{"type":"data","nodes":[{"type":"data","data":[{"lab":1,"legalFooterLinks":37},{"identity":2,"contacts":13,"office_hours":30,"web":32,"languages":34,"locale":36},{"name":3,"short_name":4,"description":5,"organisation":6,"organisation_url":7,"organisation_logo":8,"university":9,"university_url":10,"university_logo":11,"established":12},"Human-Centered Intelligent Systems Lab","HCIS Lab","We are shaping the future of automotive technology through intelligent systems that seamlessly integrate human needs with cutting-edge AI innovation.","AImotion Bavaria","https://www.thi.de/forschung/aimotion/","/content/lab/aimotion-bavaria.png","Ingolstadt University of Applied Sciences","https://www.thi.de/","/content/lab/thi.png",2025,{"addresses":14,"emails":21,"phones":24,"primary_type":16,"primary_email":23,"emailsByType":27,"addressesByType":28,"phonesByType":29},[15],{"type":16,"title":9,"street":17,"city":18,"postal_code":19,"country":20},"office","Esplanade 10","Ingolstadt","85049","Germany",[22],{"type":16,"email":23},"hcis@thi.de",[25],{"type":16,"number":26},"+49 841 9348 0",{"office":23},{"office":15},{"office":26},{"days":31,"timezone":-1},{},{"social":33},{},["Set",35,36],"DE","EN",[38,42,47],{"slug":39,"name":40,"label":40,"href":41},"datenschutzerklaerung","Datenschutzerklärung","/legal/privacy/datenschutzerklaerung",{"slug":43,"name":44,"label":45,"href":46},"barrierefreiheitserklaerung","Erklärung zur Barrierefreiheit","Barrierefreiheit","/legal/accessibility/barrierefreiheitserklaerung",{"slug":48,"name":49,"label":49,"href":50},"impressum","Impressum","/legal/impressum"],"uses":{}},{"type":"data","data":[{"person":1,"publications":26,"projects":112,"blogPosts":169,"teaching":259},{"slug":2,"firstname":3,"lastname":4,"email":5,"role":6,"quote":7,"image":8,"interests":9,"skills":10,"social":19,"updatedAt":23,"isPublished":24,"html":25},"tugcan-onbas","Tuğcan","ÖNBAŞ","tugcan.oenbas@thi.de","UXD / AI","Fusing creativity and technology to design experiences that bridge imagination and intelligent systems.","/content/people/tugcan-onbas/profile.png",[],[11,12,13,14,15,16,17,18],"Human–Computer Interaction (HCI)","Human-Centered & AI-Driven Experience Design","Multimodal Interaction","User Experience Research","Experience Engineering","Interactive Systems Prototyping & Development","Data-Driven Interaction Design","Applied Research Communication",{"website":20,"github":21,"linkedin":22},"https://tugcanonbas.com","https://github.com/tugcanonbas","https://www.linkedin.com/in/tugcanonbas","2025-10-31",true,"\u003Cp>Tuğcan ÖNBAŞ is a student assistant in the Human-Centered Intelligent Systems at Ingolstadt University of Applied Sciences (THI), where he is pursuing a Master’s degree in User Experience Design with a focus on the intersection of design, technology, and intelligent systems within mobility and automotive contexts.\u003C/p>\n\u003Cp>His portfolio includes a range of independent engagements—from iOS and web apps to design systems and Swift packages—bridging software engineering with visual communication. This experience informs his research in human–AI interaction, where he integrates design reasoning with technical experimentation to explore how intelligent systems can support intuitive, transparent interactions across diverse digital domains.\u003C/p>\n\u003Cp>His academic work explores human-centered AI across mobility, intelligent systems, and digital experience design, focusing on how AI-driven technologies can enhance interaction, perception, and engagement in both physical and digital contexts. His research interests include multimodal interaction, affect-sensitive interfaces, and the integration of large language models into user experience, emphasizing clarity, contextual awareness, and the creation of meaningful, adaptive systems that advance human-centered innovation.\u003C/p>",[27,56,76,96],{"slug":28,"title":29,"type":30,"authors":31,"venue":35,"publisher":36,"year":37,"month":38,"location":39,"doi":40,"pdf":41,"author_slugs":42,"project_slugs":45,"tags":48,"updatedAt":51,"isPublished":24,"html":52,"abstractHtml":53,"apa":54,"bibtexPath":55},"campusgo-uist25","CampusGO: A Smart Campus Mobility Suite with Wearable Integration","inproceedings",[32,33,34],"Tuğcan Önbaş","Laura Radetzky","Paul Bauer","UIST","ACM",2025,10,"Dublin, Ireland","10.1145/3744335.3758490","/publications/campusgo-uist25-2025.pdf",[43,2,44],"laura-radetzky","paul-bauer",[46,47],"wearable-sensing-pipeline","budget-app",[49,50],"HCI","Systems","2025-11-11","\u003Ch2 id=\"abstract\">\u003Ca href=\"#abstract\">Abstract\u003C/a>\u003C/h2>\n\u003Cp>This paper reports methods, results, and design implications for intelligent, human‑centered systems.\u003C/p>","\u003Cp>This paper reports methods, results, and design implications for intelligent, human‑centered systems.