4 items with this tag.
A standardised ontology providing business, data, and application architectures for the higher education sector — and a practical starting point for making institutional knowledge machine-readable.
Professional education curricula face a fundamental infrastructure problem: while comprehensively documented, they lack systematic queryability. This presentation introduces a three-layer architecture using graph databases as the source of truth for curriculum structure, supported by vector databases for content retrieval and the Model Context Protocol for stakeholder interfaces.
Professional curricula are extensively documented but not systematically queryable, creating artificial information scarcity that makes compliance reporting and quality assurance labour-intensive. This essay proposes a three-layer architecture — graph databases as the source of truth for curriculum structure, vector databases for semantic content retrieval, and a Model Context Protocol layer for stakeholder access — that transforms documentation into operational infrastructure. The architecture incorporates temporal versioning for longitudinal evidence, role-based access controls for multi-stakeholder environments, and internal quality audit against institutional policy alongside external regulatory compliance, enabling verification in hours rather than weeks.
The predominant AI interface paradigm — text boxes and chronological chat histories — reproduces a deeply embedded cognitive metaphor that misaligns with how professional expertise develops. Drawing on Lakoff and Johnson's container schema, this essay traces how a single organising metaphor has been uncritically reproduced across physical, digital, and AI-mediated learning environments, artificially enclosing knowledge that practitioners must mentally reintegrate. Rather than proposing to replace bounded learning spaces, this essay explores graph-based learning environments as an alternative paradigm where bounded spaces become visible communities within a navigable network. AI serves as both conversational partner and network weaver, with conversations spatially anchored to relevant concepts rather than isolated in chronological chat histories. This reconceptualisation — from enclosure to constrained traversal — suggests possibilities for AI-supported learning environments that better develop the integrative capabilities defining professional expertise.