--- title: What teaching can tell us about prompting | daily.dev description: Good prompting for coding agents can learn from teaching: clear examples and feedback that points to a mismatch. A vague instruction like 'reject dates in the... canonical: https://daily.dev/posts/what-teaching-can-tell-us-about-prompting-c4howetqs twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: What teaching can tell us about prompting | daily.dev og:description: Good prompting for coding agents can learn from teaching: clear examples and feedback that points to a mismatch. A vague instruction like 'reject dates in the... og:url: https://daily.dev/posts/what-teaching-can-tell-us-about-prompting-c4howetqs og:image: https://api.daily.dev/og/posts/c4hOWeTQs.png og:image:alt: What teaching can tell us about prompting 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. # What teaching can tell us about prompting **[Flavio Copes](https://daily.dev/sources/flaviocopes)** · 4 min read · 1 upvotes · 0 comments ## Summary Good prompting for coding agents can learn from teaching: clear examples and feedback that points to a mismatch. A vague instruction like 'reject dates in the past' hides ambiguity about today's date and time zones. A concrete example, like a shop at 14:00 where a 13:00 booking is invalid but 15:00 is valid, gives the agent something specific to implement. When an implementation fails, saying 'that's wrong, try again' gives very little new information; pointing to the exact failed case and why the code is wrong does more. A passing example doesn't prove the whole feature works, so other cases still need checking. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Why does my AI coding agent reject valid bookings made earlier today? A vague instruction like 'reject dates in the past' leaves out time zone and same-day boundary logic, so the agent may compare only calendar dates. For example, in a shop's local time zone, at 14:00 a booking for 13:00 today should be invalid but one for 15:00 should be valid. Giving the agent this concrete example fixes the ambiguity. _daily.dev surfaces practical prompting techniques for developers refining how they direct coding agents._ ### What should I say to a coding agent when its generated code is wrong, instead of just telling it to try again? Point to the specific failed example and explain why the result differs from what was expected, rather than saying 'that's wrong, try again.' For instance, state that a 15:00 booking should remain valid at 14:00 shop time, and explain the current code rejects it because it only compares calendar dates. This gives the agent concrete information to correct the mismatch. _Developers debugging agent output can find more prompting feedback strategies on daily.dev._ ## Similar posts on daily.dev - [A Guide to Effective Prompt Engineering](https://daily.dev/posts/a-guide-to-effective-prompt-engineering-akjscs4qs) · ByteByteGo · 4 upvotes · 0 comments - [Prompt Engineering for AI Agents: From Demo to Production](https://daily.dev/posts/prompt-engineering-for-ai-agents-from-demo-to-production-vfcpohk9t) · Medium · 1 upvotes · 0 comments - [AI Agents: Experience Doesn’t Fit in a Prompt](https://daily.dev/posts/ai-agents-experience-doesn-t-fit-in-a-prompt-vunycsiyo) · Atomic Spin · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#prompt-engineering](https://daily.dev/tags/prompt-engineering) [View this post on daily.dev](https://daily.dev/posts/what-teaching-can-tell-us-about-prompting-c4howetqs) ```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":"What teaching can tell us about prompting","url":"https://daily.dev/posts/what-teaching-can-tell-us-about-prompting-c4howetqs","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/what-teaching-can-tell-us-about-prompting-c4howetqs"},"datePublished":"2026-10-25T11:21:44.036Z","dateModified":"2026-10-25T11:22:19.670Z","description":"Good prompting for coding agents can learn from teaching: clear examples and feedback that points to a mismatch. A vague instruction like 'reject dates in the...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c00a633ecad8d2bdc547983ed63f4893?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c00a633ecad8d2bdc547983ed63f4893?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Flavio Copes","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":"Flavio Copes","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/1f2dbd275797411bbd37bfdaaf0951a9","url":"https://daily.dev/sources/flaviocopes"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/what-teaching-can-tell-us-about-prompting-c4howetqs","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,prompt-engineering","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Flavio Copes","item":"https://daily.dev/sources/flaviocopes"},{"@type":"ListItem","position":3,"name":"What teaching can tell us about prompting"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/what-teaching-can-tell-us-about-prompting-c4howetqs#faq","mainEntity":[{"@type":"Question","name":"Why does my AI coding agent reject valid bookings made earlier today?","acceptedAnswer":{"@type":"Answer","text":"A vague instruction like 'reject dates in the past' leaves out time zone and same-day boundary logic, so the agent may compare only calendar dates. For example, in a shop's local time zone, at 14:00 a booking for 13:00 today should be invalid but one for 15:00 should be valid. Giving the agent this concrete example fixes the ambiguity. daily.dev surfaces practical prompting techniques for developers refining how they direct coding agents."}},{"@type":"Question","name":"What should I say to a coding agent when its generated code is wrong, instead of just telling it to try again?","acceptedAnswer":{"@type":"Answer","text":"Point to the specific failed example and explain why the result differs from what was expected, rather than saying 'that's wrong, try again.' For instance, state that a 15:00 booking should remain valid at 14:00 shop time, and explain the current code rejects it because it only compares calendar dates. This gives the agent concrete information to correct the mismatch. Developers debugging agent output can find more prompting feedback strategies on daily.dev."}}]} ```