Designing an LLM-Augmented Course for Secure Coding Using a Structured Learning Design Model and Prompt Patterns

Designing an LLM-Augmented Course for Secure Coding Using a Structured Learning Design Model and Prompt Patterns | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Designing an LLM-Augmented Course for Secure Coding Using a Structured Learning Design Model and Prompt Patterns Philipp Haindl, Peter Kieseberg, Oliver Eigner This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7813236/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Purpose: Extensive use of Large Language Models (LLMs) threatens students' higher-order cognitive skills. This paper presents a novel framework redefining Prompt Engineering as a Technological Pedagogical Design Skill. It provides the syntax to operationalize pedagogical intent, specifically to sustain Productive Struggle and foster Evaluative Judgement. Methods: Following a Design Science Research (DSR) methodology, our framework artifact adapts foundational prompt pattern catalogs and maps them to pedagogical goals. We demonstrate its application via a secure coding course design using the DeLTA model and report on its preliminary validation in a master's course. Results: Our course design shows how patterns like the Cognitive Verifier can structure inquiry to sustain Productive Struggle. Preliminary validation from the master's course indicates the framework effectively scaffolds complex tasks, such as research proposal development, thereby fostering students' Evaluative Judgement. Conclusion: This DSR artifact offers a systematic method to transform the LLM from an unmanaged risk into a controlled pedagogical agent. Mastering prompt patterns allows instructors to design AI-augmented experiences that support, rather than supplant, student cognition, shifting the educator's role towards that of a 'learning architect'. Software Engineering Prompt Engineering Large Language Model Higher Education Programming Education Evaluative Judgement Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7813236","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":526870177,"identity":"7ce41905-df2e-4190-a5a5-9bdf8bf4a4d2","order_by":0,"name":"Philipp Haindl","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFElEQVRIie2RsWrDMBBAzwSUReD1QsD9hctkDMHfEiFo1o4dSnEpuEvpnMGQX+iYUUHgqdSrIBnsxVOGToUupYrp4IKMOxaqN5zgpKc76QA8nr8IBndqZVeCIAN+tQzpF0rWU+hy9gyT7y02pAAo6BQLJz2uxPP7TDW7I8RTndcnqjAOq7KGmxTCbeZUkmKfKfHSQvIoHhYFHTDZyClBKQFLdxUywiq5BrJxzulwS2bCEJjtdlSpmrPyilRpq3wquBhVTFdFISnJMMgV0ICSbET3Fk6myWcFSSQjYxJPki/KlfvHcN00H7tjRNW6xdN1ahvbt/XbexpFWrkbOwc7Td5PMrD3c+f5nvIjOTR2j8fj+ad8Ack7ZscjINrAAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-6075-5286","institution":"St. Pölten University of Applied Sciences","correspondingAuthor":true,"prefix":"","firstName":"Philipp","middleName":"","lastName":"Haindl","suffix":""},{"id":526870368,"identity":"2fb3f36a-79df-4eea-a839-6a93be045d54","order_by":1,"name":"Peter Kieseberg","email":"","orcid":"https://orcid.org/0000-0002-2847-2152","institution":"St. Pölten University of Applied Sciences","correspondingAuthor":false,"prefix":"","firstName":"Peter","middleName":"","lastName":"Kieseberg","suffix":""},{"id":526870517,"identity":"54c2d0a1-71ff-4593-ae52-95aeee348f65","order_by":2,"name":"Oliver Eigner","email":"","orcid":"https://orcid.org/0000-0003-1053-8421","institution":"St. Pölten University of Applied Sciences","correspondingAuthor":false,"prefix":"","firstName":"Oliver","middleName":"","lastName":"Eigner","suffix":""}],"badges":[],"createdAt":"2025-10-09 05:34:55","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7813236/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7813236/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93264287,"identity":"58cb5cfe-3969-4a5b-ad80-c90e6c6d0f00","added_by":"auto","created_at":"2025-10-10 19:11:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":302143,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7813236/v1_covered_28b7fcd1-50df-4cc0-90d0-58cd40ca03e0.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eDesigning an LLM-Augmented Course for Secure Coding Using a Structured Learning Design Model and Prompt Patterns\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"St. Pölten University of Applied Sciences","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Prompt Engineering, Large Language Model, Higher Education, Programming Education, Evaluative Judgement","lastPublishedDoi":"10.21203/rs.3.rs-7813236/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7813236/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003ePurpose:\u003c/strong\u003e Extensive use of Large Language Models (LLMs) threatens students' higher-order cognitive skills. This paper presents a novel framework redefining Prompt Engineering as a Technological Pedagogical Design Skill. It provides the syntax to operationalize pedagogical intent, specifically to sustain Productive Struggle and foster Evaluative Judgement.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods:\u003c/strong\u003e Following a Design Science Research (DSR) methodology, our framework artifact adapts foundational prompt pattern catalogs and maps them to pedagogical goals. We demonstrate its application via a secure coding course design using the DeLTA model and report on its preliminary validation in a master's course.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e Our course design shows how patterns like the Cognitive Verifier can structure inquiry to sustain Productive Struggle. Preliminary validation from the master's course indicates the framework effectively scaffolds complex tasks, such as research proposal development, thereby fostering students' Evaluative Judgement.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion:\u003c/strong\u003e This DSR artifact offers a systematic method to transform the LLM from an unmanaged risk into a controlled pedagogical agent. Mastering prompt patterns allows instructors to design AI-augmented experiences that support, rather than supplant, student cognition, shifting the educator's role towards that of a 'learning architect'.\u003c/p\u003e","manuscriptTitle":"Designing an LLM-Augmented Course for Secure Coding Using a Structured Learning Design Model and Prompt Patterns","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-10 19:03:36","doi":"10.21203/rs.3.rs-7813236/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"06072652-ba48-413c-85af-75363e5ea1d1","owner":[],"postedDate":"October 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56000289,"name":"Software Engineering"}],"tags":[],"updatedAt":"2025-10-10T19:03:36+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-10 19:03:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7813236","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7813236","identity":"rs-7813236","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}