For Assessment Designers
Define exam flows, rubric criteria, and policies in a structured, versioned format. Compile to runtime configurations automatically.
IOA-ORM — Interactive Oral Assessment Reference Model
An ontology-grounded reference model for interactive oral assessment systems. Bridging assessment theory and runtime execution.
For Runtime Engineers
Enforce hard constraints on transitions, follow-ups, time budgets, and evidence collection. Every state change produces a structured event.
For AI Integrators
Bounds AI agent behavior. Ensures autonomous agents operate within a strictly bounded creative space — they can follow up naturally and judge evidence, but cannot bypass structural guardrails, jump topics, or reveal rubrics.
For Researchers
Grounded in oral assessment theory (Joughin 1998, Akimov & Malin 2020, Bayley et al. 2024, Fenton 2025). Design space systematically explored.
Architecture
Section titled “Architecture”Built for Auditable AI: IOA-ORM moves beyond raw transcripts — it produces a structured, real-time Evidence Ledger, making AI-judged assessments fully transparent and marking-ready.
Where to Go Next
Section titled “Where to Go Next”Read the PrimerUnderstand the vision, theoretical grounding, and architecture.
Explore the SchemaDive into the 26 TypeScript interfaces defining the exam packages.
Runtime SemanticsSee how the runtime controller enforces transitions and bounds the AI.
Design Space MapInteractive morphological analysis of the 12 design dimensions and their dependencies.