\u003C/p>","Huber, V. B., Ertl, F. L., Schlaak, A., Simson, H., & Alvarez, I. (2025). Can an AI Voice Assistant reduce Stress for Drivers confronted with warning Signals? In Adjunct Proceedings of the 17th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (pp. 106–113). AutomotiveUI Adjunct ’25: 17th International Conference on Automotive User Interfaces and Interactive Vehicular Applications. ACM. https://doi.org/10.1145/3744335.3758490\n","C:\\Users\\alvarez\\Documents\\code\\HCIS.AI\\HCIS-website\\.cache\\doi\\campusgo-uist25\\citation.bib",{"slug":57,"title":58,"type":59,"authors":60,"venue":64,"publisher":36,"year":37,"month":65,"location":66,"doi":40,"pdf":67,"author_slugs":68,"project_slugs":72,"tags":74,"updatedAt":51,"isPublished":24,"html":52,"abstractHtml":53,"apa":54,"bibtexPath":75},"accessibility-hci25","Beyond Checklists: Pragmatic Accessibility in HCI Curricula","article",[32,61,62,34,63],"Ignacio Álvarez","Monika Szuban","Maria Kreutz","Interactions",6,"New York, USA","/publications/accessibility-hci25-2025.pdf",[69,70,71,2,44],"ignacio-alvarez","maria-kreutz","monika-szuban",[73],"crisis-mapping-app",[49,50],"C:\\Users\\alvarez\\Documents\\code\\HCIS.AI\\HCIS-website\\.cache\\doi\\accessibility-hci25\\citation.bib",{"slug":77,"title":78,"type":79,"authors":80,"publisher":84,"year":37,"month":85,"location":86,"doi":40,"pdf":87,"author_slugs":88,"project_slugs":92,"tags":94,"updatedAt":51,"isPublished":24,"html":52,"abstractHtml":53,"apa":54,"bibtexPath":95},"simulation-hub-preprint","Simulation Hub: A Unified Pipeline for CARLA and Unity Studies","preprint",[81,82,83,61,32],"Vanchha Chandrayan","Lena Wolf","Julia Podlipensky","arXiv",3,"—","/publications/simulation-hub-preprint-2025.pdf",[69,89,2,90,91],"julia-podlipensky","vanchha-chandrayan","lena-wolf",[93],"campusgo",[49,50],"C:\\Users\\alvarez\\Documents\\code\\HCIS.AI\\HCIS-website\\.cache\\doi\\simulation-hub-preprint\\citation.bib",{"slug":97,"title":98,"type":30,"authors":99,"venue":101,"publisher":36,"year":102,"month":103,"location":104,"doi":40,"pdf":105,"author_slugs":106,"project_slugs":108,"tags":110,"updatedAt":51,"isPublished":24,"html":52,"abstractHtml":53,"apa":54,"bibtexPath":111},"gamified-tor-automotiveui24","Gamified Take‑Over Requests Do Not Harm Response Time",[61,32,100,82,83],"Karthik Sai Pasupuleti","AutomotiveUI",2024,9,"Stanford, USA","/publications/gamified-tor-automotiveui24-2024.pdf",[69,89,107,2,91],"karthik-sai-pasupuleti",[109],"driver-gamification-study",[49,50],"C:\\Users\\alvarez\\Documents\\code\\HCIS.AI\\HCIS-website\\.cache\\doi\\gamified-tor-automotiveui24\\citation.bib",[113,128,140,158],{"slug":47,"title":114,"overview":115,"status":116,"leads":117,"assistants":118,"start_date":119,"tags":120,"links":123,"publications":126,"updatedAt":51,"isPublished":24,"html":127},"Budget","Collaborative finance tracking app for Apple platforms with CoreData/CloudKit.","in-progress",[44,90],[2,89],"2025-01-15",[49,121,122],"AI","Simulation",{"website":124,"github":125},"https://example.com/budget-app","https://github.com/hcis/budget-app",[],"\u003Ch2 id=\"objectives\">\u003Ca href=\"#objectives\">Objectives\u003C/a>\u003C/h2>\n\u003Cul>\n\u003Cli>Robust experimentation\u003C/li>\n\u003Cli>Real‑time insights\u003C/li>\n\u003C/ul>\n\u003Ch2 id=\"approach\">\u003Ca href=\"#approach\">Approach\u003C/a>\u003C/h2>\n\u003Cp>Explain methodology, tools, or system setup.\u003Cbr>\nYou can embed code snippets, images, or diagrams here.\u003C/p>\n\u003Ch2 id=\"results\">\u003Ca href=\"#results\">Results\u003C/a>\u003C/h2>\n\u003Cp>Milestones, outcomes, or demo links.\u003C/p>\n\u003Ch2 id=\"next-steps\">\u003Ca href=\"#next-steps\">Next Steps\u003C/a>\u003C/h2>\n\u003Cp>Roadmap, collaborations, and open‑source plans.\u003C/p>",{"slug":129,"title":130,"overview":131,"status":116,"leads":132,"assistants":133,"start_date":119,"tags":135,"links":136,"publications":139,"updatedAt":51,"isPublished":24,"html":127},"emotion-aware-cabin-agent","Emotion‑Aware In‑Cabin Agent","An LLM‑driven agent that senses driver state and adapts feedback for safer, calmer rides.",[43,2],[134,71],"anna-schmidt",[49,121,122],{"website":137,"github":138},"https://example.com/emotion-aware-cabin-agent","https://github.com/hcis/emotion-aware-cabin-agent",[],{"slug":141,"title":142,"overview":143,"status":144,"leads":145,"assistants":146,"start_date":147,"tags":148,"links":152,"publications":155,"updatedAt":156,"isPublished":24,"html":157},"driver-drowsiness-detection","Driver Drowsiness Detection","Mobile companion for THI commuters that blends shuttle tracking, micro-incentives for eco-friendly travel, and route planning across modes.","planning",[2,69],[],"2025-11-01",[149,150,151],"Mobility","Routing","Behavior Change",{"website":153,"github":154},"https://example.com/driver-drowsiness-detection","https://github.com/hcis/driver-drowsiness-detection",[],"2025-11-02","\u003Ch2 id=\"objectives\">\u003Ca href=\"#objectives\">Objectives\u003C/a>\u003C/h2>\n\u003Cul>\n\u003Cli>Increase active and shared trips on campus\u003C/li>\n\u003Cli>Provide reliable, low-friction route guidance\u003C/li>\n\u003Cli>Reward sustainable choices with transparent points\u003C/li>\n\u003C/ul>\n\u003Ch2 id=\"approach\">\u003Ca href=\"#approach\">Approach\u003C/a>\u003C/h2>\n\u003Cp>iOS-first prototype with modular data connectors (GTFS-RT for shuttles, bicycle infrastructure layers), experiment framework for A/B nudges.