This paper introduces a new human-based metaheuristic algorithm called Sewing Training-Based Optimization (STBO). The fundamental inspiration of STBO is the process of teaching sewing to beginner tailors. The process is described in three phases: (i) training, (ii) imitation of the instructor's skills, and (iii) practice, and is then mathematically modeled. STBO performance is evaluated on twenty-three objective functions of the types of unimodal, high-dimensional multimodal, and fixed-dimensional multimodal. The optimization results show that STBO, with its high power of exploration and exploitation, has provided suitable solutions for benchmark functions. Also, to evaluate the quality of STBO, the results are compared with ten well-known metaheuristic algorithms. Furthermore, the simulation results show that STBO has a much more competitive performance than competitor algorithms by providing superior results. Finally, the implementation of STBO in solving four engineering design problems demonstrates the capability of the proposed approach in dealing with real-world applications.