Agentic education · Learning science

Actionable companion · Learning design & outcomes

Learning with agency: Integrating DeepL Write and Claude AI to enhance argumentative writing competence of engineering students in India

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.

Read original paperSearch paper agentCC BY 4.0

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): Higher education. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

Abstract Introduction Artificial intelligence (AI) tools are increasingly applied to support second language writing. However, empirical research examining their potential to enhance the argumentative writing skills of STEM engineering students, particularly in the English as a Second Language (ESL) context in India, remains limited and requires more exploration. Method This study employed a quasi-experimental mixed-method design to investigate the effectiveness of two AI tools, DeepL Write and Claude AI, in improving argumentative writing among 40 first-year engineering students at a private university in Chennai, India. The Toulmin model of argumentation-based rubric was used to analyse the argumentative essays written by participants before and after the intervention using the AI tools. In the quantitative phase, paired-sample t-test and one-way ANOVA were employed to analyse differences in the pre-test and post-test essay scores. These results were further explained through comparative analysis of the essay scripts (n = 40) and thematic coding of participants’ semi-structured interview data (n = 23) in the qualitative phase. Results The quantitative results demonstrate significant improvement in the AW skills of the participants (t = −43.72; df = 39; p-value 0.05). The findings also indicated uniform improvements across all Toulmin components. The comparative analysis of the essays evidences the development of claims, data, warrants, backing and rebuttals, as well as improvements in linguistic features such as grammar, sentence structure and vocabulary. The thematic coding of the interview data yielded six themes related to perceived writing development, meta-cognitive awareness and the challenges and limitations of the tools. Discussion The findings indicate the pedagogical potential of integrating DeepL Write and Claude AI to improve argumentative writing skills of Indian ESL Engineering students. The findings also highlight the effectiveness of AI tools in improving linguistic features in students’ writing. By fostering responsible and informed use of digital technology in education, this study aligns with the Sustainable Development Goal (SDG) 4 (Quality Education). Keywords: argumentative writing, Claude AI, DeepL Write, English as a Second Language, STEM education, Sustainable Development Goal 4, Toulmin argumentation model

What kind of evidence is this?

Supporting AI learning science · Comparative / pre-post study reported

Stage: Higher education. 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

The thematic analysis of the interview transcripts identified 6 themes; Language Accuracy and Fluency, Writing Ease and Efficiency, Idea Generation and Content Development, Writing Style and Professionalism, Meta-Cognitive Awareness and Learning, Challenges and Limitations. The initial coding obtained 17 subthemes, which were then consolidated into the six primary themes. The themes, subthemes and sample excerpt from participant responses are given in Table 6.

Limitations and uncertainty · source passage

Although this study’s findings contributed many insights regarding the applications of AI tools in AW and related improvements in the second language of the participants, it is important to acknowledge the several limitations of this study while interpreting the results. Most importantly, the study used a relatively small sample collected from an institution in Chennai, Tamil Nadu, and was conducted over a short intervention period which might hinder the generalisability of the findings. Further research should investigate the long-term impacts of DeepL Write and Claude AI on a larger sample and examine the benefit of these tools across various writing genres and disciplines. Additionally, this study did not consider individual differences in L2 proficiency or first language of the participants that might have influenced the responsiveness to the tools. The study acknowledges that the observed improvements might have been influenced by focused instruction and repeated writing practice of argumentative essays. As a result, the study findings should be interpreted as evidence of the role of these AI tools as pedagogical assistants, and not as their independent effect. Moreover, this study did not explore how the use of these AI tools might improve the critical thinking of participants, despite the close relationship between critical thinking and AW. Further research could also examine the role of teacher mediation in guiding students’ engagement with these tools. Finally, the limitations of AI tools necessitate careful scaffolding, critical digital literacy and a balance between technological aid and learners’ independence.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

  • Specify a measurable learning objective, a comparator and a task without tool assistance before adopting a system.

A 90-day district pilot

  1. 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.
  2. Days 16–30 · Design. Choose one disciplinary task. Require a first attempt, a documented AI consultation, a critique of the output and an independent explanation. Align the comparison group and scoring rubric with the same objective. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. 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.
  4. Days 61–90 · Decide. Blind-score reasoning and accuracy on a new task without AI. Distinguish model examination scores, student perceptions and actual learner gains; only the last directly tests educational benefit. 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

T J Divya; C Alamelu. Integrating DeepL Write and Claude AI to enhance argumentative writing competence of engineering students in India. Frontiers in Artificial Intelligence (2026-06-02). https://doi.org/10.3389/frai.2026.1838463

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.