{"id":21958,"date":"2025-09-01T08:46:27","date_gmt":"2025-09-01T07:46:27","guid":{"rendered":"https:\/\/www.equalexperts.com\/?p=21958"},"modified":"2025-09-02T01:46:26","modified_gmt":"2025-09-02T00:46:26","slug":"re-inventing-linguistics-llm-prompting","status":"publish","type":"post","link":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/","title":{"rendered":"Coding with LLMs: are we re-inventing linguistics with prompts?"},"content":{"rendered":"

Why prompting advice feels like superstition \u2014 and how linguistics can give us a framework.<\/em><\/p>\n

If you\u2019ve been working with LLMs, you\u2019ve probably seen (or written) endless threads about \u201cgood\u201d and \u201cbad\u201d prompts. Some advice works, some doesn\u2019t, and most of it feels like trial and error.<\/p>\n

I kept wondering \u2014 is there a unifying theory behind this? Something that explains why certain prompts work better than others? At first, I tried inventing my own framework \u2014 mixing ideas of \u201cformalism\u201d and \u201cmaneuverability.\u201d But a colleague pointed out that I was just creating another system of superstition.<\/p>\n

And they were right. Because if we stop thinking of these systems as just Large Language Models and instead see them as large models of language, then the missing framework already exists: linguistics.<\/p>\n

We don\u2019t need to reinvent the wheel \u2014 decades of linguistic research already explain what makes some prompts effective and others brittle. Below are concrete examples (kept exactly as I\u2019ve used them myself) that show how theories from linguistics map onto prompt engineering.<\/p>\n

<\/h2>\n

Working Memory Theory<\/h2>\n

Working memory acts as our mental workspace, but it has limited capacity \u2014 around 7 items at a time. Overload it, and comprehension collapses. LLMs behave the same way.<\/p>\n

Before (cognitive overload):<\/strong><\/p>\n

Create a complete web application with user authentication, database integration, real-time chat, file upload functionality, admin dashboard, and responsive design using React, Node.js, Express, MongoDB, and Socket.io with proper error handling, security measures, and performance optimisation.<\/em><\/p>\n

After (chunked for cognition):<\/strong><\/p>\n

Let’s build a web application step by step:<\/em>
\n1. First, create a basic React frontend with user registration\/login forms<\/em>
\n2. Then, set up a Node.js\/Express backend with MongoDB for user management<\/em>
\n3. Next, implement secure authentication with JWT tokens<\/em>
\n4. Finally, add real-time chat using Socket.io<\/em>
\nFocus on step 1 first – create the user registration component.<\/em><\/p>\n

We intuitively know the second prompt is better. Linguistics explains why.<\/p>\n

<\/h2>\n

Linguistic Anchoring<\/h2>\n

The \u201canchoring effect\u201d describes how the first piece of information we receive heavily influences our focus. We can apply this directly in prompting.<\/p>\n

Before (attention drift):<\/strong><\/p>\n

Write a function to sort a list.<\/em><\/p>\n

After (linguistically anchored):<\/strong><\/p>\n

TASK: Sort a list of integers efficiently<\/em>
\nFOCUS: Choose optimal algorithm for large datasets<\/em>
\nCONSTRAINTS: Handle edge cases (empty lists, duplicates)<\/em>
\nDELIVERABLE: Python function with time complexity analysis<\/em><\/p>\n

def sort_large_list(nums: List[int]) -> List[int]:<\/em>
\n“””Efficiently sort a large list of integers.”””<\/em>
\n# Your implementation focusing on the TASK above<\/em><\/p>\n

By explicitly anchoring tokens like TASK, FOCUS, and CONSTRAINTS, we guide the LLM\u2019s attention in a predictable way.<\/p>\n

<\/h2>\n

Information Density<\/h2>\n

Too much noise = weak prompts. Information theory helps explain why clarity beats vagueness.<\/p>\n

Before (low density, high noise):<\/strong><\/p>\n

Please help me write some code that can handle files and do some processing on them. I need it to work with different types of files and be able to process them efficiently. Can you make something that’s robust and handles errors well?<\/em><\/p>\n

