HOW FARMERS IN KENYA CAN USE ARTIFICIAL INTELLIGENCE (AI) FOR AGRICULTURAL PRODUCTIVITY

Artificial Intelligence (AI) has improved agricultural productivity and food security in Kenya by increasing crop yields and reducing risks through technologies like precision farming and predictive analytics. The purpose of this study was to evaluate artificial intelligence’s potential to improve agricultural productivity and food security in Kenya. The study was guided by one objective: to investigate how farmers in Kenya can use Artificial Intelligence (AI) for agricultural productivity. Smallholder farmers in Kenya can use AI to increase food security systems can be strengthened and agricultural productivity increased through the use of artificial intelligence technologies. The study is anchored on Technology Acceptance Model. In order to improve agricultural productivity and food security in Kenya, the study will employ a desktop research design and rely on a systematic review and analysis of existing literature, policy documents, technical reports, and secondary datasets. The target population included in all publicly available documents, academic articles, government policies, reports from non-governmental organizations, and digital datasets on AI-driven agricultural innovations in Kenya published between 2015 and 2025. Based on relevance, credibility, and alignment with the study theme, a sample size of roughly 60–120 documents and 5–15 pertinent datasets was purposefully chosen. Structured searches in scholarly databases, the retrieval of gray literature from institutional repositories, the examination of national agricultural strategies, and the extraction of secondary agricultural and climate data from open-access portals are some of the data collection techniques. Key variables were extracted using a data extraction matrix after collected materials have been screened using predetermined inclusion and exclusion criteria. In order to identify emerging AI applications, opportunities, challenges, and their implications for agricultural productivity and food security, data analysis  included descriptive synthesis, thematic content analysis of documents, and comparative analysis across sources.