\u003C/p>\n\u003Ch2 id=\"results\">\u003Ca href=\"#results\">Results\u003C/a>\u003C/h2>\n\u003Cp>Design sprint complete; data contracts drafted; pilot routes mapped.\u003C/p>\n\u003Ch2 id=\"next-steps\">\u003Ca href=\"#next-steps\">Next Steps\u003C/a>\u003C/h2>\n\u003Cp>User testing with students and staff; publish a public beta roadmap.\u003C/p>",{"slug":159,"title":160,"overview":161,"status":144,"leads":162,"assistants":163,"start_date":119,"tags":164,"links":165,"publications":168,"updatedAt":51,"isPublished":24,"html":127},"ar-navigation-lab","AR Navigation Lab","Indoor navigation experiments with UWB beacons and AR overlays.",[2,43],[70,69],[49,121,122],{"website":166,"github":167},"https://example.com/ar-navigation-lab","https://github.com/hcis/ar-navigation-lab",[],[170,186,200,212,236,247],{"slug":171,"title":172,"authors":173,"external_authors":174,"tags":175,"category":177,"description":178,"cover":179,"attachments":180,"updatedAt":51,"publishedAt":184,"isPublished":24,"html":185},"accessibility-audit-kit-kickoff","Kicking off the Accessibility Audit Kit",[2],[],[49,176],"Research Log","Project Diary","Scope, milestones, and community input.","assets/images/default-post-cover.png",[181],{"label":182,"url":183},"PDF version","/blog/accessibility-audit-kit-kickoff/accessibility-audit-kit-kickoff.pdf","2025-07-16","\u003Ch2 id=\"blog-content\">\u003Ca href=\"#blog-content\">Blog Content\u003C/a>\u003C/h2>\n\u003Cp>Updates from the field related to [accessibility-audit-kit].\u003C/p>\n\u003Ch3 id=\"citations-for-entities\">\u003Ca href=\"#citations-for-entities\">Citations for Entities\u003C/a>\u003C/h3>\n\u003Cp>We extended \u003Ca href=\"/research/projects/accessibility-audit-kit\" target=\"_self\">Accessibility Audit Kit\u003C/a> and referenced recent work.\u003C/p>",{"slug":187,"title":188,"subtitle":189,"authors":190,"external_authors":191,"tags":193,"category":177,"description":194,"cover":179,"attachments":195,"updatedAt":51,"publishedAt":198,"isPublished":24,"html":199},"ai-for-interfaces","Prompt Patterns We Actually Use","AI-Driven Design for Interfaces and Prototyping Tools",[43,2],[192],"John Smith",[49],"Productive prompts, guardrails, and design.",[196],{"label":182,"url":197},"/blog/ai-for-interfaces/ai-for-interfaces.pdf","2025-06-13","\u003Chr>\n\u003Cp>title: “Exploring the Wonders of Markdown: A Complete Demonstration”\r\nauthor: “AI Research Collective”\r\ndate: “2025-11-11”\r\ntags: [“markdown”, “documentation”, “syntax”, “tutorial”]\u003C/p>\n\u003Chr>\n\u003Ch1 id=\"exploring-the-wonders-of-markdown-\">\u003Ca href=\"#exploring-the-wonders-of-markdown-\">Exploring the Wonders of Markdown 📝\u003C/a>\u003C/h1>\n\u003Cp>Markdown is a lightweight markup language designed for readability and simplicity. This post demonstrates \u003Cstrong>every major Markdown element\u003C/strong>, showing how you can combine structure, clarity, and design into a single file.\u003C/p>\n\u003Chr>\n\u003Ch2 id=\"table-of-contents\">\u003Ca href=\"#table-of-contents\">Table of Contents\u003C/a>\u003C/h2>\n\u003Col>\n\u003Cli>\u003Ca href=\"#introduction\">Introduction\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#headings-and-text-styles\">Headings and Text Styles\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#lists\">Lists\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#tables\">Tables\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#code-blocks\">Code Blocks\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#links-and-images\">Links and Images\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#blockquotes-and-citations\">Blockquotes and Citations\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#math-and-latex\">Math and LaTeX\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#footnotes\">Footnotes\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#task-lists\">Task Lists\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#horizontal-rules-and-escapes\">Horizontal Rules and Escapes\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#html-embeds\">HTML Embeds\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"#conclusion\">Conclusion\u003C/a>\u003C/li>\n\u003C/ol>\n\u003Chr>\n\u003Ch2 id=\"introduction\">\u003Ca href=\"#introduction\">Introduction\u003C/a>\u003C/h2>\n\u003Cp>Markdown allows writers and developers to create clean, structured documents with minimal syntax. It’s widely used in \u003Cstrong>GitHub README files\u003C/strong>, \u003Cstrong>academic papers\u003C/strong>, and \u003Cstrong>technical blogs\u003C/strong>.