Actionable companion · Learning design & outcomes
Learning with agency: A Model to Develop Chatbots for Assisting the Teaching and Learning Process
AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.
Evidence and context
Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Secondary school. Verify the participant population and task before transferring the findings.
Original authors’ abstract, reproduced under the linked source license:
Abstract Recently, in the commercial and entertainment sectors, we have seen increasing interest in incorporating chatbots into websites and apps, in order to assist customers and clients. In the academic area, chatbots are useful to provide some guidance and information about courses, admission processes and procedures, study programs, and scholarly services. However, these virtual assistants have limited mechanisms to suitably help the teaching and learning process, considering that these mechanisms should be advantageous for all the people involved. In this article, we design a model for developing a chatbot that serves as an extra-school tool to carry out academic and administrative tasks and facilitate communication between middle-school students and academic staff (e.g., teachers, social workers, psychologists, and pedagogues). Our approach is designed to help less tech-savvy people by offering them a familiar environment, using a conversational agent to ease and guide their interactions. The proposed model has been validated by implementing a multi-platform chatbot that provides both textual-based and voice-based communications and uses state-of-the-art technology. The chatbot has been tested with the help of students and teachers from a Mexican middle school, and the evaluation results show that our prototype obtained positive usability and user experience endorsements from such end-users. Keywords: chatbots, extra-school tool, middle school, teaching and learning process
What kind of evidence is this?
Conversational & pedagogical agents · Design / feasibility study
Stage: Secondary school. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.
Study methods · source passage
Finally, the former tests with end-users were conducted. Thus, we assessed the workload perceived by the participants after having performed some tasks. Eight individuals from the middle school were gathered: two teachers (one 36 years old man and one 28 years old woman) and six students—three females and three males between 14 and 15 years old, who had not used a chatbot. Thus, to perform our tests, we started letting them interact with the chatbot’s user interface for a few minutes, in order to become familiar with the different widgets and their functions. Afterwards, we asked them to complete specific tasks according to their roles. As shown by our results, the chatbot-based solution seems to be a good option, as anyone can use it, many academic processes can be systematized, it will always be available, and it allows end-users to participate accordingly.
Design the system before the pilot
Define whether the agent asks questions, gives hints, explains or assesses. Test hallucinated feedback, excessive praise, misleading confidence and responses when the learner is confused. A conversational interface alone does not establish autonomous agency.
- Specify a measurable learning objective, a comparator and a task without tool assistance before adopting a system.
A 90-day district pilot
- Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
- Days 16–30 · Design. Ask learners to attempt a problem unaided, compare an agent hint, explain a revision and verify the final reasoning against a trusted source. Make the permitted use explicit for each assignment. Name an accountable owner and set the baseline, success threshold and budget before implementation.
- Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
- Days 61–90 · Decide. Measure unaided transfer and delayed retention, calibration of confidence and the ability to identify an incorrect AI explanation. Record whether help-seeking becomes answer copying. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.
The board decision brief
Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.
Attribution and reuse
Sonia Mendoza; Luis Martín Sánchez-Adame; José Fidel Urquiza-Yllescas; Beatriz A González-Beltrán; Dominique Decouchant. A Model to Develop Chatbots for Assisting the Teaching and Learning Process. Sensors (Basel, Switzerland) (2022-07-25). https://doi.org/10.3390/s22155532
Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.