Retrieval-augmented generative AI learning platform for construction education

Design · All designs
Evidence · no claims cited

Description

A web-based generative AI–supported learning platform developed for construction education that "enables document-grounded interaction with course materials and generates source-linked responses aligned with curated instructional resources." It uses a retrieval-augmented generation architecture combining semantic retrieval with large language model generation to constrain responses to course-specific content. Prior evaluations included expert review of accuracy and relevance, automated grounding assessment, and a formative classroom usability evaluation; the same configuration and knowledge base served both AI conditions in the experiment.

Design Implications

Context

Requirements

• A curated course-aligned knowledge base and prior evaluation establishing response reliability and instructional alignment

Constraints

• Responses are constrained to course-specific content via the RAG architecture

Target Learners

• undergraduate construction engineering students

Learning Goals

• self-directed review of construction course concepts with source-linked explanations

Claims

Related Designs

• GraphRAG textbook knowledge retrieval for grounded tutoring
• Retrieval-augmented Conversational AI Tutor with modular GROW-aligned coaching routines
• Intelligent digital textbook framework with LLM-powered structured dialogue for reading comprehension support
• RAG-based GenAI chatbot used as the AI-assisted learning support in the external validity study

Examples

-

Key Sources

• Xiaoyu Hou, Bo Xiao, Hexu Liu and Shane Mueller. (2026). The Role of Instructional Guidance in Generative AI-Assisted Learning: Empirical Evidence from Construction Engineering Education.

Page metadata

Field	Value
type	design
id	rag-generative-ai-platform-construction-education
title	Retrieval-augmented generative AI learning platform for construction education
description	A web-based generative AI–supported learning platform developed for construction education that "enables document-grounded interaction with course materials and generates source-linked responses aligned with curated i...
status	review
generated	by process:settle-candidates on 2026-10-11
trust	unverified — no one has confirmed this page's content
sources	1 — xiaoyu-hou-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.