\u003C/p>\n\u003Cblockquote>\n\u003Cp>“Markdown is writing with structure, not decoration.” — \u003Cem>Unknown\u003C/em>\u003C/p>\n\u003C/blockquote>\n\u003Chr>\n\u003Ch2 id=\"headings-and-text-styles\">\u003Ca href=\"#headings-and-text-styles\">Headings and Text Styles\u003C/a>\u003C/h2>\n\u003Ch3 id=\"heading-levels\">\u003Ca href=\"#heading-levels\">Heading Levels\u003C/a>\u003C/h3>\n\u003Ch1 id=\"h1-heading\">\u003Ca href=\"#h1-heading\">H1 Heading\u003C/a>\u003C/h1>\n\u003Ch2 id=\"h2-heading\">\u003Ca href=\"#h2-heading\">H2 Heading\u003C/a>\u003C/h2>\n\u003Ch3 id=\"h3-heading\">\u003Ca href=\"#h3-heading\">H3 Heading\u003C/a>\u003C/h3>\n\u003Ch4 id=\"h4-heading\">\u003Ca href=\"#h4-heading\">H4 Heading\u003C/a>\u003C/h4>\n\u003Ch5 id=\"h5-heading\">\u003Ca href=\"#h5-heading\">H5 Heading\u003C/a>\u003C/h5>\n\u003Ch6 id=\"h6-heading\">\u003Ca href=\"#h6-heading\">H6 Heading\u003C/a>\u003C/h6>\n\u003Ch3 id=\"text-styles\">\u003Ca href=\"#text-styles\">Text Styles\u003C/a>\u003C/h3>\n\u003Cul>\n\u003Cli>\u003Cem>Italic\u003C/em> or \u003Cem>Italic\u003C/em>\u003C/li>\n\u003Cli>\u003Cstrong>Bold\u003C/strong> or \u003Cstrong>Bold\u003C/strong>\u003C/li>\n\u003Cli>\u003Cstrong>\u003Cem>Bold Italic\u003C/em>\u003C/strong>\u003C/li>\n\u003Cli>\u003Cdel>Strikethrough\u003C/del>\u003C/li>\n\u003Cli>\u003Ccode>Inline code\u003C/code>\u003C/li>\n\u003C/ul>\n\u003Chr>\n\u003Ch2 id=\"lists\">\u003Ca href=\"#lists\">Lists\u003C/a>\u003C/h2>\n\u003Ch3 id=\"unordered-list\">\u003Ca href=\"#unordered-list\">Unordered List\u003C/a>\u003C/h3>\n\u003Cul>\n\u003Cli>Item A\n\u003Cul>\n\u003Cli>Subitem A1\u003C/li>\n\u003Cli>Subitem A2\u003C/li>\n\u003C/ul>\n\u003C/li>\n\u003Cli>Item B\u003C/li>\n\u003Cli>Item C\u003C/li>\n\u003C/ul>\n\u003Ch3 id=\"ordered-list\">\u003Ca href=\"#ordered-list\">Ordered List\u003C/a>\u003C/h3>\n\u003Col>\n\u003Cli>Step One\u003C/li>\n\u003Cli>Step Two\u003C/li>\n\u003Cli>Step Three\n\u003Col>\n\u003Cli>Nested Step\u003C/li>\n\u003C/ol>\n\u003C/li>\n\u003C/ol>\n\u003Ch3 id=\"definition-list\">\u003Ca href=\"#definition-list\">Definition List\u003C/a>\u003C/h3>\n\u003Cp>Term 1\u003Cbr>\n: Definition for term 1\u003C/p>\n\u003Cp>Term 2\u003Cbr>\n: Definition for term 2\u003C/p>\n\u003Chr>\n\u003Ch2 id=\"tables\">\u003Ca href=\"#tables\">Tables\u003C/a>\u003C/h2>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Name\u003C/th>\n\u003Cth>Role\u003C/th>\n\u003Cth>Experience\u003C/th>\n\u003C/tr>\n\u003C/thead>\n\u003Ctbody>\n\u003Ctr>\n\u003Ctd>Alice\u003C/td>\n\u003Ctd>UX Designer\u003C/td>\n\u003Ctd>5 years\u003C/td>\n\u003C/tr>\n\u003Ctr>\n\u003Ctd>Bob\u003C/td>\n\u003Ctd>Backend Engineer\u003C/td>\n\u003Ctd>7 years\u003C/td>\n\u003C/tr>\n\u003Ctr>\n\u003Ctd>Charlie\u003C/td>\n\u003Ctd>Data Scientist\u003C/td>\n\u003Ctd>3 years\u003C/td>\n\u003C/tr>\n\u003C/tbody>\n\u003C/table>\n\u003Cp>\u003Cstrong>Table Alignment Example:\u003C/strong>\u003C/p>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth align=\"left\">Left Aligned\u003C/th>\n\u003Cth align=\"center\">Center Aligned\u003C/th>\n\u003Cth align=\"right\">Right Aligned\u003C/th>\n\u003C/tr>\n\u003C/thead>\n\u003Ctbody>\n\u003Ctr>\n\u003Ctd align=\"left\">Alpha\u003C/td>\n\u003Ctd align=\"center\">Beta\u003C/td>\n\u003Ctd align=\"right\">Gamma\u003C/td>\n\u003C/tr>\n\u003Ctr>\n\u003Ctd align=\"left\">10\u003C/td>\n\u003Ctd align=\"center\">20\u003C/td>\n\u003Ctd align=\"right\">30\u003C/td>\n\u003C/tr>\n\u003C/tbody>\n\u003C/table>\n\u003Chr>\n\u003Ch2 id=\"code-blocks\">\u003Ca href=\"#code-blocks\">Code Blocks\u003C/a>\u003C/h2>\n\u003Cp>Inline example: \u003Ccode>console.log(\"Hello, Markdown!\");\u003C/code>\u003C/p>\n\u003Ch3 id=\"javascript-example\">\u003Ca href=\"#javascript-example\">JavaScript Example\u003C/a>\u003C/h3>\n\u003Cpre>\u003Ccode class=\"language-javascript\">function greet(name) {\r\n\tconsole.log(`Hello, ${name}!`);\r\n}\r\ngreet('World');\n\u003C/code>\u003C/pre>",{"slug":201,"title":202,"authors":203,"external_authors":204,"tags":205,"category":177,"description":206,"cover":179,"attachments":207,"updatedAt":51,"publishedAt":210,"isPublished":24,"html":211},"campusgo-beta","CampusGO enters closed beta",[2,69],[],[49,176],"Feature highlights and how to join.",[208],{"label":182,"url":209},"/blog/campusgo-beta/campusgo-beta.pdf","2025-07-19","\u003Ch2 id=\"blog-content\">\u003Ca href=\"#blog-content\">Blog Content\u003C/a>\u003C/h2>\n\u003Cp>Updates from the field related to [campusgo].