A recent article presents a novel Bayesian tensor regression model aimed at improving phenotype prediction by effectively handling multiple factors in multi-environmental trials. The model incorporates a distinctive set of prior distributions to address potential identifiability issues that can arise in such complex analyses. Additionally, it employs a spike-and-slab structure designed to identify relevant interactions within the linear predictor, enhancing interpretability and model precision. This approach is particularly relevant for applications involving the analysis of genotype-by-environment interactions, where capturing both main effects and multiplicative interactions is crucial. The proposed methodology reflects ongoing advancements in statistical modeling techniques for biological data, offering a promising tool for researchers working on phenotype prediction across diverse environmental conditions. The integration of these features suggests a comprehensive framework that balances model complexity with interpretability. Overall, this Bayesian additive main effects and multiplicative interaction model represents a significant contribution to the field of multi-environmental trial analysis.