Educators, curriculum designers, and researchers building AI-assisted educational agents that stay within explicit knowledge boundaries.
Active Inference for Grounded Educational Knowledge Environments.
Lead: Matthew D Murphy
Ed4All (Active Inference for Grounded Educational Knowledge Environments) is an open, locally deployable, empirically evaluated framework for grounded educational agents that operate within explicit knowledge and evidentiary boundaries.
Ed4All develops educational agents whose responses are grounded in an explicit, bounded body of knowledge and evidence, rather than an open-ended generative model — aimed at classroom and self-directed learning contexts where staying within a defined curriculum or evidence base matters. The framework is designed to run locally and be empirically evaluated rather than deployed as an opaque black box.
Educators, curriculum designers, and developers interested in grounded, evaluable educational AI agents are welcome.
Related resources
Audience: Newcomer
Primary public community channel for conversation, coordination, and newcomer orientation.
Audience: Researcher
Public ecosystem shortlink for Institute context, projects, activities, and conceptual maps.