The properties of sputtered thin films are highly dependent on the conditions during the deposition process. The plasma emission spectra can be used to continuously observe the composition and energy levels of different species in the plasma and thus the (energetic) growth conditions for the resulting films. This demonstrator presents an AI-driven approach to predict the plasma emission spectra in sputtering processes based on key machine-specific process parameters - such as power, or pressure. Built as an interactive browser application, the tool allows to adjust these parameters and instantly predicts the corresponding plasma spectrum. Additionally, spectra are colour-coded with elements and their various excitation states, enabling users to visualize how changes in process conditions affect plasma composition and emission characteristics. The underlying AI model is trained on experimental data from the DigiMatUS project, integrating standardized process and spectral data across the thin-film process chain. By linking process parameters to plasma diagnostics, the demonstrator enhances understanding of plasma behavior as basis of film growth and facilitates data-driven decision-making in industrial sputtering environments.