\u003C/p>\n\u003Ch3 id=\"citations-for-entities\">\u003Ca href=\"#citations-for-entities\">Citations for Entities\u003C/a>\u003C/h3>\n\u003Cp>We extended \u003Ca href=\"/research/projects/campusgo\" target=\"_self\">CampusGO\u003C/a> and referenced recent work.\u003C/p>",{"slug":213,"title":214,"subtitle":215,"authors":216,"external_authors":217,"tags":219,"category":224,"description":225,"cover":226,"attachments":227,"updatedAt":51,"publishedAt":234,"isPublished":24,"html":235},"prompt-patterns-we-actually-use","Promptmuster, die wir wirklich nutzen","Vom Chaos zur Klarheit: wie sich strukturiertes Prompting in unseren täglichen Workflows entwickelt hat",[2],[218],"Lina Hoffmann",[220,221,222,223],"KI","Prompt Engineering","LLM Forschung","UX Writing","Research Diary","Ein Deep Dive in die praktischen Promptmuster, die wir in unserem Labor einsetzen — die echten, die tägliche Iterationen, Debugging und Deployment überleben.","/content/news/prompt-patterns-we-actually-use/cover.png",[228,231],{"label":229,"url":230},"PDF-Version","/blog/prompt-patterns-we-actually-use/post.pdf",{"label":232,"url":233},"Foliensatz","https://example.com/slides","2025-11-15","\u003Ch2 id=\"introduction\">\u003Ca href=\"#introduction\">Introduction\u003C/a>\u003C/h2>\n\u003Cp>We’ve written thousands of prompts — some elegant, some embarrassing. Over time, patterns emerge.\u003Cbr>\nThis post collects \u003Cstrong>real prompt patterns\u003C/strong> we use across our research projects, UX workflows, and development pipelines.\u003C/p>\n\u003Cblockquote>\n\u003Cp>\u003Cem>“Prompt engineering is not an art of magic — it’s an art of maintenance.”\u003C/em>\u003Cbr>\n— A very tired developer\u003C/p>\n\u003C/blockquote>\n\u003Cp>Our \u003Ca href=\"/research/projects/budget-app\" target=\"_self\">Emotion Agent\u003C/a> project heavily relies on LLMs for generating user scenarios, analyzing multimodal data, and drafting research reports. Through trial and error, we distilled several prompt patterns that consistently yield reliable results.\u003C/p>\n\u003Cp>Now it’s time to share this \u003Ca href=\"/research/publications/accessibility-hci25\" target=\"_self\">Beyond Checklists: Pragmatic Accessibility in HCI Curricula\u003C/a> paper with you and document how we structure our prompts for maximum clarity and repeatability.\u003C/p>\n\u003Cp>While this is thought on \u003Ca href=\"/teaching/offerings/data-visualization\" target=\"_self\">our prompting workshop\u003C/a>, consider this a living document. We’ll update it as we refine our techniques. And here’s a thesis diving deeper into prompt engineering best practices. Thanks to \u003Ca href=\"/team/monika-szuban\" target=\"_self\">Monika Szuban\u003C/a> for co-authoring this post!\u003C/p>\n\u003Cp>Dive deeper in \u003Ca href=\"/news/swiftui-prototyping-tips\" target=\"_self\">SwiftUI Prototyping Tips for Researchers\u003C/a>.\u003C/p>\n\u003Chr>\n\u003Ch2 id=\"1-the-instructional-stack\">\u003Ca href=\"#1-the-instructional-stack\">1. The Instructional Stack\u003C/a>\u003C/h2>\n\u003Cp>We layer our prompts like lasagna: context first, task next, then constraints.\u003C/p>\n\u003Cpre>\u003Ccode class=\"language-text\">SYSTEM: You are an expert UX researcher writing a comparative analysis.\r\nUSER: Compare the interaction models of autonomous shuttles in our dataset.\r\nCONSTRAINTS: Use concise academic tone, include a summary table, cite 2 sources.\n\u003C/code>\u003C/pre>\n\u003Cp>Here’s my personal \u003Ca href=\"https://tugcanonbas.com\" rel=\"noopener noreferrer\" target=\"_blank\">as tugcanonbas.com\u003C/a>:\u003C/p>\n\u003Cp>Why it works:\u003C/p>\n\u003Cul>\n\u003Cli>\u003Cstrong>Context primes the model\u003C/strong> without overloading.\u003C/li>\n\u003Cli>\u003Cstrong>Constraints anchor\u003C/strong> creativity.\u003C/li>\n\u003Cli>\u003Cstrong>Explicit task type\u003C/strong> prevents drift.\u003C/li>\n\u003C/ul>\n\u003Chr>\n\u003Ch2 id=\"2-the-sandwich-pattern\">\u003Ca href=\"#2-the-sandwich-pattern\">2. The Sandwich Pattern\u003C/a>\u003C/h2>\n\u003Cp>When collaborating with LLMs, we use the \u003Cstrong>sandwich\u003C/strong>:\u003Cbr>\ncontext → task → output structure → tone reminder.\u003C/p>\n\u003Cpre>\u003Ccode class=\"language-json\">{\r\n\t\"context\": \"Research project: Emotion-Aware Driver Agent\",\r\n\t\"task\": \"Write user story\",\r\n\t\"output_format\": \"Markdown\",\r\n\t\"tone\": \"Human-centered and data-informed\"\r\n}\n\u003C/code>\u003C/pre>\n\u003Cp>This pattern works wonders in SvelteKit or SwiftUI documentation generation.\u003C/p>\n\u003Chr>\n\u003Ch2 id=\"3-self-check-loop\">\u003Ca href=\"#3-self-check-loop\">3. Self-Check Loop\u003C/a>\u003C/h2>\n\u003Cp>We make the model critique itself before we trust it.