Urinalysis is a noninvasive clinical chemistry method that is essential for human diagnosis. It is one of the most convenient body fluids that can be regularly monitored. Parameters such as urea (UR), uric acid (UA), creatinine (CRE), total protein (TP), and amylase (AMY) are commonly used in urinalysis. Urine analysis is now commonly performed at the point-of-care of test strips using colorimetric reactions. Similar reactions are used in the wet-lab approach in the clinical pathology laboratory. Spectral Point-of-Care can eliminate the use of reagents, allowing simple, fast, and consumable-free measurements. Herein, we present a case study of urinalysis using ultraviolet, visible, and near-infrared spectroscopy to relate spectral information to urine composition using self-learning artificial intelligence. This preliminary study demonstrated the capacity for direct detection of UR, CRE, TP, and AMY. These parameters were determined with significant statistical agreement in terms of correlation (R) and total error (TE) with the ground-truth methods used in the clinical pathology laboratory, where i. UR: R=0.79 and TE=15.5%; ii. UA: R=0.82 and TE=25.1%; iii. CRE: R=0.77 and TE=24.6%; iii. TP: R=0.74 and TE=25%; and iv. AMY: R=0.9 and TE=14.5%. These results demonstrate the possibility of performing clinical chemistry on urine without any reagents. Further research is necessary to enhance the detection of constituents with lower absorbance and expand the range of parameters investigated to develop a system that can perform urinalysis with a drop of urine.