Automation of electrochemical methods is crucial to achieve high-throughput experimentation (HTE) and self-driving laboratories (SDLs) for accelerating chemistry and materials engineering on pressing research challenges. Obtaining reproducible and reliable electrochemical results requires frequent monitoring of the experimental apparatus, particularly the surface condition of the electrodes. Here, a rapid surface evaluation method that combines optical macro imaging with machine learning (ML) is investigated. We demonstrated that the degradation of a glassy-carbon (GC) electrode can be quantified using only an optical image. This approach enables easily automatable, non-intrusive, and rapid monitoring of electrode health without significantly increasing the complexity of the experimental setup, while also providing spatially resolved insights into degradation.