Knowledge-Learning-Instruction Framework Koedinger studied and developed the KLI framework of Learning Science. In 2012, Koedinger, along with his colleagueAlbert Corbett from the HCII and Charles Perfetti from the University of Pittsburgh, introduced the Knowledge-Learning-Instruction framework. The propositions within the KLI framework can help generate research questions within specific domains and instructional situations that, with further work, yield precise and falsifiable predictions. The KLI framework relates a set of observable and unobservable events: Learning Events, Instructional Events, Assessment Events and Knowledge Components.
Instructional Events: Variations, typically planned, in the learning environment that are intended to produce learning. Instructional Events cause Learning Events.
Learning Events: Changes in cognitive and brain states that can be inferred from data, but cannot be directly observed or directly controlled.
Assessment Events: Involve student responses that are evaluated. Assessment Events are usually test items that can be directly observed, but they can also be embedded in the context of instruction.
Knowledge Components: A description of a mental structure or process that a learner uses, alone or in combination with other knowledge components, to accomplish steps in a task or a problem. A knowledge component is also closely related to an assessment event, since it is an acquired unit of cognitive function or structure that can be inferred from performance on a set of related tasks.
Cognitive Tutor Koedinger has a huge contribution to the Intelligent Tutoring System, and developed several cognitive tutor software to aid the traditional classroom learning. Among which the "Cognitive Tutor Algebra" is one of the precursors of the ITS. In 2006, Koedinger and Albert Corbett invented the Cognitive Tutor Algebra from their Cognitive Tutor research. It is intended to provide students with immediate step by step hints and feedback, which traditional classroom practice can not provide. In 2011, Koedinger, and his colleagues Ido Roll, Vincent Aleven and Bruce McLaren introduced the Help Tutor, an enhanced version of the Geometry Cognitive Tutor that is capable of giving immediate metacognitive feedback on students' help-seeking errors. As an enhanced version, the Help Tutor teaches help-seeking skills by giving metacognitive feedback on students' help-seeking errors in the context of learning a domain-specific problem-solving skill. The Help Tutor messages include only domain-independent metacognitive content for several reasons: to encourage students to focus more on the metacognitive feedback, to help students generalize the help-seeking skills, and to make the Help Tutor reusable with different Cognitive Tutors.
