Sub-Saharan Africa has long faced extreme teacher-to-student ratios. A single science teacher may face over a hundred students, making personalized feedback impossible. But sending a WhatsApp message? That's easy. WhatsApp penetration in West Africa is extremely high—nearly every student and parent uses it. Adesua, developed by Boateng, Atompoya, and their team, is an AI science tutor built on WhatsApp.
The technical stack is not complex: the backend integrates curriculum standards and a 33-year archive of national exam questions, while the frontend interacts with students through a WhatsApp bot interface. A student sends a message like "explain photosynthesis," and the AI retrieves relevant textbook content and generates an answer. Students can also take multiple-choice quizzes, scheduled or on-demand, by topic or by year—submitting answers triggers instant scoring with explanations for every question.
This simplicity may actually be a strength. In resource-constrained regions, there's no app store visit, no account registration, no extra data plan needed—WhatsApp traffic is free, and messaging is an interaction pattern students already know. That means zero deployment friction.
The feasibility study ran for 6 months with 56 active users (including students and parents). AI-generated answers received a helpfulness rating of 93.75%—but from only 16 ratings, a very small sample. The number is preliminary and fragile, yet it provides a starting point for larger-scale research.
An interesting angle: Adesua shares a design philosophy with Eskwai (another paper from the same group at the same venue)—build AI education on the communication infrastructure students already have, rather than requiring them to adapt to a new platform first. A WhatsApp bot is more likely to be genuinely used than a standalone education app, simply because it doesn't require changing user habits.
Unclear points: with 56 active users over 6 months, is that retention high or low in real-world terms? The 93.75% helpfulness rating rests on just 16 rating samples, with limited statistical significance. There's no rigorous evaluation of answer accuracy—could the AI feed incorrect scientific knowledge to West African secondary students? And has the exam-question bank been human-verified?
References
1. Boateng, G., Atompoya, E., Badu, P., et al. (2026). *Adesua: Development and Feasibility Study of an AI WhatsApp Bot for Science Learning in West Africa*. arXiv:2605.15376 [cs.CL].
2. Boateng, G., et al. (2024). *Kwame for Science: A Learning and Assessment Platform for Science Education in Africa*. AIED.
3. UNESCO. (2023). *Technology in Education: A Tool on Whose Terms?* Global Education Monitoring Report.