Search papers, labs, and topics across Lattice.
Kwame 2.0, a bilingual (English-French) generative AI teaching assistant, was developed using retrieval-augmented generation to provide context-aware support in a mobile-based coding course across Africa. A 15-month longitudinal study with 3,717 enrollments showed that Kwame 2.0 delivered high-quality and timely support for curriculum-related questions. Human facilitators effectively addressed administrative queries and mitigated errors, demonstrating the potential of human-in-the-loop AI for scalable learning assistance in resource-constrained environments.
A human-in-the-loop AI assistant can provide scalable, high-quality coding education support in resource-constrained African contexts, even with limited infrastructure.
Providing timely and accurate learning support in large-scale online coding courses is challenging, particularly in resource-constrained contexts. We present Kwame 2.0, a bilingual (English-French) generative AI teaching assistant built using retrieval-augmented generation and deployed in a human-in-the-loop forum within SuaCode, an introductory mobile-based coding course for learners across Africa. Kwame 2.0 retrieves relevant course materials and generates context-aware responses while encouraging human oversight and community participation. We deployed the system in a 15-month longitudinal study spanning 15 cohorts with 3,717 enrollments across 35 African countries. Evaluation using community feedback and expert ratings shows that Kwame 2.0 provided high-quality and timely support, achieving high accuracy on curriculum-related questions, while human facilitators and peers effectively mitigated errors, particularly for administrative queries. Our findings demonstrate that human-in-the-loop generative AI systems can combine the scalability and speed of AI with the reliability of human support, offering an effective approach to learning assistance for underrepresented populations in resource-constrained settings at scale.
