Grade AI-dialogue assignments on evidence of sustained dialogue, and explicitly teach students to answer the AI's questions¶

Strategy · All strategies
Evidence · no claims cited

Description¶

From implementation, the authors recommend that if the goal is dialogue, then the grading criteria should reflect dialogue: students should provide the main contextual prompt and enough follow-up interaction to demonstrate meaningful exploration, responding to the AI's questions rather than only prompting in one direction. They also advise making explicit that students should answer the AI's Socratic questions and participate in a sustained dialogue, since many students did not do so unprompted.

Design Implications¶

Context¶

Requirements¶

• Students need explicit guidance, since many are unfamiliar with using AI as a conversational learning partner rather than as a search engine

Constraints¶

Target Learners¶

• university students new to conversational AI use

Target Learning Goals¶

• sustained dialogic engagement with course content via AI

Related Strategies¶

• Context-prompt reflection assignments in which students elaborate on a concept, apply it to a novel problem, and receive AI feedback
• Reflective Writing
• Calibrate AI writing support by providing contextual feedback, dialogic scaffolding, and initiative matched to learner needs and task complexity
• Describe AI instructional role and learner–AI interaction design in detail (prompts, scaffolds, modality, dialogue structures)

Examples¶

-

Key Sources¶

• Miguel Rodriguez and Peter Wulff. (2026). Artificial Intelligence Driven Physics Assignments using Context Prompts. https://arxiv.org/abs/2609.22578