--- title: The cost of saying yes has changed | daily.dev description: The cost of writing code has dropped dramatically with AI tools, but the cost of owning code hasn't. This creates a new engineering discipline: using... canonical: https://daily.dev/posts/the-cost-of-saying-yes-has-changed-zqla2vfa5 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The cost of saying yes has changed | daily.dev og:description: The cost of writing code has dropped dramatically with AI tools, but the cost of owning code hasn't. This creates a new engineering discipline: using... og:url: https://daily.dev/posts/the-cost-of-saying-yes-has-changed-zqla2vfa5 og:image: https://api.daily.dev/og/posts/ZQla2Vfa5.png og:image:alt: The cost of saying yes has changed 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. # The cost of saying yes has changed **[GitHub Blog](https://daily.dev/sources/ghblog)** · 6 min read · 0 upvotes · 0 comments ## Summary The cost of writing code has dropped dramatically with AI tools, but the cost of owning code hasn't. This creates a new engineering discipline: using AI-generated patches as 'price checks' rather than deliverables. Instead of debating scope upfront, engineers can ask an agent for a constrained first attempt and use the resulting diff as evidence to make better decisions. The key distinction is that cheap-to-generate code is not the same as cheap-to-own code — changes touching auth, billing, privacy, or product contracts still carry full ownership costs regardless of how clean the diff looks. The new skill is pricing uncertainty fast: knowing when to try it versus when to say no. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How should engineering teams decide whether a small feature request is actually in scope when using AI coding agents? Instead of debating scope before writing any code, ask an agent to produce the smallest possible constrained patch behind an existing feature flag, without changing the public contract, and then judge scope based on the real diff. If it returns as a small, clean change with obvious tests, it was cheap; if it sprawls across unrelated files or touches sensitive areas like auth, it confirms the request was never actually small. _Engineers refining how they scope AI-assisted changes can find more perspectives like this through daily.dev._ ### Why isn't a code change considered cheap just because an AI agent generated it quickly? A change is only cheap if a human can confidently review and own the result afterward, not merely because the code was fast to produce. A large diff that technically passes tests but nobody wants to be responsible for is a deferred cost, not a cheap change; ownership cost for things like authorization logic or data-retention semantics stays high regardless of how quickly the code was written. _Anyone weighing ai-generated code against long-term ownership risk can track this debate on daily.dev._ ## Similar posts on daily.dev - [Code Is Cheap. Engineering Judgement Is Now the Scarce Resource](https://daily.dev/posts/code-is-cheap-engineering-judgement-is-now-the-scarce-resource-gdrecpyhk) · Towards Data Science · 0 upvotes · 0 comments - [Simon Willison’s Weblog](https://daily.dev/posts/simon-willison-s-weblog-ypcurxob3) · Hacker News · 1 upvotes · 1 comments - [The feature is cheap to code, so we might as well build it. \(Probably not\)](https://daily.dev/posts/the-feature-is-cheap-to-code-so-we-might-as-well-build-it-probably-not--fsotesh3m) · Medium · 0 upvotes · 0 comments --- Tags: [#github](https://daily.dev/tags/github), [#ai-coding](https://daily.dev/tags/ai-coding), [#code-review](https://daily.dev/tags/code-review) [View this post on daily.dev](https://daily.dev/posts/the-cost-of-saying-yes-has-changed-zqla2vfa5) ```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":"The cost of saying yes has changed","url":"https://daily.dev/posts/the-cost-of-saying-yes-has-changed-zqla2vfa5","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-cost-of-saying-yes-has-changed-zqla2vfa5"},"datePublished":"2026-07-17T16:48:00.995Z","dateModified":"2026-09-14T06:38:38.622Z","description":"The cost of writing code has dropped dramatically with AI tools, but the cost of owning code hasn't. This creates a new engineering discipline: using...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0ac53a7c345bed71ad274b67b10acb64?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0ac53a7c345bed71ad274b67b10acb64?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"GitHub Blog","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":"GitHub Blog","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/106cf162b88840808484d4b5429b59b1","url":"https://daily.dev/sources/ghblog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-cost-of-saying-yes-has-changed-zqla2vfa5","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"github,ai-coding,code-review","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"GitHub Blog","item":"https://daily.dev/sources/ghblog"},{"@type":"ListItem","position":3,"name":"The cost of saying yes has changed"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/the-cost-of-saying-yes-has-changed-zqla2vfa5#faq","mainEntity":[{"@type":"Question","name":"How should engineering teams decide whether a small feature request is actually in scope when using AI coding agents?","acceptedAnswer":{"@type":"Answer","text":"Instead of debating scope before writing any code, ask an agent to produce the smallest possible constrained patch behind an existing feature flag, without changing the public contract, and then judge scope based on the real diff. If it returns as a small, clean change with obvious tests, it was cheap; if it sprawls across unrelated files or touches sensitive areas like auth, it confirms the request was never actually small. Engineers refining how they scope AI-assisted changes can find more perspectives like this through daily.dev."}},{"@type":"Question","name":"Why isn't a code change considered cheap just because an AI agent generated it quickly?","acceptedAnswer":{"@type":"Answer","text":"A change is only cheap if a human can confidently review and own the result afterward, not merely because the code was fast to produce. A large diff that technically passes tests but nobody wants to be responsible for is a deferred cost, not a cheap change; ownership cost for things like authorization logic or data-retention semantics stays high regardless of how quickly the code was written. Anyone weighing ai-generated code against long-term ownership risk can track this debate on daily.dev."}}]} ```