\u003C/p>\n\u003Cpre>\u003Ccode class=\"language-markdown\">### Step 1 — Generate\r\n\r\nCreate 3 hypotheses for driver emotion classification errors.\r\n\r\n### Step 2 — Evaluate\r\n\r\nFor each, add a confidence score (0–1) and a rationale.\r\n\r\n### Step 3 — Reflect\r\n\r\nPick the most plausible hypothesis and rephrase it as a design insight.\n\u003C/code>\u003C/pre>\n\u003Cp>This “self-loop” style produces near peer-review–ready insights.\u003C/p>\n\u003Chr>\n\u003Ch2 id=\"4-output-scaffolding\">\u003Ca href=\"#4-output-scaffolding\">4. Output Scaffolding\u003C/a>\u003C/h2>\n\u003Cp>When generating structured content like YAML, we \u003Cstrong>predefine the schema\u003C/strong> in the prompt:\u003C/p>\n\u003Cpre>\u003Ccode class=\"language-yaml\"># Schema\r\ntitle: string\r\nsummary: string\r\ntakeaways: [string]\r\nreferences: [string]\n\u003C/code>\u003C/pre>\n\u003Cp>Then we ask:\u003C/p>\n\u003Cblockquote>\n\u003Cp>“Fill the schema with insights from our last driving study.”\u003C/p>\n\u003C/blockquote>\n\u003Cp>The result stays valid and ready for version control.\u003C/p>\n\u003Chr>\n\u003Ch2 id=\"5-the-critique--rewrite-pattern\">\u003Ca href=\"#5-the-critique--rewrite-pattern\">5. The “Critique + Rewrite” Pattern\u003C/a>\u003C/h2>\n\u003Cp>Used for academic drafts and UX copy reviews.\u003C/p>\n\u003Cblockquote>\n\u003Cp>You are a senior editor.\u003C/p>\n\u003Col>\n\u003Cli>Critique the following text in 3 bullet points.\u003C/li>\n\u003Cli>Then rewrite it for clarity and flow.\u003C/li>\n\u003C/ol>\n\u003C/blockquote>\n\u003Cp>This ensures we keep both diagnostic and prescriptive outputs.\u003C/p>\n\u003Chr>\n\u003Ch2 id=\"6-the-simulation-prompt\">\u003Ca href=\"#6-the-simulation-prompt\">6. The Simulation Prompt\u003C/a>\u003C/h2>\n\u003Cp>We simulate human behavior for multimodal systems.\u003Cbr>\nIt’s structured like a screenplay:\u003C/p>\n\u003Cpre>\u003Ccode class=\"language-text\">ROLE: Driver\r\nCONTEXT: Rainy day, low visibility\r\nEMOTION: Frustrated\r\nACTION: Misses a traffic sign and sighs\r\nRESPONSE (System): Gentle haptic vibration + calming voice cue\n\u003C/code>\u003C/pre>\n\u003Cp>Such pseudo-scripts drive data augmentation for Emotion Agent.\u003C/p>\n\u003Chr>\n\u003Ch2 id=\"7-the-ifthen-meta-prompt\">\u003Ca href=\"#7-the-ifthen-meta-prompt\">7. The “If–Then” Meta Prompt\u003C/a>\u003C/h2>\n\u003Cp>Meta prompts guide smaller prompts dynamically.\u003C/p>\n\u003Cpre>\u003Ccode class=\"language-python\">if \"data\" in user_task:\r\n    model_role = \"data analyst\"\r\nelif \"design\" in user_task:\r\n    model_role = \"UX designer\"\r\nelse:\r\n    model_role = \"general assistant\"\n\u003C/code>\u003C/pre>\n\u003Cp>We embed this logic in our internal LLM orchestrator to match tone and expertise per task.\u003C/p>\n\u003Chr>\n\u003Ch2 id=\"8-the-context-memory-trick\">\u003Ca href=\"#8-the-context-memory-trick\">8. The Context Memory Trick\u003C/a>\u003C/h2>\n\u003Cp>LLMs forget easily. To maintain continuity:\u003C/p>\n\u003Cblockquote>\n\u003Cp>“You are continuing from the previous session. Recall our last summary on multimodal input fusion. Do not reintroduce context; build upon it.”\u003C/p>\n\u003C/blockquote>\n\u003Cp>This mimics working memory — essential in iterative design reviews.\u003C/p>\n\u003Chr>\n\u003Ch2 id=\"9-tables-lists-and-checkboxes\">\u003Ca href=\"#9-tables-lists-and-checkboxes\">9. Tables, Lists, and Checkboxes\u003C/a>\u003C/h2>\n\u003Cp>Even in conversational design, structure improves reasoning.\u003C/p>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Pattern\u003C/th>\n\u003Cth>Used For\u003C/th>\n\u003Cth>Example Output\u003C/th>\n\u003C/tr>\n\u003C/thead>\n\u003Ctbody>\n\u003Ctr>\n\u003Ctd>Table\u003C/td>\n\u003Ctd>Comparative summaries\u003C/td>\n\u003Ctd>Emotion model metrics\u003C/td>\n\u003C/tr>\n\u003Ctr>\n\u003Ctd>Checklist\u003C/td>\n\u003Ctd>Task breakdowns\u003C/td>\n\u003Ctd>✅ Collect data ✅ Preprocess ✅ Train\u003C/td>\n\u003C/tr>\n\u003Ctr>\n\u003Ctd>List\u003C/td>\n\u003Ctd>Brainstorming\u003C/td>\n\u003Ctd>1. Audio cues 2. Haptic responses\u003C/td>\n\u003C/tr>\n\u003C/tbody>\n\u003C/table>\n\u003Chr>\n\u003Ch2 id=\"10-embedding-references\">\u003Ca href=\"#10-embedding-references\">10. Embedding References\u003C/a>\u003C/h2>\n\u003Cp>We often reference connected projects directly in text:\u003C/p>\n\u003Cblockquote>\n\u003Cp>Our iterative prompting approach evolved from our 2024 CHI paper, later tested in Emotion Agent.\u003Cbr>\nFurther teaching materials appear in prompting-ws25.\u003C/p>\n\u003C/blockquote>\n\u003Chr>\n\u003Ch2 id=\"example-image\">\u003Ca href=\"#example-image\">Example Image\u003C/a>\u003C/h2>\n\u003Cp>\u003Cimg src=\"/_app/immutable/assets/diagram.kostgB6-.png\" alt=\"Prompt evolution diagram\" width=\"1376\" height=\"786\" loading=\"lazy\" decoding=\"async\">\r\n\u003Cem>Figure 1: Prompt structures evolving over time.