A Methodology for Prompt Engineering in Engineering: Framework Development and Performance Evaluation

Show simple item record
dc.contributor.authordos Santos, Valeria Vieira
dc.contributor.authorMalaga, Miroslav
dc.contributor.editorMalaga, Miroslav
dc.contributor.editorBroum, Tomáš
dc.date.accessioned2025-11-29T12:08:24Z
dc.date.available2025-11-29T12:08:24Z
dc.date.issued2025
dc.description.abstract-translatedThe growing integration of Artificial Intelligence in engineering faces the challenge of response effectiveness and dependence on the quality of user prompts. This article addresses this issue by introducing a systematic framework for prompt engineering, composed of five essential elements: specificity, contextualization, formatting, audience alignment, and constraint definition. The methodology validated the framework through case studies and a comparative evaluation of four LLMs (ChatGPT, DeepSeek, Gemini, MetaAI). The results demonstrate that structured prompts increase output accuracy and reveal significant performance differences among models, with ChatGPT and DeepSeek showing superiority in conceptual tasks. It is concluded that prompt engineering is a fundamental competence, and its maximum effectiveness is achieved through a robust methodology and the careful selection of the AI model, ensuring greater reliability in technical applications.en
dc.description.sponsorshipThis contribution was prepared with the support of the SGS-2025-026 project entitled “Artificial intelligence algorithms in sustainable manufacturing”, financed by the Ministry of Education, Youth and Sports of the Czech Republic.en
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.doihttps://doi.org/10.24132/PI.2025.13287.169-178
dc.identifier.isbn978-80-261-1328-7
dc.identifier.urihttp://hdl.handle.net/11025/64177
dc.publisherZápadočeská univerzita v Plznics
dc.rights© autoři © Západočeská univerzita v Plznics
dc.subjectumělá inteligencecs
dc.subjectuživatelské výzvycs
dc.subjectinženýrstvícs
dc.subject.translatedartificial intelligenceen
dc.subject.translateduser promptsen
dc.subject.translatedengineeringen
dc.titleA Methodology for Prompt Engineering in Engineering: Framework Development and Performance Evaluationen
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.type.statusPeer revieweden
dc.type.versionpublishedVersionen
local.files.count2*
local.files.size1140295*
local.has.filesyes*

Files

Original bundle
Showing 1 - 2 out of 2 results
No Thumbnail Available
Name:
978-80-261-1328-7-175-184.pdf
Size:
327.38 KB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
978-80-261-1328-7-uvod.pdf
Size:
786.19 KB
Format:
Adobe Portable Document Format
Download
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Průmyslové inženýrství 2025
Průmyslové inženýrství 2025