--- title: Everyone's learning to prompt better. That's the wrong... description: An opinion piece argues that prompt engineering is the wrong skill to chase because a better prompt only makes AI output more convincing, not more correct —... canonical: https://daily.dev/posts/everyone-s-learning-to-prompt-better-that-s-the-wrong-skill--rrfpegqzt twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Everyone's learning to prompt better. That's the wrong skill. | daily.dev og:description: An opinion piece argues that prompt engineering is the wrong skill to chase because a better prompt only makes AI output more convincing, not more correct —... og:url: https://daily.dev/posts/everyone-s-learning-to-prompt-better-that-s-the-wrong-skill--rrfpegqzt og:image: https://api.daily.dev/og/posts/rrFPegQZT.png og:image:alt: Everyone's learning to prompt better. That's the wrong skill. 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. # Everyone's learning to prompt better. That's the wrong skill. **[DEV](https://daily.dev/sources/devto)** · 10 min read · 54 upvotes · 11 comments ## Summary An opinion piece argues that prompt engineering is the wrong skill to chase because a better prompt only makes AI output more convincing, not more correct — and correctness is decided at review time, not at the moment of asking. The author illustrates this with a personal story about an AI-generated write path that acknowledged a request before persisting it, causing a customer lockout when a retry hit. The real, durable skill is described as distrust: the discipline of trying to break AI output before accepting it, having someone other than the AI act as skeptic, and shipping to real users so mistakes carry consequences. The piece ties this into an 'author, skeptic, human' architecture for an agent platform the author builds, arguing verification and judgment — not prompting — are what compounds in value as models improve. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Why doesn't a better prompt make AI-generated code more correct? A better prompt improves how convincing and polished output looks, not whether it is actually correct — those are separate dials. Cleaner, more authoritative-looking code is harder to doubt, so genuinely wrong answers become harder to catch rather than easier, since correctness is only ever decided at review time by whether a human is willing to reject a confident-looking diff. _Anyone relying on AI-generated code can compare arguments on verification versus prompting through daily.dev._ ### What is the ack-before-persist bug and why is it hard to catch with AI-generated code? It is a bug where a system acknowledges a write request before the underlying row has actually been saved, so a retry hitting at the wrong moment can lock a user out with no record the action ever happened. One engineer shipped this from a clean, well-prompted AI-generated diff that passed tests and looked flawless, and only a trained reflex to distrust acknowledge-before-persist patterns would have caught it before a real customer was affected. _Developers debugging retry and idempotency issues can find related failure-shape discussions on daily.dev._ ### Why is using a second AI model call as a code reviewer considered a weak verification strategy? Two AI generators trained to produce plausible output tend to agree plausibly with each other, creating an illusion of independent review rather than an actual check. A more reliable pattern separates roles into a deterministic script that hard-gates named invariants (row counts, rollback correctness, valid-on-disk state), a model-based skeptic that only surfaces evidence without ever issuing a verdict, and a human who makes the final merge decision. _Teams designing AI code-review pipelines can track debate on skeptic architectures via daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@yaireo** · 8 upvotes > A better prompt does **_very much_** makes AI output more correct. that is a fact from me using AI every day, all day long, since AI came out some years ago. learning how to prompt is extremely important. > > I see people being lazy with their prompts and thus their deliver sub-optimal PRs which are then reviewed and as expected changes needs to be done. This time could have been saved with better/more prompts by PR authors. **@agustinbarrientos** · 3 upvotes > I wouldn't dismiss a prompt that specifies when a write