This paper presents the automated design and optimization of a compact circular microstrip patch antenna for C-band applications using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Microstrip patch antennas inherently suffer from narrow impedance bandwidth, making systematic optimization essential for wideband wireless applications. The antenna is implemented on an FR4 substrate (24 × 24 mm2, εr = 4.4, h = 1.6 mm) and optimized through ANSYS HFSS using the PyAEDT Python interface. Three key design parameters were tuned to enhance impedance bandwidth and minimize return loss GA achieved the best performance among the considered optimization methods, with an optimized bandwidth of 3.74 GHz and a minimum S11 of –37 dB, while the optimized PSO method reduced computation time by approximately 49% compared to manual tuning and 31% compared to GA. The final optimized design exhibits consistent gain performance (2.3–2.8 dB) and stable radiation patterns across the operational band, confirming reliable C-band operation. The results demonstrate that metaheuristic optimization integrated with HFSS automation provides a powerful and efficient antenna design framework, which can be extended toward hybrid algorithms and intelligent machine-learning-assisted antenna prediction models.