An artificial intelligence system generated highly accurate preliminary interpretations of urine drug tests and reduced laboratory sign-out time when integrated into routine clinical practice. Researchers developed and evaluated the workflow using 83,553 urine drug tests from 26,459 patients performed at the University of Washington Medical Center between January 2014 and February 2024. Large language models extracted structured substance-use labels from historical interpretations, which trained machine learning models to predict substance use from immunoassay and mass spectrometry results. The LLM correctly extracted 99.9% of substance-use labels. Machine learning models predicted substance use with an area under the receiver operating characteristic curve greater than 0.99 for 23 of 26 substances, and prediction accuracy exceeded 94% for every substance. Model performance remained consistent across major demographic subgroups, with no subgroup area under the receiver operating characteristic curve below 0.97. The AI tool reduced average sign-out time by 28.5 seconds per case, a 23% efficiency gain; combined with an automated medication-list import feature, average sign-out time decreased by 65 seconds per case, a 51% efficiency gain. Among 198 AI-generated preliminary interpretations, 70% required no substantive changes and 16% required only minor grammatical edits. Incorrect substance-use classification prompted overrides in 4% of cases. Following deployment, three of four laboratory readers used the AI interpreter for more than two-thirds of eligible cases.