Category: Artificial Intelligence in Education (AIEd)
-
Beyond Prompt-to-App: Why Teacher-Facing AI Authoring Needs Accountable Translation
A new arXiv preprint traces how teacher intent changes as an agentic app moves from brief to specification, generated package, checks and approval—and argues that those transformations must remain attributable, inspectable and contestable.
-
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.
-
Building the Next Educational AI With Partners: Inside the LearnAdapt Ecosystem
LearnAdapt is inviting educators, researchers, institutions and product teams to co-design focused educational applications around real learning problems, using PedOS, Agentic Studio and a wider governed ecosystem.
-
Introducing LearnAdapt Praxis: A Five-Stage Journey from Learning to Workplace Practice
LearnAdapt Praxis helps adults move through Frame, Learn, Build, Validate, and Transfer while keeping their Design·AI learning journey visible to both learner and facilitator.
-
Introducing RankCert: When Is Simulation Evidence Strong Enough to Select an AI Tutor?
RankCert tests when simulated learners support selecting one AI tutoring policy—and when structural uncertainty makes abstention the more defensible result.