← Retour aux actualités recherche
German secondary students refine AI questions with prompt cards while a researcher observes their inquiry process in a small learning lab
Article de revuePeer-reviewed study20252 août 2026· 3 min

A brief prompt scaffold changed how secondary students used ChatGPT but did not improve knowledge gain

Maria Klar

Smart Learning Environments

Résumé de 500 mots

German secondary students refine AI questions with prompt cards while a researcher observes their inquiry process in a small learning lab

Klar asks why students who find ChatGPT easy to operate may still use only a small part of its learning potential. The mixed-methods experiment involved 106 Grade 9 and 10 students from five German secondary schools. In small after-school sessions, groups were randomly assigned to use a ChatGPT-3.5 research interface with or without additional support. Both groups investigated cognitive biases for 20 minutes. The supported group received about 2.5 minutes of instruction, suggestions for follow-up and adaptation prompts, and controls for response length and language difficulty.

The support clearly changed interaction behaviour. Students in the supported condition used an average of 6.00 adaptation prompts, compared with 2.51 in the comparison condition. The difference was statistically significant with a large reported effect, partial eta-squared of .283. Supported students also asked more total questions, 7.8 compared with 4.8, used more follow-ups and engaged in less off-topic conversation. Chat logs therefore show that a small scaffold can make student dialogue more iterative and tailored.

The learning measures tell a different story. The support did not significantly reduce extraneous cognitive load and did not significantly improve knowledge gain. Both groups reported high usability and satisfaction. That combination is educationally important: liking a chatbot and asking more sophisticated questions do not guarantee that learners understand or retain more. Interaction quality may be a mechanism worth developing, but it remains an intermediate outcome unless linked to independent learning evidence.

The study is deliberately small and bounded. Students completed one unfamiliar topic in a 20-minute session and could not use ordinary web search alongside the chatbot. The sample may be too small to detect modest learning effects. Explicitly telling the supported group that adaptation is helpful could create demand characteristics. The research does not establish long-term self-regulated learning, transfer across subjects or how students use unrestricted tools at home.

For classroom design, the findings argue against treating a list of prompt tips as a complete intervention. Teachers can combine question adaptation with source comparison, retrieval and explanation. For example, a student might request a simpler explanation, then identify a claim to verify, compare it with an assigned source and explain the concept without the chat. A teacher can score both the inquiry process and the unaided explanation.

The interface also matters. Follow-up suggestions can help novices notice options they might not invent, but they can channel every learner into the same pattern or add cognitive clutter. Supports should be optional, age-appropriate and tested with learners who have different language proficiency and accessibility needs.

For Hong Kong schools, bilingual studies could test whether language controls support Cantonese- and English-medium learning without simplifying disciplinary meaning. Longer units should measure delayed retention and transfer. The paper's central lesson is precise: brief prompting support changed what students did with ChatGPT, but this experiment did not show that the behavioural change improved learning.

A future study could vary the scaffold itself, compare optional and mandatory supports, and examine whether students transfer adaptation strategies to a new topic after the interface suggestions disappear. That would test whether behaviour becomes a learner capability.

Articles liés

Two older learners explain a balcony-gardening plan and tablet choices to a facilitator during a community-library learning session.
Politique / éthique20 sept. 2026
Politique / éthique 167

Industry news: OpenAI and OATS bring hands-on AI learning to older adults through community partners

OpenAI

AI Product and Learning Report

OpenAI's September 16 announcement describes free, in-person AI workshops with OATS from AARP across ten U.S. communities. This September 20 report examines the lifelong-learning design, rather than claiming completed outcomes. Anthropic's practical AI-learning guidance and Gemini's educator resources offer comparisons. Effective support should begin with a participant's own task, allow different paces and preferences, and help people decide when to question an answer or seek human assistance.

product newslifelong learningolder adults
Lire le résumé de 500 mots →
A student using a wheelchair works at a keyboard while two educators compare an enlarged course page with a hand-drawn keyboard-navigation sequence.
Politique / éthique5 sept. 2026
Politique / éthique 139

Product news: An accessibility specialist uses ChatGPT to adapt reading tools, without shifting responsibility to users

OpenAI Academy

AI Product and Learning Report

An OpenAI Academy profile published September 4 describes accessibility specialist James Warnken using ChatGPT to create browser shortcuts and a keyboard-focus styling tool. Reported here on September 5, the case shows a person directing technology around a specific access need. Anthropic's teaching guidance and Gemini's educator training offer related learning opportunities, but personal adaptations do not replace a school's responsibility to provide usable digital materials.

product newsaccessibilityinclusive design
Lire le résumé de 500 mots →