| Sumario: | Smallholder farmers form the backbone of African food systems, yet they face persistent yield gaps driven by blanket recommendations, soil fertility decline, climate variability, and limited access to timely, context‑specific agronomic advice (Liben et al., 2024). Traditional extension systems struggle to meet demand due to high farmer‑to‑agent ratios, logistical constraints, and resource limitations (African Union, 2024). As a result, many farmers rely on generalized or outdated guidance that does not reflect local agro‑ecological or socio‑economic realities. AgWise was developed as a modular, data‑driven agronomic decision‑support platform to address these challenges (Excellence in Agronomy, 2024). By integrating spatial soil, climate, and topographic data with crop models and machine‑learning algorithms, AgWise delivers tailored recommendations on fertilizer rates, planting dates, cultivar choice, and soil health management. Deployments in Ethiopia, Kenya, Rwanda, and other countries have already demonstrated yield gains of up to 30 percent for selected crops (Liben et al., 2024; CGIAR, 2025). To further enhance inclusivity, adaptability, and scalability, AgWise is now being transformed through the integration of artificial intelligence. This transition represents a shift from a primarily static decision‑support system to a dynamic, interactive, and farmer‑centered advisory platform. The present report documents this transformation and situates AgWise within ongoing efforts to advance sustainable agricultural practices in Africa through responsible and participatory AI (Sahoo & Jena, 2025).
|
|---|