Kwame 2.0: Human-in-the-Loop Generative AI Teaching Assistant for Large Scale Online Coding Education in Africa

TL;DR

Kwame 2.0 is a bilingual AI teaching assistant for large-scale online coding courses in Africa, combining retrieval-augmented generation with human oversight to provide accurate, context-aware support.

Contribution

This paper introduces Kwame 2.0, a novel human-in-the-loop generative AI system tailored for resource-constrained, multilingual online coding education in Africa.

Findings

High accuracy in curriculum-related questions

Effective mitigation of errors through human oversight

Positive community feedback and expert ratings

Abstract

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.