Technical Project Ongoing
Live
A live web tool that coaches students through structured thinking on an assignment — planning, questioning and evaluating their own reasoning — instead of generating answers for them.
Key insight — Asking structuring questions instead of drafting content was the design choice that kept the tool from quietly turning into an essay generator.
TypeScript · Web application · Prompt design · Vercel deployment
Empirical Study Completed
A scenario-based method that tests whether a university's public AI-governance documents still produce an accountable decision as AI use moves from simple assistance toward more autonomous, delegated action.
Key insight — The most common weak point wasn't a missing rule — it was a named responsible role with no specific criteria, safeguards or review to back it up.
Document analysis · Scenario-based stress testing · Structured coding protocol · Independent reliability checking
Last updated 26 August 2026
Policy Analysis Completed
A vignette-based test of whether the published policy environment at 20 Australian universities actually resolves common AI-assisted student behaviours, or leaves them ambiguous.
Key insight — Transparent, verified AI use was consistently the most clearly resolved by published policy — ambiguous or partially-disclosed use often wasn't resolved at all.
Vignette methodology · Structured policy classification · Dual-coder reliability testing
Last updated 26 August 2026
Technical Project In progress
A Python pipeline using web extraction and the Gemini API to collect, structure and organise university AI-policy information, with human verification of every record.
Key insight — Every AI-extracted field is treated as a claim, not data, until a human checks it against the source — extraction speed never substitutes for verification.
Python · Web extraction · Gemini API · Structured JSON outputs · Human verification workflow
Last updated 28 July 2026
Framework Ongoing
A six-question framework that structures fair, consistent decisions about student generative-AI use in assessment.
Key insight — Separating disclosure failures from authorship failures stops honest, permitted-but-poorly-acknowledged AI use from being treated as contract cheating.
Conceptual synthesis · Case testing · Policy analysis
Last updated 28 July 2026
Workflow Ongoing
A documented, human-led workflow in which AI assists with drafting, organising, coding and formatting while humans remain responsible for meaning, accuracy, ethics and final approval.
Key insight — Most corrections happen at the verification stage, not the drafting stage — AI-assisted first drafts are rarely wrong in an obviously detectable way.
Workflow design · LLM-assisted drafting · Verification checklists · Documentation
Last updated 28 July 2026