CoChat
Sign Up
Cited by 64Artificial Intelligence in EducationTeaching and Learning ProgrammingArtificial Intelligence in Healthcare and Education

Enhancing data analysis and programming skills through structured prompt training: The impact of generative AI in engineering education

Open access
Garg, Ashish, Nisumba Soodhani, K., Rajendran, Ramkumar·2025·Computers and Education: Artificial Intelligence
DOI 10.1016/j.caeai.2025.100380
Open this paper in CoChat — free account

Abstract

The advent of Generative Artificial Intelligence (GenAI) and large language models like LLama, Palm2, GPT, Gemini, and Claude has revolutionized education by generating human-like text and contextually relevant responses. Our research investigates the impact of structured prompt training on students' learning in data analysis and programming. We experimented with 157 first-year engineering students divided into three groups: a control group (internet access, no GenAI), an experimental group 1 (internet and GenAI without prompt training), and an experimental group 2 (internet and GenAI with prompt training). The prompt training session included techniques like few-shot prompting, chain prompting, and the CLEAR framework. We assessed participants' performance in data analysis tasks using Python, with pre-tests and post-tests measuring their skills in programming across three Bloom's taxonomy levels (understanding, application, and analysis). ANOVA on post-test scores showed significant differences among the groups, with G3 (with prompt training) outperforming G2 (without prompt training) and the control group across all three levels, evidenced by higher mean scores (G3: 6.60, G2: 4.94, Control: 4.28), similar pattern observed in task completion also. These results underscore the effectiveness of structured prompt training in enhancing students' data analysis and programming skills. Our study highlights the potential of GenAI and structured prompt training to transform education…

Integrity signals

Registry

Crossref · 10.1016/j.caeai.2025.100380

Cites

55 of 55 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Unguided or unstructured use of GenAI tools in data analysis and programming may hinder learning outcomes.

    “Garg et al. (2025) demonstrated that unguided or unstructured use of GenAI tools in data analysis and programming may hinder learning outcomes.”

    From Integrating Generative AI into Programming Education: Student Perceptions and the Challenge of Correcting AI Errors (2025) · cites this paper as Garg et al. (2025)

  • Students who received structured training in how to prompt GenAI tools outperformed both those who used the tools without guidance and those who relied solely on traditional internet search strategies.

    “In their study, students who received structured training in how to prompt GenAI tools outperformed both those who used the tools without guidance and those who relied solely on traditional internet search strategies.”

    From Integrating Generative AI into Programming Education: Student Perceptions and the Challenge of Correcting AI Errors (2025) · cites this paper as Garg et al. (2025)

  • Carefully scaffolded activities that require students to compare, debug, or improve AI-generated code can reinforce conceptual understanding and strengthen engagement with core programming principles.

    “Carefully scaffolded activities that require students to compare, debug, or improve AI-generated code can reinforce conceptual understanding and strengthen engagement with core programming principles (Garg et al., 2025).”

    From Integrating Generative AI into Programming Education: Student Perceptions and the Challenge of Correcting AI Errors (2025) · cites this paper as Garg et al., 2025

  • Prior studies on GenAI integration in higher education have underscored the importance of scaffolding, transparent assessment criteria, and guided practice, demonstrating that the way GenAI tools are introduced critically shapes students' abilities to use them effectively.

    “Prior studies on GenAI integration in higher education have underscored the importance of scaffolding, transparent assessment criteria, and guided practice, demonstrating that the way GenAI tools are introduced critically shapes students' abilities to use them effectively (Garg et al., 2025;Usher, 2025).”

    From Integrating Generative AI into Programming Education: Student Perceptions and the Challenge of Correcting AI Errors (2025) · cites this paper as Garg et al., 2025

  • Garg et al. (2025) found that students who received explicit prompt training outperformed both those who used GenAI tools without guidance and those who relied solely on traditional internet search strategies.

    “For instance, Garg et al. (2025) found that students who received explicit prompt training outperformed both those who used GenAI tools without guidance and those who relied solely on traditional internet search strategies.”

    From Integrating Generative AI into Programming Education: Student Perceptions and the Challenge of Correcting AI Errors (2025) · cites this paper as Garg et al., 2025

Cites

Flagged first, then by citations

2 of the 57 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Related

Authors
Garg, A., Nisumba Soodhani, K., & Rajendran, R.
Affiliations
Indian Institute of Technology Bombay (IN)
ORCID
Venue
Computers and Education: Artificial Intelligence
Publisher
Elsevier BV
Published
2025-06
Volume
8
Pages
100380
ISSN
2666-920X (ISSN-L)
DOI
10.1016/j.caeai.2025.100380
OpenAlex
W4407319724
Cited by
49
References
57
Citations by year
2026: 36 · 2025: 13
FWCI
50.95
Type
journal article
Language
en
Open access
Licence
Locations
  • Computers and Education Artificial Intelligence (publishedVersion, cc-by-nc)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
  • Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
generative AI in education, prompt engineering, data analysis skills, programming skills, engineering students, large language models, few-shot prompting, Bloom's taxonomy, human-AI collaboration

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review