can be acknowledged. I'd put that requirement in the task before generating code. **@bob72** · 3 upvotes > I heard prompting is dead, loops is the new thing. No? **@ristotoldsep** · 1 upvotes > yeah. ‘Looks right’ is not a test strategy, however good the prompt was. **@musikk** · 1 upvotes > > No prompt was going to save me there. > > How about "Make sure that the system commits before replying with an acknowledgement." Too specific? Maybe "The system must be able to handle errors during write safely." > > I don't really see what the message of the post is and who it's for. The described situation can happen if you blindly vibe your way through a product and don't care about the details. But then the post arguably is not really for you because at that point a convincing result is indistinguishable from a correct one anyways. On the other hand, if you engineer a solution, think about... ## Similar posts on daily.dev - [Beyond the Prompt: Why Your Prompt Engineering Skills Are Already Becoming Obsolete](https://daily.dev/posts/beyond-the-prompt-why-your-prompt-engineering-skills-are-already-becoming-obsolete-q9drv3drv) · Medium · 1 upvotes · 0 comments - [Prompt Engineering Is Not Enough](https://daily.dev/posts/prompt-engineering-is-not-enough-14xdxnnrk) · Telerik · 9 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#webdev](https://daily.dev/tags/webdev), [#career](https://daily.dev/tags/career), [#llm](https://daily.dev/tags/llm), [#testing](https://daily.dev/tags/testing), [#ai-coding](https://daily.dev/tags/ai-coding), [#prompt-engineering](https://daily.dev/tags/prompt-engineering), [#code-review](https://daily.dev/tags/code-review) [View this post on daily.dev](https://daily.dev/posts/everyone-s-learning-to-prompt-better-that-s-the-wrong-skill--rrfpegqzt) ```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":"Everyone's learning to prompt better. That's the wrong skill.","url":"https://daily.dev/posts/everyone-s-learning-to-prompt-better-that-s-the-wrong-skill--rrfpegqzt","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/everyone-s-learning-to-prompt-better-that-s-the-wrong-skill--rrfpegqzt"},"datePublished":"2026-09-28T07:19:06.907Z","dateModified":"2026-09-28T07:19:32.954Z","description":"An opinion piece argues that prompt engineering is the wrong skill to chase because a better prompt only makes AI output more convincing, not more correct —...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d4dbc5b20c6f2d9ca1238ce4a32378aa?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d4dbc5b20c6f2d9ca1238ce4a32378aa?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"DEV","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":"DEV","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/devto","url":"https://daily.dev/sources/devto"},"commentCount":11,"discussionUrl":"https://daily.dev/posts/everyone-s-learning-to-prompt-better-that-s-the-wrong-skill--rrfpegqzt","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":54},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":11}],"keywords":"ai,webdev,career,llm,testing,ai-coding,prompt-engineering,code-review","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"DEV","item":"https://daily.dev/sources/devto"},{"@type":"ListItem","position":3,"name":"Everyone's learning to prompt better. That's the wrong skill."}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/everyone-s-learning-to-prompt-better-that-s-the-wrong-skill--rrfpegqzt","comment":[{"@type":"Comment","text":"A better prompt does very much makes AI output more correct. that is a fact from me using AI every day, all day long, since AI came out some years ago. learning how to prompt is extremely important.\nI see people being lazy with their prompts and thus their deliver sub-optimal PRs which are then reviewed and as expected changes needs to be done. This time could have been saved with better/more prompts by PR authors.","datePublished":"2026-09-28T15:26:52.960Z","dateModified":"2026-09-29T06:39:22.230Z","url":"https://daily.dev/posts/rrFPegQZT#c-5q4pRJrhS","author":{"@type":"Person","name":"Yair Even Or","url":"https://daily.dev/yaireo","image":"https://avatars.githubusercontent.com/u/845031?v=4"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":8}},{"@type":"Comment","text":"I wouldn’t dismiss a prompt that specifies when a write can be acknowledged. I’d put that requirement in the task before generating code.","datePublished":"2026-09-28T22:32:07.014Z","url":"https://daily.dev/posts/rrFPegQZT#c-AdPyxeCee","author":{"@type":"Person","name":"Agustin Barrientos","url":"https://daily.dev/agustinbarrientos","image":"https://media.daily.dev/image/upload/s--5ayxQnqn--/f_auto/v1788281802/avatars/avatar_wQYYVe5Tbj0NJ7C7qPoa8?