Cutaneous squamous cell carcinoma (cSCC) is the second most common type of skin cancer and, according to recent data from Europe, has possibly overtaken melanoma as the leading cause of skin cancer–related death.^1,2 Accurate data from the US remain elusive, limiting the ability to conduct large-scale analyses of cSCC. Much of the issue lies in assembling a complete clinical record for individual patients and in processing text from notes and pathology reports into a usable format. The ability of large language models to do these tasks holds great promise to capture more of the patient record in the near future and provide highly granular data.^3,4 Even once there is better integration of these tools, new approaches to provide high-quality data are necessary as it is painfully evident that methods relying on International Classification of Disease codes alone are poor at identifying distinct skin cancers, let alone differentiating basal cell carcinoma from cSCC.⁵