3 items with this tag.
Professional curricula are comprehensively documented but not systematically queryable, creating artificial information scarcity. This creates significant problems for institutions: regulatory compliance reporting consumes weeks of staff time, quality assurance requires exhaustive manual verification, and curriculum office teams cannot efficiently answer structural questions. Current approaches—manual document review, VLE keyword search, curriculum mapping spreadsheets, and purpose-built curriculum management systems—fail to expose curriculum structure in queryable form. We propose an architecture where graph databases become the source of truth for curriculum structure, with vector databases for content retrieval and the Model Context Protocol providing accessible interfaces. This makes documented curriculum structure explicitly queryable—prerequisite chains, competency mappings, and assessment coverage—enabling compliance verification in hours rather than weeks. The architecture suits AI-forward institutions—those treating AI integration as ongoing strategic practice requiring active engagement with evolving technologies. Technology handles structural verification; educators retain essential authority over educational meaning-making. The proposal argues for removing technical barriers to interrogating curriculum complexity rather than eliminating that complexity through technological solution.
Higher education institutions face a fundamental choice in AI engagement that will determine whether they undergo genuine transformation or sophisticated preservation of existing paradigms. While institutional responses have centred on prompt engineering—teaching students to craft effective AI queries—this approach inadvertently reinforces hierarchical knowledge transmission models and container-based educational structures that increasingly misalign with professional practice. Context engineering emerges as a paradigmatic alternative that shifts focus from optimising individual AI interactions toward architecting persistent knowledge ecosystems. This demands sophisticated technical infrastructure including knowledge graphs capturing conceptual relationships, standardised protocols enabling federated intelligence, and persistent memory systems accumulating understanding over time. These technologies enable epistemic transformations that fundamentally reconceptualise how knowledge exists and operates within educational environments. Rather than discrete curricular containers, knowledge exists as interconnected networks where concepts gain meaning through relationships to broader understanding frameworks. Dynamic knowledge integration enables real-time incorporation of emerging research and community insights, while collaborative construction processes challenge traditional academic gatekeeping through democratic validation involving multiple stakeholder communities. The systemic implications prove profound, demanding governance reconceptualisation, substantial infrastructure investment, and operational transformation that most institutions currently lack capabilities to address effectively. Context engineering creates technical dependencies making traditional educational approaches increasingly untenable, establishing path dependencies favouring continued transformation over reversion to familiar paradigms. This analysis reveals context engineering as a potential watershed moment for higher education institutions seeking educational relevance and technological sophistication within rapidly evolving contexts that traditional academic structures struggle to address effectively.
The current discourse around artificial intelligence in education has become preoccupied with prompting strategies, overlooking more fundamental questions about the nature of context in human-AI collaboration. This paper explores the concept of *context engineering* as an operational framework that supports personal learning and the philosophical goal of *context sovereignty*. Drawing from complexity science and learning theory, we argue that context functions as a dynamic field of meaning-making rather than static background information, and that ownership of that context is an essential consideration. Current approaches to context-setting in AI-supported learning—primarily prompting and document uploading—create episodic burdens requiring learners to adapt to AI systems rather than insisting that AI systems adapt to learners. Context sovereignty offers an alternative paradigm based on three principles: persistent understanding, individual agency, and cognitive extension. This framework addresses concerns about privacy, intellectual challenge, and authentic assessment while enabling new forms of collaborative learning that preserve human agency. Rather than treating AI as an external tool requiring skilful manipulation, context sovereignty suggests AI can become a cognitive partner that understands and extends human thinking while respecting individual boundaries. The implications extend beyond technical implementation to fundamental questions about the nature of learning, assessment, and human-AI collaboration in educational settings.