_a=BAMAMicg0"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3}},{"@type":"Comment","text":"I heard prompting is dead, loops is the new thing. No?","datePublished":"2026-09-28T19:09:06.735Z","url":"https://daily.dev/posts/rrFPegQZT#c-vASRiAJQ6","author":{"@type":"Person","name":"Bob","url":"https://daily.dev/bob72","image":"https://avatars.githubusercontent.com/u/193962566?v=4"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3}},{"@type":"Comment","text":"yeah. ‘Looks right’ is not a test strategy, however good the prompt was.","datePublished":"2026-09-30T11:04:48.321Z","url":"https://daily.dev/posts/rrFPegQZT#c-a4sIEvkZm","author":{"@type":"Person","name":"Risto Tõldsep","url":"https://daily.dev/ristotoldsep","image":"https://lh3.googleusercontent.com/a/ACg8ocLDWc6mZn0JwNmXXw6WY0L_HJ6pegzRttooC5VgtXESHSj3MNYx=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1}},{"@type":"Comment","text":"No prompt was going to save me there.\n\nHow about “Make sure that the system commits before replying with an acknowledgement.” Too specific? Maybe “The system must be able to handle errors during write safely.”\nI don’t really see what the message of the post is and who it’s for. The described situation can happen if you blindly vibe your way through a product and don’t care about the details. But then the post arguably is not really for you because at that point a convincing result is indistinguishable from a correct one anyways. On the other hand, if you engineer a solution, think about the architecture and correctness, the statement that a better prompt does nothing about correctness is just plain wrong.","datePublished":"2026-09-29T07:41:43.678Z","url":"https://daily.dev/posts/rrFPegQZT#c-nszNYWboU","author":{"@type":"Person","name":"Werner Hahn","url":"https://daily.dev/musikk","image":"https://lh3.googleusercontent.com/a/ACg8ocJr9LIXrt1E5zAmLx3QtOkq4iGvcwdh-t__bh6z4dhVoZyOEgE=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/everyone-s-learning-to-prompt-better-that-s-the-wrong-skill--rrfpegqzt#faq","mainEntity":[{"@type":"Question","name":"Why doesn't a better prompt make AI-generated code more correct?","acceptedAnswer":{"@type":"Answer","text":"A better prompt improves how convincing and polished output looks, not whether it is actually correct — those are separate dials. Cleaner, more authoritative-looking code is harder to doubt, so genuinely wrong answers become harder to catch rather than easier, since correctness is only ever decided at review time by whether a human is willing to reject a confident-looking diff. Anyone relying on AI-generated code can compare arguments on verification versus prompting through daily.dev."}},{"@type":"Question","name":"What is the ack-before-persist bug and why is it hard to catch with AI-generated code?","acceptedAnswer":{"@type":"Answer","text":"It is a bug where a system acknowledges a write request before the underlying row has actually been saved, so a retry hitting at the wrong moment can lock a user out with no record the action ever happened. One engineer shipped this from a clean, well-prompted AI-generated diff that passed tests and looked flawless, and only a trained reflex to distrust acknowledge-before-persist patterns would have caught it before a real customer was affected. Developers debugging retry and idempotency issues can find related failure-shape discussions on daily.dev."}},{"@type":"Question","name":"Why is using a second AI model call as a code reviewer considered a weak verification strategy?","acceptedAnswer":{"@type":"Answer","text":"Two AI generators trained to produce plausible output tend to agree plausibly with each other, creating an illusion of independent review rather than an actual check. A more reliable pattern separates roles into a deterministic script that hard-gates named invariants (row counts, rollback correctness, valid-on-disk state), a model-based skeptic that only surfaces evidence without ever issuing a verdict, and a human who makes the final merge decision. Teams designing AI code-review pipelines can track debate on skeptic architectures via daily.dev."}}]} ```