Individualized learning support is an essential part of formal educational learning processes. However, in typical large-scale educational settings, resource constraints result in limited interaction among students, teaching assistants, and lecturers. Due to this, learning success in those settings may suffer. Inspired by current technological advances, we transfer the concept of chatbots to formal educational settings to support not only a single task but a full lecture period. Grounded on an expert workshop and prior research, we design a natural language-based digital tutor acting as an intermediary among students, teaching assistants, and lecturers. The aim of the digital tutor is to support learners automated during the lecture period in natural language-based chat conversations. We implement a digital tutor in an iterative design process and evaluate it extensively in a large-scale field setting. The results demonstrate the applicability and beneficial support of introducing digital tutors as intermediaries in formal education. Our study proposes the concept of using digital tutors as intermediaries and documents the development and underlying principles.