, offering no real advantage over kubectl create until additional context, specs, or agent skills were supplied. _Developers weighing AI-assisted config generation against kubectl workflows can compare real experiences like this on daily.dev._ ### What information helps an AI agent generate more complete and secure Kubernetes configuration? Providing application interface specifications (commands, flags, environment variables, ports, probe endpoints, filesystem paths) plus architectural documents and agent skills lets an agent like Claude correctly infer pod-security labels, ConfigMaps, Secrets, liveness/readiness probes, security contexts, and NetworkPolicies without repeated back-and-forth, compared to bare prompting which yields only minimal placeholder resources. _Anyone refining prompts and context for AI-generated infra config can track approaches like this on daily.dev._ ## Similar posts on daily.dev - [AI-driven Kubernetes in Action: Exploring AI-Assisted Kubernetes Operations](https://daily.dev/posts/ai-driven-kubernetes-in-action-exploring-ai-assisted-kubernetes-operations-uo6kz7s2k) · Cloud Native Now · 1 upvotes · 0 comments - [Claude Code: creating Kubernetes debugging AI Agent for VictoriaMetrics](https://daily.dev/posts/claude-code-creating-kubernetes-debugging-ai-agent-for-victoriametrics-junzs8wjz) · ITNEXT · 1 upvotes · 0 comments - [Four Layers of Validation in Kubernetes with Claude Code](https://daily.dev/posts/four-layers-of-validation-in-kubernetes-with-claude-code-kckstnypq) · MetalBear · 0 upvotes · 0 comments --- Tags: [#kubernetes](https://daily.dev/tags/kubernetes), [#ai-coding](https://daily.dev/tags/ai-coding), [#claude-code](https://daily.dev/tags/claude-code), [#iac](https://daily.dev/tags/iac) [View this post on daily.dev](https://daily.dev/posts/using-ai-to-generate-kubernetes-configuration-eb1sciy6b) ```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":"Using AI to generate Kubernetes configuration","url":"https://daily.dev/posts/using-ai-to-generate-kubernetes-configuration-eb1sciy6b","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/using-ai-to-generate-kubernetes-configuration-eb1sciy6b"},"datePublished":"2026-07-30T19:34:57.073Z","dateModified":"2026-09-13T21:55:59.262Z","description":"An exploration of using AI (specifically Claude Code) to generate Kubernetes configuration, comparing different approaches: naive prompting, agent skills with...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/dbb4ffb48d313a152f7613887c493c95?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/dbb4ffb48d313a152f7613887c493c95?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","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":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/using-ai-to-generate-kubernetes-configuration-eb1sciy6b","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":5},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"kubernetes,ai-coding,claude-code,iac","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"Using AI to generate Kubernetes configuration"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/using-ai-to-generate-kubernetes-configuration-eb1sciy6b#faq","mainEntity":[{"@type":"Question","name":"Is using Claude Code to generate Kubernetes Deployment and Service YAML better than just running kubectl create?","acceptedAnswer":{"@type":"Answer","text":"Not by default. Asking Claude Code directly to generate a Kubernetes Service and Deployment produced a minimalistic pair of resources filled with dummy values that still needed manual editing, offering no real advantage over kubectl create until additional context, specs, or agent skills were supplied. Developers weighing AI-assisted config generation against kubectl workflows can compare real experiences like this on daily.dev."}},{"@type":"Question","name":"What information helps an AI agent generate more complete and secure Kubernetes configuration?","acceptedAnswer":{"@type":"Answer","text":"Providing application interface specifications (commands, flags, environment variables, ports, probe endpoints, filesystem paths) plus architectural documents and agent skills lets an agent like Claude correctly infer pod-security labels, ConfigMaps, Secrets, liveness/readiness probes, security contexts, and NetworkPolicies without repeated back-and-forth, compared to bare prompting which yields only minimal placeholder resources. Anyone refining prompts and context for AI-generated infra config can track approaches like this on daily.dev."}}]} ```