AlignED Studies

When can an AI’s judgement be trusted?

And what would count as evidence? Every project here is a run at that question.

AI already grades essays, gives students feedback and advises teachers. AlignED Studies tests that judgement instead of taking it on trust.

• AlignED Benchmark & reports   frontier models tested on professional teaching tasks, with open data and methods. Browse the studies
• Aligned Interviewer   AI-led qualitative interviews, synthesised against the researcher’s own framework. By invitation.
• Landscape Scanner   field scans where every claim traces to a verbatim source quote. Source on GitHub
• Analytical thinking continuum   an empirically derived progression of analytical thinking, and a Socratic interview built on it. Methods paper in preparation.
• Qual Research Suite   the engine shared by the above, being consolidated into one tool. In development.

Much of this work is done with AI assistance.