Teacher orchestration and custom AI mediation in an inquiry-bound activity for young language learners

This qualitative case study examines how a customized artificial intelligence (CAI) assistant supported young learners during a Mystery Classroom activity as part of a broader technology-enhanced project-based language learning (TEPBLL) initiative. The participants were 59 elementary learners in Spain and Nigeria who prepared yes-or-no questions to identify the geographical location of a partner class. The activity required learners to use the target language as a tool for authentic inquiry, collaborative reasoning, question formulation, and intercultural communication. Data included CAI chat logs, classroom interaction videos, and teacher field notes. Thematic analysis was used to examine the interaction data. The analysis generated three higher-order themes: task alignment as an interactionally achieved process, language mediation within inquiry, and the pedagogical boundaries and limits of customization. Across these themes, learners used CAI for question formulation, local language repair, clue testing, and the evaluation and constraint of AI output. Boundary cases showed that customization did not prevent task drift or safety-relevant prompting, including location-related questions inappropriate for child-facing AI use. CAI functioned as a task-bound mediator through the combination of its configured support for simple English, target-language redirection, classroom task instructions, and teacher mediation. Teacher orchestration and peer discussion remained necessary for evaluating output, repairing drift, and maintaining child-safety boundaries. The study shows both the promise and the limits of configured custom AI in language learning for young learners. It demonstrates that the pedagogical value of CAI depends on configuration capacity together with teacher orchestration, peer discussion, learner evaluation, and explicit task and safety boundaries.

Authors

Institutions

Publication Details

Journal
Innovation in Language Learning and Teaching
Published
2026-11-16
DOI
https://doi.org/10.1080/17501229.2026.2763682
Primary Topic
EFL/ESL Teaching and Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Teacher orchestration and custom AI mediation in an inquiry-bound activity for young language learners

Ese Emmanuel Uwosomah
4 links
Innovation in Language Learning and Teaching
EFL/ESL Teaching and Learning
article

Teacher orchestration and custom AI mediation in an inquiry-bound activity for young language learners

Ese Emmanuel Uwosomah
article en

Abstract

This qualitative case study examines how a customized artificial intelligence (CAI) assistant supported young learners during a Mystery Classroom activity as part of a broader technology-enhanced project-based language learning (TEPBLL) initiative. The participants were 59 elementary learners in Spain and Nigeria who prepared yes-or-no questions to identify the geographical location of a partner class. The activity required learners to use the target language as a tool for authentic inquiry, collaborative reasoning, question formulation, and intercultural communication. Data included CAI chat logs, classroom interaction videos, and teacher field notes. Thematic analysis was used to examine the interaction data. The analysis generated three higher-order themes: task alignment as an interactionally achieved process, language mediation within inquiry, and the pedagogical boundaries and limits of customization. Across these themes, learners used CAI for question formulation, local language repair, clue testing, and the evaluation and constraint of AI output. Boundary cases showed that customization did not prevent task drift or safety-relevant prompting, including location-related questions inappropriate for child-facing AI use. CAI functioned as a task-bound mediator through the combination of its configured support for simple English, target-language redirection, classroom task instructions, and teacher mediation. Teacher orchestration and peer discussion remained necessary for evaluating output, repairing drift, and maintaining child-safety boundaries. The study shows both the promise and the limits of configured custom AI in language learning for young learners. It demonstrates that the pedagogical value of CAI depends on configuration capacity together with teacher orchestration, peer discussion, learner evaluation, and explicit task and safety boundaries.

Innovation in Language Learning and Teaching
Universitat Autònoma de Barcelona (ES)
Quality education
EFL/ESL Teaching and Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon