Bridging UX and AI: Why Fullstack Applications are the Future of Custom LLM Pipelines
Keywords:
LLM Pipelines, UX, Full-Stack Applications, AIAbstract
As artificial intelligence (AI) systems mature, the integration of user experience (UX) principles into large language model (LLM) pipelines has become essential to ensuring usability, trust, and efficiency. Traditional LLM deployments—often focused solely on back-end processing—have faced persistent challenges, including excessive prompt debugging, low user confidence, and poor workflow coherence. This paper presents a paradigm shift toward full-stack LLM applications, where advanced back-end intelligence is seamlessly coupled with intuitive, human-centered front-end design. Through simulation-based evaluations using key UX metrics such as the System Usability Score (SUS), Task Success Rate (TSR), and Trust Index, our findings demonstrate substantial gains: a 29.3% reduction in prompt debugging time, an average SUS of 88.7, and a 50% improvement in deployment speed. These results highlight how a UX-first, full-stack approach can reduce developer bottlenecks, promote prompt reusability, and increase organizational trust in AI outputs. Rather than functioning as isolated tools, such systems evolve into adaptive, transparent, and co-creative platforms—aligning AI capabilities with the expectations and operational realities of diverse user groups. This research makes the case for embedding UX as a foundational element in the design, rollout, and scaling of LLM solutions.
Downloads
References
Strobelt, H., Gehrmann, S., Behrisch, M., Perer, A., Pfister, H., & Rush, A. M. (2018). Seq2Seq-Vis: a visual debugging tool for Sequence-to-Sequence models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1804.09299
Jiang, Z., Xu, F. F., Gao, L., Sun, Z., Liu, Q., Dwivedi-Yu, J., Yang, Y., Callan, J., & Neubig, G. (2023). Active Retrieval Augmented generation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2305.06983
Vukovac, D. P., Horvat, A., & Čižmešija, A. (2021). Usability and User Experience of a Chat Application with Integrated Educational Chatbot Functionalities. In Lecture notes in computer science (pp. 216–229). https://doi.org/10.1007/978-3-030-77943-6_14
Wu, T., Jiang, E., Donsbach, A., Gray, J., Molina, A., Terry, M., & Cai, C. J. (2022). PromptChainer: Chaining Large Language Model Prompts through Visual Programming. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2203.06566
Huo, S., Arabzadeh, N., & Clarke, C. (2023, November). Retrieving supporting evidence for generative question answering. In Proceedings of the annual international acm sigir conference on research and development in information retrieval in the Asia Pacific region (pp. 11-20). https://doi.org/10.48550/arXiv.2309.11392
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP tasks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2005.11401
Kamalloo, E., Dziri, N., Clarke, C. L. A., & Rafiei, D. (2023). Evaluating Open-Domain question answering in the era of large language models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2305.06984
Shao, Z., Gong, Y., Shen, Y., Huang, M., Duan, N., & Chen, W. (2023). Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2305.15294
Thulke, D., Daheim, N., Dugast, C., & Ney, H. (2021). Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2102.04643
Siriwardhana, S., Weerasekera, R., Wen, E., Kaluarachchi, T., Rana, R., & Nanayakkara, S. (2022). Improving the domain adaptation of Retrieval Augmented Generation (RAG) models for open domain question answering. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2210.02627
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