\u003C/em>\u003C/p>\n\u003Cp>\u003Cimg src=\"/_app/immutable/assets/default-profile.BX96yRDd.png\" alt=\"Default Profile Image\" width=\"1024\" height=\"1024\" loading=\"lazy\" decoding=\"async\">\r\n\u003Cem>Figure 2: Relative path.\u003C/em>\u003C/p>\n\u003Cp>\u003Cimg src=\"/_app/immutable/assets/cover.C8PKuPSV.png\" alt=\"Prompt engineering workflow\" width=\"1670\" height=\"1238\" loading=\"lazy\" decoding=\"async\">\r\n\u003Cem>Figure 3: Relative path.\u003C/em>\u003C/p>\n\u003Chr>\n\u003Ch2 id=\"footnotes\">\u003Ca href=\"#footnotes\">Footnotes\u003C/a>\u003C/h2>\n\u003Col>\n\u003Cli>Prompt failure rate decreases ~40% after introducing schema-based output.\u003C/li>\n\u003Cli>Using meta-prompts for reflection yields 1.6× higher factual consistency.\u003C/li>\n\u003C/ol>\n\u003Chr>\n\u003Ch2 id=\"conclusion\">\u003Ca href=\"#conclusion\">Conclusion\u003C/a>\u003C/h2>\n\u003Cp>The best prompts are not clever — they are \u003Cstrong>repeatable\u003C/strong>.\u003Cbr>\nWe’ve learned that \u003Cstrong>structure beats intuition\u003C/strong> and \u003Cstrong>clarity scales better than creativity\u003C/strong>.\u003C/p>\n\u003Cp>When your prompts start reading like documentation, that’s when you know you’re doing it right.\u003C/p>\n\u003Chr>\n\u003Ch3 id=\"resources\">\u003Ca href=\"#resources\">Resources\u003C/a>\u003C/h3>\n\u003Cul>\n\u003Cli>\u003Ca href=\"https://www.promptingguide.ai\" rel=\"noopener noreferrer\" target=\"_blank\">Prompt Engineering Guide\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"https://www.anthropic.com/prompt-library\" rel=\"noopener noreferrer\" target=\"_blank\">Anthropic Prompt Library\u003C/a>\u003C/li>\n\u003Cli>\u003Ca href=\"https://github.com/openai/openai-cookbook\" rel=\"noopener noreferrer\" target=\"_blank\">OpenAI Cookbook\u003C/a>\u003C/li>\n\u003C/ul>\n\u003Chr>\n\u003Cblockquote>\n\u003Cp>\u003Cem>“The goal isn’t to write perfect prompts. It’s to build systems that don’t need perfect prompts.”\u003C/em>\u003C/p>\n\u003C/blockquote>\n\u003Chr>",{"slug":213,"title":188,"subtitle":237,"authors":238,"external_authors":239,"tags":240,"category":224,"description":242,"cover":226,"attachments":243,"updatedAt":51,"publishedAt":234,"isPublished":24,"html":235},"From chaos to clarity: how structured prompting evolved in our daily workflows",[2],[218],[121,221,241,223],"LLM Research","A deep dive into the practical prompt patterns used in our lab — the real ones that survive daily iteration, debugging, and deployment.",[244,245],{"label":182,"url":230},{"label":246,"url":233},"Slide deck",{"slug":248,"title":249,"authors":250,"external_authors":251,"tags":252,"category":177,"description":253,"cover":179,"attachments":254,"updatedAt":51,"publishedAt":257,"isPublished":24,"html":258},"swiftui-prototyping-tips","SwiftUI Prototyping Tips for Researchers",[90,2],[],[49,176],"Patterns that scale from demo to study.",[255],{"label":182,"url":256},"/blog/swiftui-prototyping-tips/swiftui-prototyping-tips.pdf","2025-09-28","\u003Ch2 id=\"blog-content\">\u003Ca href=\"#blog-content\">Blog Content\u003C/a>\u003C/h2>\n\u003Cp>Updates from the field related to [budget-app].\u003C/p>\n\u003Ch3 id=\"citations-for-entities\">\u003Ca href=\"#citations-for-entities\">Citations for Entities\u003C/a>\u003C/h3>\n\u003Cp>We extended \u003Ca href=\"/research/projects/budget-app\" target=\"_self\">Budget\u003C/a> and referenced recent work.\u003C/p>",[260,287,294,302,329,347],{"slug":261,"title":262,"description":263,"key_topics":264,"type":270,"level":271,"code":272,"ects":65,"language":273,"instructors":274,"assistants":275,"period":276,"weekday":277,"time":278,"room":279,"duration_weeks":280,"capacity":281,"materials":282,"updatedAt":156,"isPublished":24,"html":286},"mock-applied-ux-research-lab-ss26","Applied UX Research Lab","Hands-on studio focusing on planning, running, and analyzing UX studies with real stakeholders.",[265,266,267,268,269],"UX Research in Practice","User Studies And Ethics","Qualitative Methods In HCI","Data Analysis Techniques","Stakeholder Engagement - Communication","lab","Master","UXD-672","EN",[69],[2],"SS26","Friday","10:00–13:00","Lab B",12,20,[283],{"label":284,"url":285},"Lab Handbook","/assets/teaching/aur-ss26/handbook.pdf","\u003Ch2 id=\"overview\">\u003Ca href=\"#overview\">Overview\u003C/a>\u003C/h2>\n\u003Cp>Hands-on studio focusing on planning, running, and analyzing UX studies with real stakeholders.