After (optimised information density):<\/strong><\/p>\n

Create a Python file processor class that:<\/em>
\n– Accepts .txt, .csv, .json file types<\/em>
\n– Reads content with encoding detection<\/em>
\n– Applies transformation function (passed as parameter)<\/em>
\n– Writes to output directory with ‘_processed’ suffix<\/em>
\n– Handles FileNotFoundError, PermissionError, UnicodeDecodeError<\/em>
\n– Logs progress for files > 1MB<\/em><\/p>\n

Precision beats verbosity \u2014 but when you can\u2019t be precise, redundancy and multiple explanations can still help (as pragmatics and discourse theory suggest).<\/p>\n

<\/h2>\n

Embodied Cognition<\/h2>\n

Humans understand abstract concepts through physical metaphors. LLMs \u2014 trained on our language \u2014 respond well to this too.<\/p>\n

Before (abstract):<\/strong><\/p>\n

Implement caching functionality<\/em><\/p>\n

After (embodied):<\/strong><\/p>\n

Create a memory system that works like a librarian’s quick-access shelf\u2014frequently requested books stay within arm’s <\/em>reach while rarely used volumes move to distant archives. Build this caching layer where hot data stays close and cold <\/em>data migrates to deeper storage.<\/em><\/p>\n

Other useful image schemas include:<\/strong><\/p>\n

CONTAINER: \u201cPut validation logic inside a protective wrapper\u201d<\/em><\/p>\n

PATH: \u201cGuide data through transformation pipelines\u201d<\/em><\/p>\n

BALANCE: \u201cMaintain equilibrium between performance and memory\u201d<\/em><\/p>\n

<\/h2>\n

Register and Politeness<\/h2>\n

Tone matters. Sociolinguistics shows that the \u201cregister\u201d of speech influences how it\u2019s received. LLMs mirror this.<\/p>\n

Before (inappropriate register):<\/strong><\/p>\n

hey can u plz write me some python code that does stuff with lists thx<\/em><\/p>\n

After (professional technical register):<\/strong><\/p>\n

Generate a Python function that implements efficient list manipulation operations, including sorting, filtering, and transformation methods. Include docstrings and type hints following PEP 8 conventions.<\/em><\/p>\n

Adopting the persona of \u201can expert Python developer\u201d leverages accommodation theory, nudging the LLM to respond in kind.<\/p>\n

<\/h2>\n

Discourse Markers<\/h2>\n

Markers like first, next, finally guide reasoning. They provide cognitive scaffolding \u2014 for both humans and LLMs.<\/p>\n

Before (unstructured):<\/strong><\/p>\n

Make this code faster and add error handling and documentation<\/em><\/p>\n

After (discourse-structured):<\/strong><\/p>\n

Let’s improve this code systematically. First, analyse performance bottlenecks using profiling data. Next, implement targeted optimisations for the critical path. Then, add comprehensive error handling for edge cases. Finally, document the optimisation strategy and performance gains.<\/em><\/p>\n

<\/h2>\n

Frame Semantics<\/h2>\n

Words make sense inside structured \u201cframes.\u201d Activate the right frame, and prompts align better with expectations.<\/p>\n

Before (isolated concepts):<\/strong><\/p>\n

Add authentication to the API<\/em><\/p>\n

After (frame-activated):<\/strong><\/p>\n

Implement the AUTHENTICATION frame for our API:<\/em>
\n– Authority: JWT token issuer<\/em>
\n– Credentials: username\/password pairs<\/em>
\n– Validation: cryptographic verification<\/em>
\n– Session: token lifecycle management<\/em>
\n– Permissions: role-based access control<\/em>
\n– Audit: authentication event logging<\/em><\/p>\n

Build these frame components with security-first design.<\/em><\/p>\n

<\/h2>\n

Construction Grammar<\/h2>\n

Certain sentence constructions consistently produce strong prompts:<\/p>\n

Role-Action-Object<\/strong><\/p>\n

As a senior Python developer, architect a data pipeline that handles real-time streaming<\/em><\/p>\n

Conditional-Temporal<\/strong><\/p>\n

When user input arrives, validate and sanitise it, ensuring no code injection<\/em><\/p>\n

Analogy Mapping<\/strong><\/p>\n

Database normalisation is like organising a library where books are grouped by topic without duplication<\/em><\/p>\n

Treat prompts as constructions \u2014 test variations systematically.<\/p>\n

<\/h2>\n

Formal Specification<\/h2>\n

Pure formal language is overkill, but BDD-style (Given\/When\/Then) prompt structures approximate it well.<\/p>\n

