Educator-guided ai gives staged feedback for database design learning
An Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database Design
Artificial Intelligence
Summary
Designing databases can be tricky, and learners need helpful feedback to improve. This paper shows a tool that uses AI guided by educators to give step-by-step feedback on students' database diagrams. The feedback starts simple and becomes more detailed only when needed, helping students understand their mistakes without confusion. The authors tested it in real classroom settings and found most students improved by following the advice.
What this means in practice
- •For educational software developers: Integrate AI-driven, staged feedback into diagram editors for teaching database design concepts effectively.
- •For corporate training teams: Deploy scaffolded AI feedback tools to improve database design skills in employee learning programs.
Authors
Sara Riazi, Pedram Rooshenas
Abstract
We present an educator-guided LLM pedagogical agent for scaffolded feedback in conceptual database design. Integrated into an entity--relationship diagram (ERD) editor, the system grounds feedback in the student artifact, assignment requirements, educator-authored rubrics, and instructional resources. Its architecture separates hidden, artifact-grounded diagnosis from the workflow that controls the form and disclosure level of student-facing support. We instantiate the architecture as a four-stage workflow progressing from concept checks and guided application to low-detail feedback and localized clarification. Each feedback request creates a stateful episode linked to versioned ERD states. In a deployment spanning three ERD environments and 383 feedback episodes, 71.1\% of observed target-level changes fully or partially incorporated the hidden diagnostic target, including many after Stages~1--2. Qualitative analysis showed that staged disclosure sometimes withheld inaccurate details, supported selective uptake, or allowed later recovery, though some errors still shaped revisions. Survey responses from a self-selected sample favored delayed disclosure and student agency but noted indirectness and repetition.