NEXUS: A Visual Low-Code Platform for Designing, Executing, and Deploying AI Automation Pipelines

This article introduced NEXUS, which is a low-code solution that utilizes visual components for the creation, use, and observation of AI automation pipelines using a user-friendly node-centered platform. The platform utilizes direct acyclic graphs (DAGs) to structure its procedures, ensure the correctness of the architecture before its usage, and visualize the functions of each node in real time for the purpose of easing the usage of inexperienced and educational users. Parts IV and V of the paper offer detailed information on the architecture of the system, its procedures along with the components of the platform and the methods for control of DAG structures and timings. The directions for the future work include the implementation of the tools mentioned in Section VI and conducting the benchmarks РQ1-RQ4 for the finalization of the Results chapter of the current paper. Furthermore, future work will involve the implementation of comparisons between visual and coding workflows and pre- and post-tests regarding the education effectiveness.

[1] R. Du, N. Li, J. Jin, M. Carney, S. Miles, M. Kleiner, X. Yuan, Y. Zhang, A. Kulkarni, X. Liu, A. Sabie, S. Orts-Escolano, A. Kar, P. Yu, R. Iyengar, A. Kowdle and A. Olwal, "Rapsai: Accelerating machine learning prototyping of multimedia applications through visual programming," in Proc. of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ‘23), 2023, Article Number 125, doi: 10.1145/3544548.3581338. [2] Z. Zhou, J. Jin, V. Phadnis, X. Yuan, J. Jiang, X. Qian, J. Zhou, Y. Huang, Z. Xu, Y. Zhang, K. Wright, J. Mayes, M. Sherwood, J. Lee, A. Olwal, D. Kim, R. Iyengar, N. Li and R. Du, "InstructPipe: Generating visual blocks pipelines with human instructions and LLMs," in Proc. of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ‘25), 2025, doi: 10.1145/3706598.3713905. [3] H. An, Y. Kim, W. Seo, J. Park, D. Kang, C. Oh, D. Kim and S. Lee, "AIAP: A no-code workflow builder for non-experts with natural language and multi-agent collaboration," arXiv:2508.02470, 2025. [4] Y. Ye, X. Cong, S. Tian, J. Cao, H. Wang, Y. Qin, Y. Lu, H. Yu, H. Wang, Y. Lin, Z. Liu and M. Sun, "ProAgent: From robotic process automation to agentic process automation," arXiv:2311.10751, 2023. [5] A. Grilo, P. Figueiras, B. Rêga, L. Lourenço, A. Khodamoradi, R. Costa, and R. Jardim-Gonçalves, "Data analytics environment: Combining visual programming and MLOps for AI workflow creation," in Proc. 2024 IEEE Int. Conf. Eng., Technol., Innov. (ICE/ITMC), 2024, pp. 1-9, doi: 10.1109/ICE/ITMC61926.2024.10794244. [6] Y. I. Rogozov, V. S. Lapshin, and M. A. Borovskaya, "Approach to the implementation of intelligent low-code platforms," in Proc. Int. Conf. Intell. Inf. Technol. Ind., Cham: Springer, 2022, pp. 42-50, doi: 10.1007/978-3-031-19620-1_5. [7] J. Martins, F. Branco, and H. Mamede, "Combining low-code development with ChatGPT to novel no-code approaches: A focus-group study," Intell. Syst. Appl., vol. 20, Art. no. 200289, 2023. [8] L. Sundberg and J. Holmström, "Democratizing artificial intelligence: How no-code AI can leverage machine learning operations," Bus. Horizons, vol. 66, no. 6, pp. 777-788, 2023. [9] M. Truss and M. Schmitt, "Human-centered AI product prototyping with no-code AutoML: Conceptual framework, potentials and limitations," Int. J. Human-Comput. Interact., 2024. [10] I. Weber, "Feasibility of AI-assisted programming for end-user development," preprint, accepted for NLPIR 2025.