--- title: Haskell for all: Prompting 101: Show, don’t tell | daily.dev description: Effective prompting requires showing LLMs desired behavior through examples rather than telling them to act like experts. Instructions like "You are a Staff+... canonical: https://daily.dev/posts/haskell-for-all-prompting-101-show-don-t-tell-bxwlx58m6 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Haskell for all: Prompting 101: Show, don’t tell | daily.dev og:description: Effective prompting requires showing LLMs desired behavior through examples rather than telling them to act like experts. Instructions like "You are a Staff+... og:url: https://daily.dev/posts/haskell-for-all-prompting-101-show-don-t-tell-bxwlx58m6 og:image: https://api.daily.dev/og/posts/BxwlX58M6.png og:image:alt: Haskell for all: Prompting 101: Show, don’t tell 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. # Haskell for all: Prompting 101: Show, don’t tell **[Planet Haskell](https://daily.dev/sources/phaskell)** · 7 min read · 2 upvotes · 0 comments ## Summary Effective prompting requires showing LLMs desired behavior through examples rather than telling them to act like experts. Instructions like "You are a Staff+ Software Architect" are counterproductive because LLMs pattern-match training data, and such phrases appear in screenplays and job descriptions, not actual expertise. Instead, seed conversations with example exchanges demonstrating the desired style. A practical demonstration shows how seeding a chat history with conversational examples produces more natural, participatory responses compared to instructional system prompts. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Achieving 5x Agentic Coding Performance with Few-Shot Prompting](https://daily.dev/posts/achieving-5x-agentic-coding-performance-with-few-shot-prompting-6xxjyufkp) · Towards Data Science · 1 upvotes · 0 comments - [Prompt engineering for developers](https://daily.dev/posts/prompt-engineering-for-developers-5wubmqagr) · The New Stack · 1 upvotes · 1 comments - [Applying Prompt Theory to LLM Apps: Practical Steps for AI Engineers](https://daily.dev/posts/applying-prompt-theory-to-llm-apps-practical-steps-for-ai-engineers-d7owdbhbe) · PromptLayer Blog · 0 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#llm](https://daily.dev/tags/llm), [#chatgpt](https://daily.dev/tags/chatgpt), [#prompt-engineering](https://daily.dev/tags/prompt-engineering), [#haskell](https://daily.dev/tags/haskell) [View this post on daily.dev](https://daily.dev/posts/haskell-for-all-prompting-101-show-don-t-tell-bxwlx58m6) ```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":"Haskell for all: Prompting 101: Show, don’t tell","url":"https://daily.dev/posts/haskell-for-all-prompting-101-show-don-t-tell-bxwlx58m6","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/haskell-for-all-prompting-101-show-don-t-tell-bxwlx58m6"},"datePublished":"2026-01-09T21:08:05.246Z","dateModified":"2026-01-09T21:08:24.990Z","description":"Effective prompting requires showing LLMs desired behavior through examples rather than telling them to act like experts. Instructions like \"You are a Staff+...","image":"https://media.daily.dev/image/upload/s--ZrL_HSsR--/f_auto/v1722860399/public/Placeholder%2006","thumbnailUrl":"https://media.daily.dev/image/upload/s--ZrL_HSsR--/f_auto/v1722860399/public/Placeholder%2006","isAccessibleForFree":true,"articleSection":"Planet Haskell","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":"Planet Haskell","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/cd3e48fb3b974d10993a5b5b8dcb8a08","url":"https://daily.dev/sources/phaskell"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/haskell-for-all-prompting-101-show-don-t-tell-bxwlx58m6","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,llm,chatgpt,prompt-engineering,haskell","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Planet Haskell","item":"https://daily.dev/sources/phaskell"},{"@type":"ListItem","position":3,"name":"Haskell for all: Prompting 101: Show, don’t tell"}]} ```