Skip to content

Three-phase instructional workflow with iFlytek Spark in property law sessions

Design · All designs
Evidence · 1 claim (1 for) · 1 study (1 causal), q1 · 0 of 1 report an effect size · 1 claim rests on one study

Description

Each class session during the 16-week intervention followed a three-phase workflow (Fig. 2): pre-AI preparation, in which the instructor presents a case scenario and students draft an initial analysis independently; AI interaction, in which students submit to iFlytek Spark, compare with their own draft, engage in iterative dialogue and follow-up probing, and integrate AI feedback; and post-AI reflection, with whole-class discussion evaluating AI versus student analysis and a reflection journal entry documenting the reasoning process. The design operationalizes the constructivist scaffolding rationale of the intervention.

Design Implications

Context

Requirements

  • Students submit only hypothetical case scenarios and avoid personally identifiable information, per the study's data governance measures

Constraints

  • The workflow was implemented with iFlytek Spark, a Chinese-language commercial platform selected for language appropriateness, ease of use, and compatibility with national data governance norms

Target Learners

  • third-year law students in property law courses

Learning Goals

  • legal reasoning
  • iterative analysis refinement
  • metacognitive awareness of reasoning processes

Claims

Examples

-

Key Sources

  • Haifang Liu. (2026). AI-enhanced legal pedagogy: a case study of generative AI integration in property law courses. Education Tech Research Dev. https://doi.org/10.1007/s11423-026-10698-9
Page metadata
Field Value
type design
id three-phase-genai-workflow-property-law
title Three-phase instructional workflow with iFlytek Spark in property law sessions
description Each class session during the 16-week intervention followed a three-phase workflow (Fig.
status review
generated by process:settle-candidates on 2026-10-29
trust unverified — no one has confirmed this page's content
sources 1 — haifang-liu-2026

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