This paper presents the implementation of Generative Artificial Intelligence (GAI) for providing descriptive feedback on 578 responses to pedagogical cases written by a cohort of students (n = 347) from seven initial teacher education programs at a Faculty of Education in Chile. To deliver feedback on these responses, a process called RECaP-GPT was developed, which incorporates human action and utilizes ChatGPT-4 as a teaching support tool. The feedback provided is based on pre-established criteria known to the students. The feedback generated by the GAI was validated and delivered to the students to enhance their evidence of learning throughout a semester of classes. The paper discusses the capacity of this tool to offer formative and extensive feedback on students' written work in a short period of time. Furthermore, it raises limitations observed in the implementation process that necessitate further research.