\u003C/p>\n\u003Ch2 id=\"learning-outcomes\">\u003Ca href=\"#learning-outcomes\">Learning Outcomes\u003C/a>\u003C/h2>\n\u003Cul>\n\u003Cli>Translate stakeholder goals into testable questions\u003C/li>\n\u003Cli>Collect and analyze qualitative data reliably\u003C/li>\n\u003Cli>Communicate evidence to product teams\u003C/li>\n\u003C/ul>\n\u003Ch2 id=\"assessment\">\u003Ca href=\"#assessment\">Assessment\u003C/a>\u003C/h2>\n\u003Cp>Study plan (30%), field execution (40%), final report & presentation (30%)\u003C/p>\n\u003Ch2 id=\"schedule\">\u003Ca href=\"#schedule\">Schedule\u003C/a>\u003C/h2>\n\u003Cp>Weeks 1–4: Planning & ethics\u003Cbr>\nWeeks 5–8: Data collection\u003Cbr>\nWeeks 9–12: Analysis & reporting\u003C/p>",{"slug":288,"title":262,"description":263,"key_topics":289,"type":270,"level":271,"code":272,"ects":65,"language":273,"instructors":290,"assistants":291,"period":276,"weekday":277,"time":278,"room":279,"duration_weeks":280,"capacity":281,"materials":292,"updatedAt":156,"isPublished":24,"html":286},"mock-teaching-demo-2",[265,266,267,268,269],[69],[2],[293],{"label":284,"url":285},{"slug":295,"title":262,"description":263,"key_topics":296,"type":270,"level":271,"code":272,"ects":65,"language":273,"instructors":297,"assistants":298,"period":299,"weekday":277,"time":278,"room":279,"duration_weeks":280,"capacity":281,"materials":300,"updatedAt":156,"isPublished":24,"html":286},"mock-teaching-demo",[265,266,267,268,269],[69],[2],"WS2728",[301],{"label":284,"url":285},{"slug":303,"title":304,"description":305,"key_topics":306,"type":310,"level":271,"code":311,"ects":312,"language":273,"instructors":313,"assistants":314,"period":315,"weekday":316,"time":317,"room":318,"duration_weeks":319,"capacity":320,"materials":321,"updatedAt":51,"isPublished":24,"html":328},"automotive-hmi","Automotive HMI","Driver‑vehicle interaction, in‑cabin agents, and safety‑critical UX for AD/ADAS contexts.",[307,308,309],"Design","Prototyping","Evaluation","lecture","AHM101",5,[43,134],[2],"SS23","Tuesday","10:00–12:00","E0.18",14,30,[322,325],{"label":323,"url":324},"Syllabus (PDF)","/teaching/automotive-hmi/syllabus.pdf",{"label":326,"url":327},"Lecture Website","https://example.com/automotive-hmi/slides","\u003Ch2 id=\"overview\">\u003Ca href=\"#overview\">Overview\u003C/a>\u003C/h2>\n\u003Cp>Brief summary of the course, its learning objectives, and scope.\u003C/p>\n\u003Ch2 id=\"learning-outcomes\">\u003Ca href=\"#learning-outcomes\">Learning Outcomes\u003C/a>\u003C/h2>\n\u003Cul>\n\u003Cli>Apply methods\u003C/li>\n\u003Cli>Build prototypes\u003C/li>\n\u003Cli>Evaluate UX at scale\u003C/li>\n\u003C/ul>\n\u003Ch2 id=\"assessment\">\u003Ca href=\"#assessment\">Assessment\u003C/a>\u003C/h2>\n\u003Cp>Projects, lab assignments, and a final presentation.\u003C/p>\n\u003Ch2 id=\"schedule\">\u003Ca href=\"#schedule\">Schedule\u003C/a>\u003C/h2>\n\u003Cp>Week‑by‑week labs and critiques.\u003C/p>",{"slug":330,"title":331,"description":332,"key_topics":333,"type":334,"level":271,"code":335,"ects":65,"language":273,"instructors":336,"assistants":337,"period":276,"weekday":338,"time":339,"room":340,"duration_weeks":319,"capacity":341,"materials":342,"updatedAt":51,"isPublished":24,"html":328},"data-visualization","Data Visualization for HCI","Narrative visualization, dashboards, and evaluation for decision‑making.",[307,308,309],"seminar","DVHCI01",[90,2],[69],"Thursday","14:00–16:00","E1.12",40,[343,345],{"label":323,"url":344},"/teaching/data-visualization/syllabus.pdf",{"label":326,"url":346},"https://example.com/data-visualization/slides",{"slug":348,"title":349,"description":350,"type":310,"level":271,"code":351,"ects":312,"language":273,"instructors":352,"assistants":354,"period":356,"weekday":316,"time":339,"room":318,"duration_weeks":319,"capacity":320,"materials":357,"updatedAt":156,"isPublished":24,"html":362},"mock-multimodal-interactive-systems-ws25","Multimodal Interactive Systems","Graduate introduction to designing and evaluating systems that combine speech, vision, haptics, and context data.","UXD-541",[2,353,69],"prof-jane-smith",[355],"hcis-research-team","WS2526",[358,360],{"label":323,"url":359},"/assets/teaching/mis-ws25/syllabus.pdf",{"label":326,"url":361},"https://example.com/mis","\u003Ch2 id=\"overview\">\u003Ca href=\"#overview\">Overview\u003C/a>\u003C/h2>\n\u003Cp>Graduate introduction to designing and evaluating systems that combine speech, vision, haptics, and context data.\u003C/p>\n\u003Ch2 id=\"learning-outcomes\">\u003Ca href=\"#learning-outcomes\">Learning Outcomes\u003C/a>\u003C/h2>\n\u003Cul>\n\u003Cli>Explain trade-offs of multimodal fusion\u003C/li>\n\u003Cli>Design low-distraction feedback for safety-critical contexts\u003C/li>\n\u003Cli>Run and analyze small simulator studies\u003C/li>\n\u003C/ul>\n\u003Ch2 id=\"assessment\">\u003Ca href=\"#assessment\">Assessment\u003C/a>\u003C/h2>\n\u003Cp>Project (50%), weekly labs (30%), reflection (20%)\u003C/p>\n\u003Ch2 id=\"schedule\">\u003Ca href=\"#schedule\">Schedule\u003C/a>\u003C/h2>\n\u003Cp>Weeks 1–3: Sensing & synchronization\u003Cbr>\nWeeks 4–7: Fusion & feedback\u003Cbr>\nWeeks 8–14: Team project + study\u003C/p>"],"uses":{"params":["slug"]}}]}