Example:<\/strong><\/p>\n

Given a user has items in their shopping cart<\/em>
\nWhen they proceed to checkout<\/em>
\nThen they should see the payment options<\/em>
\nAnd the cart total should be calculated correctly<\/em><\/p>\n

Or more concretely:<\/strong><\/p>\n

Scenario: Valid login<\/em><\/strong><\/p>\n

Given a user with email “test@example.com” and password “secure123”<\/em>
\nWhen they attempt to login<\/em>
\nThen they should be redirected to the dashboard<\/em><\/p>\n

Scenario: Invalid password<\/em><\/strong><\/p>\n

Given a user with email “test@example.com” and password “wrong”<\/em>
\nWhen they attempt to login<\/em>
\nThen they should see “Invalid credentials” error<\/em><\/p>\n

BDD works so well because it combines compositional structure, discourse coherence, frame activation, and model-theoretic validation \u2014 all core to linguistics.<\/p>\n

<\/h2>\n

Final thoughts<\/h2>\n

We don\u2019t need to reinvent \u201cprompt theory.\u201d Linguistics already gives us tools to understand why some prompts succeed and others fail.<\/p>\n

A few extra techniques worth experimenting with:<\/p>\n

    \n
  • Conceptual Blending:<\/strong> \u201cLibrary-memory hybrid where frequent books migrate to the reference desk\u201d (for caching).<\/li>\n
  • Relevance Theory:<\/strong> Keep only context that enables new inferences.<\/li>\n
  • Code-switching:<\/strong> Mix natural language for logic with code syntax for structure.<\/li>\n
  • Specification Languages:<\/strong> Use natural language where it helps comprehension, but lean on formal semantics where precision matters.<\/li>\n<\/ul>\n

    If you\u2019re a developer or data practitioner experimenting with LLMs, try treating your prompts less like magic incantations and more like applied linguistics. You may find you get more predictable, higher-quality outputs \u2014 and fewer wasted cycles.<\/p>\n

    At Equal Experts, we\u2019re always swapping notes on real practices that make day-to-day delivery easier. If you\u2019ve been experimenting with these techniques, we\u2019d love to hear what you\u2019ve found.<\/p>\n

    Try it, share it, and let\u2019s keep refining our collective practice.<\/strong><\/p>\n","protected":false},"excerpt":{"rendered":"

