From the Student Success edition of October 24, 2026
Question-chain prompting for generative AI raised self-regulated learning behaviours, metacognitive awareness and course achievement versus free-form use in an 83-student quasi-experiment
South China Normal University, Lehigh University and Guangzhou University (study authors) · Higher education guided student use of generative AI for coursework · Guangzhou, China (transferability to US institutions untested)
- Publisher
- International Journal of Educational Technology in Higher Education (Springer Nature)
- Original publication
- International Journal of Educational Technology in Higher Education, volume 23, article 57, published 23 October 2026
- Source retrieved
- 2026-10-25
What happened
A quasi-experiment with 83 undergraduates in three intact classes of a television programme production course at a university in Guangzhou tested question-chain prompting during a GenAI-supported short-film project using DeepSeek. The control class (n=28) used free-form questioning; two classes used progressive (n=30) or divergent (n=25) question chains, an instructional package of specific, sequenced and required questions. Using interaction logs, reflections, an adapted metacognitive awareness inventory and course grades, both question-chain groups showed significantly more learning-strategy and learning-monitoring behaviours than the control and scored significantly higher on knowledge of cognition, regulation of cognition and academic achievement. The two chain types did not differ. The authors caution that reflection prompts differed by condition and that effects reflect the whole package rather than chaining alone.
Why it matters
Offers a low-cost instructional design (structured prompting sequences) that institutions could test to counter passive AI use, a recurring student-success concern.
Evidence and measured results
Peer-reviewed quasi-experiment with log coding, a validated-but-adapted instrument and grades; non-random assignment by intact class.
Limitations and uncertainty
Single instructor, single course, intact classes, Chinese context and DeepSeek; adapted 10-item instrument; differing reflection prompts.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-10-25; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- Students use generative AI passively, weakening self-regulated learning in project-based courses.
- Stakeholders
- Center for teaching and learning
- Instructional designers
- Academic affairs AI working group
- Course instructors
- Discovery questions
- Does course AI guidance say how students should question AI?
- Which project-based courses rely heavily on AI use?
- Can interaction logs be collected with consent?
- Value hypothesis
- Interpretation: structured question sequences can make student AI use more active and may improve metacognition and grades.
- Potential engagement
- A one-term pilot writing question-chain templates for two project-based courses, with a free-form comparison section.
- Unsupported claims
- That gains transfer to US institutions
- That chaining alone, without the package, drives effects
- Any retention effect
Pre-sales engineering
Role takeaway
- Fit
- Any course where students already use a general-purpose AI assistant for project work.
- Architecture and integration
- Instruction sheets, LMS templates or assistant system prompts that require sequenced questions.
- Prerequisites
- Assignment stages mapped to question chains
- Consent process for log collection
- Comparison section
- Constraints
- Single course and instructor
- Chinese context and DeepSeek
- Adapted instrument
- Security
- Collect interaction logs only with consent, de-identify for analysis and set retention limits.
- Proof of value
- Code logs for planning and monitoring behaviours
- Compare grades with a free-form control
- Use identical reflection prompts across groups
Delivery
Role takeaway
- Work
- Design, run and evaluate question-chain guidance for AI-supported course projects.
- Dependencies
- Instructor participation
- Teaching-centre design support
- Log access
- Ownership
- Center for teaching and learning with participating instructors.
- Skills and adoption
- Instructors learn to write question chains; students practise structured questioning as part of AI literacy.
- Governance checkpoints
- Consent and log-retention approval
- Mid-project review of log quality
- End-of-term review before broader rollout
- Acceptance criteria
- Proposed: chain groups show more monitoring behaviours in coded logs than the control
- Proposed: grade comparison reported with design limits
- Proposed: identical reflection prompts used across groups
- Risks
- Confounding by class or instructor
- Student resistance to required prompts
- Over-generalizing from one course
Implementation considerations
Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.
Architecture and integration
What must connect, and where does the AI sit in the workflow?
Tool-agnostic: the intervention is an instruction sheet that structures questions, not a product change. Interpretation: it could be built into course templates or assistant system prompts.
Governance
Who approves, reviews and stays accountable for outcomes?
Suggests course-level AI guidance could specify how students question AI, not only whether they may use it.
Security and privacy
What data, permissions and controls need testing?
Study used interaction logs for coding; institutions replicating this need consent and log-handling rules.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Structured prompts may help students with less AI experience, but this was not tested by subgroup.
Procurement
What should contracts, pricing and exit terms secure?
None directly; the intervention needs no new purchase.
Operating model
Which teams own the service once it runs?
Faculty development could teach question-chain design as part of AI literacy, with teaching centres providing templates.
Publication history
- 2026-10-24Student Success · Issue 455 resources
Stable resource ID: ijethe-question-chain-prompting-genai-self-regulated-learning-quasi-experiment-guangzhou-20261023