/home/michael

Beyond document management: Graph infrastructure for professional curricula

1 min read

Presentation

Advance HE AI Symposium · Online · 10 February 2026

Contributed presentation with Wesley Lynch (Snapplify)

Abstract

Professional education curricula face a fundamental infrastructure problem: while comprehensively documented, they lack systematic queryability. Programme teams must demonstrate competency coverage for regulatory audits, which sometimes requires days or weeks of manual document review. Quality assurance staff need to manually cross-reference spreadsheets to verify assessment coverage. Module leads work in isolation, struggling to identify what colleagues teach or discover curriculum gaps. These artefacts of document-based infrastructure create artificial information scarcity through technical limitations.

We propose a three-layer architecture: graph databases storing curriculum structure as typed relationships (programmes contain modules, assessments test learning outcomes, outcomes map to competencies), vector databases enabling semantic content search, and the Model Context Protocol providing natural language interfaces, tool-use, and agents. The goal is not to create structure but to make existing structure computationally accessible.

Slides

Use arrow keys or click to navigate slides. Open slides in full screen

Continue reading

  • Documentation becomes infrastructure when AI agents are the readers

    When AI agents consume documentation as operational input, it undergoes a category shift from reference material to operational architecture — inaccuracies no longer merely inconvenience readers, they cause system failures. This essay argues that the primary bottleneck for institutional AI integration is not AI capability but information architecture: how institutional knowledge is structured, maintained, and made available to AI systems. Documentation written for human readers cannot function as reliable AI input without deliberate restructuring around explicit relationships and rigorous maintenance workflows. Treating this transition as a governance imperative — rather than a technical afterthought — determines whether AI integration delivers on its institutional promise.

  • Beyond document management: Graph infrastructure for professional education curricula

    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.

  • Agentic workflows

    A mode of working in which AI agents handle execution-level tasks while the human operates at the direction layer — deciding what should be made, defining what good looks like, and evaluating outputs.

Graph View