From Consumers to Designers: Building Rule-Based Chatbots to Reinforce Chemistry Learning and Foster Critical AI Literacy

Abstract This article describes an instructional approach that shifts secondary school participants from passive consumers of artificial intelligence to active designers by engaging them in building a closed-loop, rule-based chatbot. Implemented with 62 students (grades 8–12) in Georgia, the project required collaborative curation of chemistry content and programming of deterministic conversational logic. Unlike generative AI, this rule-based approach aligns with the rule-governed nature of core chemistry concepts such as stoichiometry and the mole concept. Pre- and post-test comparisons demonstrated substantial conceptual gains, particularly in abstract domains (+28% to +30%). Incorporating a social-contextual layer containing class-specific “insider knowledge”-triggered cognitive conflict that reduced uncritical trust in chatbot outputs from 70% to 15%. This approach offers secondary chemistry educators a practical strategy to simultaneously reinforce disciplinary understanding and foster critical digital literacy.

Authors

Publication Details

Journal
Journal of Chemical Education
Published
2026-11-14
DOI
https://doi.org/10.1021/acs.jchemed.6c01077
Primary Topic
Artificial Intelligence in Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

From Consumers to Designers: Building Rule-Based Chatbots to Reinforce Chemistry Learning and Foster Critical AI Literacy

Maka Makaridze
Journal of Chemical Education
Artificial Intelligence in Education
article

From Consumers to Designers: Building Rule-Based Chatbots to Reinforce Chemistry Learning and Foster Critical AI Literacy

Maka Makaridze
article en

Abstract

Abstract This article describes an instructional approach that shifts secondary school participants from passive consumers of artificial intelligence to active designers by engaging them in building a closed-loop, rule-based chatbot. Implemented with 62 students (grades 8–12) in Georgia, the project required collaborative curation of chemistry content and programming of deterministic conversational logic. Unlike generative AI, this rule-based approach aligns with the rule-governed nature of core chemistry concepts such as stoichiometry and the mole concept. Pre- and post-test comparisons demonstrated substantial conceptual gains, particularly in abstract domains (+28% to +30%). Incorporating a social-contextual layer containing class-specific “insider knowledge”-triggered cognitive conflict that reduced uncritical trust in chatbot outputs from 70% to 15%. This approach offers secondary chemistry educators a practical strategy to simultaneously reinforce disciplinary understanding and foster critical digital literacy.

Journal of Chemical Education
Artificial Intelligence in Education
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