    Why prompting advice feels like superstition \u2014 and how linguistics can give us a framework. If you\u2019ve been working with LLMs, you\u2019ve probably seen (or written) endless threads about \u201cgood\u201d and \u201cbad\u201d prompts. Some advice works, some doesn\u2019t, and most of it feels like trial and error. I kept wondering \u2014 is there a unifying […]<\/p>\n","protected":false},"author":245,"featured_media":21961,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"categories":[412,917,5],"tags":[99,813,922,426,391,920,921,873,209],"location":[],"class_list":["post-21958","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","category-experiment-with-us","category-our-thinking","tag-ai","tag-ai-enabled-delivery","tag-cognitive-science","tag-generative-ai","tag-large-language-models","tag-linguistics","tag-nlp","tag-prompt-engineering","tag-software-delivery"],"acf":[],"yoast_head":"\nAre We Re-Inventing Linguistics? Prompting Meets Theory<\/title>\n<meta name=\"description\" content=\"Prompt engineering feels like trial and error. Linguistics gives us proven frameworks for writing better LLM prompts \u2014 with real examples.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Coding with LLMs: are we re-inventing linguistics with prompts?\" \/>\n<meta property=\"og:description\" content=\"Prompt engineering feels like trial and error. Linguistics gives us proven frameworks for writing better LLM prompts \u2014 with real examples.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/\" \/>\n<meta property=\"og:site_name\" content=\"Equal Experts\" \/>\n<meta property=\"article:published_time\" content=\"2025-09-01T07:46:27+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-09-02T00:46:26+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2025\/08\/shutterstock_2431689071-scaled-e1756393138995.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"2560\" \/>\n\t<meta property=\"og:image:height\" content=\"1088\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Neil Murray\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@EqualExperts\" \/>\n<meta name=\"twitter:site\" content=\"@EqualExperts\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Neil Murray\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/\"},\"author\":{\"name\":\"Neil Murray\",\"@id\":\"https:\/\/www.equalexperts.com\/#\/schema\/person\/d897ccf8ef13d100f1be78ec3ec5312c\"},\"headline\":\"Coding with LLMs: are we re-inventing linguistics with prompts?\",\"datePublished\":\"2025-09-01T07:46:27+00:00\",\"dateModified\":\"2025-09-02T00:46:26+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/\"},\"wordCount\":1241,\"publisher\":{\"@id\":\"https:\/\/www.equalexperts.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2025\/08\/shutterstock_2431689071-scaled-e1756393138995.jpg\",\"keywords\":[\"AI\",\"AI Enabled Delivery\",\"Cognitive Science\",\"Generative AI\",\"Large Language Models\",\"Linguistics\",\"NLP\",\"prompt engineering\",\"software delivery\"],\"articleSection\":[\"AI\",\"Experiment with us\",\"Our Thinking\"],\"inLanguage\":\"en-GB\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/\",\"url\":\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/\",\"name\":\"Are We Re-Inventing Linguistics? Prompting Meets Theory\",\"isPartOf\":{\"@id\":\"https:\/\/www.equalexperts.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2025\/08\/shutterstock_2431689071-scaled-e1756393138995.jpg\",\"datePublished\":\"2025-09-01T07:46:27+00:00\",\"dateModified\":\"2025-09-02T00:46:26+00:00\",\"description\":\"Prompt engineering feels like trial and error. Linguistics gives us proven frameworks for writing better LLM prompts \u2014 with real examples.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#primaryimage\",\"url\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2025\/08\/shutterstock_2431689071-scaled-e1756393138995.jpg\",\"contentUrl\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2025\/08\/shutterstock_2431689071-scaled-e1756393138995.jpg\",\"width\":2560,\"height\":1088},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.equalexperts.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Coding with LLMs: are we re-inventing linguistics with prompts?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.equalexperts.com\/#website\",\"url\":\"https:\/\/www.equalexperts.com\/\",\"name\":\"Equal Experts\",\"description\":\"Making Software. Better.\",\"publisher\":{\"@id\":\"https:\/\/www.equalexperts.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.equalexperts.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.equalexperts.com\/#organization\",\"name\":\"Equal Experts\",\"url\":\"https:\/\/www.equalexperts.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/www.equalexperts.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2018\/08\/Equal_Experts_Logo_CMYK_Colour.jpg\",\"contentUrl\":\"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2018\/08\/Equal_Experts_Logo_CMYK_Colour.jpg\",\"width\":719,\"height\":340,\"caption\":\"Equal Experts\"},\"image\":{\"@id\":\"https:\/\/www.equalexperts.com\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/EqualExperts\",\"https:\/\/www.linkedin.com\/company\/equal-experts\/?viewAsMember=true\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.equalexperts.com\/#\/schema\/person\/d897ccf8ef13d100f1be78ec3ec5312c\",\"name\":\"Neil Murray\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/www.equalexperts.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/bee315559ac161a7a3e2a5f7cef5e47396587ba41b90ed119dbf8b9f422d05fa?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/bee315559ac161a7a3e2a5f7cef5e47396587ba41b90ed119dbf8b9f422d05fa?s=96&d=mm&r=g\",\"caption\":\"Neil Murray\"}}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Are We Re-Inventing Linguistics? Prompting Meets Theory","description":"Prompt engineering feels like trial and error. Linguistics gives us proven frameworks for writing better LLM prompts \u2014 with real examples.