New Curriculum, New Chance – Retrieval Augmented Generation for Lesson Planning in Ugandan Secondary Schools

Poor educational quality in Secondary Schools is a major struggle in 21st century Uganda. Research identifies several problems, including low-quality or absent teacher lesson planning. Applying Retrieval Augmented Generation, we developed a prototype that generates customized lesson plans based on government-accredited textbooks. This helps teachers create lesson plans more efficiently and with better quality, ensuring they fully align the new curriculum and the competence-based learning approach. Using the prototype, 24 lesson plans were generated following a pseudo-random generation protocol and analysed regarding their technical quality by three independent raters following the Lesson Plan Analysis Protocol (LPAP) by Ndihokubwayo et al. (2022). Evaluation resulted in an average quality of between 75 and 80%, corresponding to “very good lesson plan”. None of the lesson plans scored below 65%, although one lesson plan could be argued to have been missing the topic. In conclusion, the quality of the generated lesson plans is comparable to or better than those created by humans, as demonstrated in a study in Rwanda, whereby no lesson plan reached the benchmark of 50%. Based on the prototype's success, the study recommends further exploring the use of RAG in this problem domain.