Category: Pedagogy & Assessment
-
CALLIOPE: Building an Inspectable Path from Spoken Response to Educator Review
A new technical report presents CALLIOPE’s source-grounded oral-assessment workflow and a bounded synthetic evaluation of the software paths exercised so far.
-
Presenting “From Misconceptions to Evidence” at SISTC 2026
At SISTC 2026, I will present our study of how science teachers translate misconceptions, learner interactions, evidence, authority, and safeguards into specifications for agentic learning apps.
-
Correct Is Not the Same as Learned
AI tutors can help students reach the right answer faster, but correctness alone does not prove durable understanding. As AI becomes more embedded in education, we need to ask whether learners are truly building mastery, or simply performing well with assistance. The future of educational AI should not just optimise for immediate success, but for…
-
The Architect’s Dilemma: Rethinking Assessment When AI Does the Heavy Lifting
In an hour, I built a production-grade ML app with full documentation—without writing a single line of code. If AI is the mason, students must become the Architects. Here’s why we need to stop grading the product and start assessing the process.