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/","og_locale":"en_GB","og_type":"article","og_title":"Coding with LLMs: are we re-inventing linguistics with prompts?","og_description":"Prompt engineering feels like trial and error. Linguistics gives us proven frameworks for writing better LLM prompts \u2014 with real examples.","og_url":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/","og_site_name":"Equal Experts","article_published_time":"2025-09-01T07:46:27+00:00","article_modified_time":"2025-09-02T00:46:26+00:00","og_image":[{"width":2560,"height":1088,"url":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2025\/08\/shutterstock_2431689071-scaled-e1756393138995.jpg","type":"image\/jpeg"}],"author":"Neil Murray","twitter_card":"summary_large_image","twitter_creator":"@EqualExperts","twitter_site":"@EqualExperts","twitter_misc":{"Written by":"Neil Murray","Estimated reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#article","isPartOf":{"@id":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/"},"author":{"name":"Neil Murray","@id":"https:\/\/www.equalexperts.com\/#\/schema\/person\/d897ccf8ef13d100f1be78ec3ec5312c"},"headline":"Coding with LLMs: are we re-inventing linguistics with prompts?","datePublished":"2025-09-01T07:46:27+00:00","dateModified":"2025-09-02T00:46:26+00:00","mainEntityOfPage":{"@id":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/"},"wordCount":1241,"publisher":{"@id":"https:\/\/www.equalexperts.com\/#organization"},"image":{"@id":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#primaryimage"},"thumbnailUrl":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2025\/08\/shutterstock_2431689071-scaled-e1756393138995.jpg","keywords":["AI","AI Enabled Delivery","Cognitive Science","Generative AI","Large Language Models","Linguistics","NLP","prompt engineering","software delivery"],"articleSection":["AI","Experiment with us","Our Thinking"],"inLanguage":"en-GB"},{"@type":"WebPage","@id":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/","url":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/","name":"Are We Re-Inventing Linguistics? Prompting Meets Theory","isPartOf":{"@id":"https:\/\/www.equalexperts.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#primaryimage"},"image":{"@id":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#primaryimage"},"thumbnailUrl":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2025\/08\/shutterstock_2431689071-scaled-e1756393138995.jpg","datePublished":"2025-09-01T07:46:27+00:00","dateModified":"2025-09-02T00:46:26+00:00","description":"Prompt engineering feels like trial and error. Linguistics gives us proven frameworks for writing better LLM prompts \u2014 with real examples.","breadcrumb":{"@id":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/"]}]},{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#primaryimage","url":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2025\/08\/shutterstock_2431689071-scaled-e1756393138995.jpg","contentUrl":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2025\/08\/shutterstock_2431689071-scaled-e1756393138995.jpg","width":2560,"height":1088},{"@type":"BreadcrumbList","@id":"https:\/\/www.equalexperts.com\/blog\/our-thinking\/re-inventing-linguistics-llm-prompting\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.equalexperts.com\/"},{"@type":"ListItem","position":2,"name":"Coding with LLMs: are we re-inventing linguistics with prompts?"}]},{"@type":"WebSite","@id":"https:\/\/www.equalexperts.com\/#website","url":"https:\/\/www.equalexperts.com\/","name":"Equal Experts","description":"Making Software. Better.","publisher":{"@id":"https:\/\/www.equalexperts.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.equalexperts.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"},{"@type":"Organization","@id":"https:\/\/www.equalexperts.com\/#organization","name":"Equal Experts","url":"https:\/\/www.equalexperts.com\/","logo":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.equalexperts.com\/#\/schema\/logo\/image\/","url":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2018\/08\/Equal_Experts_Logo_CMYK_Colour.jpg","contentUrl":"https:\/\/www.equalexperts.com\/wp-content\/uploads\/2018\/08\/Equal_Experts_Logo_CMYK_Colour.jpg","width":719,"height":340,"caption":"Equal Experts"},"image":{"@id":"https:\/\/www.equalexperts.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/EqualExperts","https:\/\/www.linkedin.com\/company\/equal-experts\/?viewAsMember=true"]},{"@type":"Person","@id":"https:\/\/www.equalexperts.com\/#\/schema\/person\/d897ccf8ef13d100f1be78ec3ec5312c","name":"Neil Murray","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.equalexperts.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/bee315559ac161a7a3e2a5f7cef5e47396587ba41b90ed119dbf8b9f422d05fa?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/bee315559ac161a7a3e2a5f7cef5e47396587ba41b90ed119dbf8b9f422d05fa?s=96&d=mm&r=g","caption":"Neil Murray"}}]}},"_links":{"self":[{"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/posts\/21958","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/users\/245"}],"replies":[{"embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/comments?post=21958"}],"version-history":[{"count":0,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/posts\/21958\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/media\/21961"}],"wp:attachment":[{"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/media?parent=21958"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/categories?post=21958"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/tags?post=21958"},{"taxonomy":"location","embeddable":true,"href":"https:\/\/www.equalexperts.com\/wp-json\/wp\/v2\/location?post=21958"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}