Copyright (c) 2026 REICIT
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Data analysis in university physics laboratories often relies on proprietary software, limiting reproducibility, transparency, and adaptability across different experimental contexts. The objective of this study is to present an open computational workflow based on Python and assisted by generative artificial intelligence tools for the analysis and visualization of experimental data in physics laboratory courses. The proposal is implemented through a multifunctional open-source script, developed with the support of generative AI for iterative code construction and debugging, ensuring full traceability of computational processes. The workflow integrates data acquisition, statistical analysis, and high-resolution visualization within a reproducible environment. Its technical feasibility is evaluated through three representative laboratory experiences, including regression analysis, descriptive statistics, and electric field mapping. The results show that the proposed tool can replace proprietary software without significant loss in analytical accuracy or visualization quality. It is concluded that the use of open workflows assisted by generative artificial intelligence constitutes a flexible, reproducible, and extensible alternative for computational data processing in physics education across different experimental contexts
Este obra está bajo una licencia de Creative Commons Reconocimiento-NoComercial-CompartirIgual 4.0 Internacional.
