GenAITEd Ghana as a Context-Aware and Curriculum-Aligned Conversational AI Agent for Teacher Education

Global frameworks increasingly call for Responsible Artificial Intelligence (AI) in education, yet they provide limited guidance on how ethical, culturally responsive, and curriculum-aligned AI can be operationalized within functioning teacher education systems, particularly in the Global South. This study addresses this gap through the design and evaluation of GenAITEd Ghana, a context-aware, region-specific conversational AI prototype developed to support teacher education in Ghana. Adopting a Design Science Research approach, the study developed GenAITEd Ghana as a school-mimetic digital infrastructure aligned with the organizational logic of Ghanaian Colleges of Education. The platform provisions NaCCA-aligned course environments based on users’ institutional affiliation, academic year, semester, and course specialization. Teacher educators create course-specific AI agents and invite student teachers into individual or collaborative learning spaces using cryptographic passkeys. The system operates as a multi-agent, retrieval-augmented conversational AI that coordinates multiple AI models for curriculum-grounded dialogue, automatic speech recognition, voice synthesis and cloning, and multimedia processing. Two complementary prompt pathways were embedded: system-level prompts enforcing curriculum boundaries, ethical constraints, retrieval scope, and teacher-in-the-loop oversight, and interaction-level semi-automated prompts that structure live pedagogical dialogue through clarification, confirmation, and guided response generation. Evaluation findings show that the system features and prompt logics addressed key Responsible AI framework requirements, including transparency, accountability, cultural responsiveness, privacy, and human oversight. Human expert evaluations further indicated that GenAITEd Ghana is pedagogically appropriate for Ghanaian teacher education and consistently perceived the system as capable of promoting student engagement while preserving educators’ professional authority. However, some implementation challenges were noted, particularly regarding the successful deployment of teacher voice cloning and avatar generation for AI agents. Experts also highlighted the risk of student teachers over-relying on AI agents without sufficiently engaging other domains of learning that require human judgment, social interaction, and affective engagement. The study therefore advocates for the scalable advancement of context-aware educational AI through enhanced model integration, sustained professional development, and critical AI literacy for both teachers and student teachers.