Short answer

Design learning experiences and tools that guide users to leverage LLMs as collaborators for complex tasks, rather than as shortcuts that bypass fundamental skill development.

Field: User-Centred Design
Source: Applied Sciences (2025)
Method: Literature Review and Case Study Analysis
Evidence: Moderate effect

The strategic integration of Large Language Models (LLMs) in computer science education requires careful consideration of their impact on foundational skill acquisition to ensure students develop robust problem-solving abilities. This user-centred design research insight is drawn from a 2025 study published in Applied Sciences. Using Literature review and case study analysis, researchers explored how this design variable affects real-world outcomes. The key design takeaway: Design learning experiences and tools that guide users to leverage LLMs as collaborators for complex tasks, rather than as shortcuts that bypass fundamental skill development.

Study

User-Centred DesignNew This WeekModerate effect

LLM Integration in Computer Science: Balancing Skill Development with AI Assistance

Applied Sciences · 2025

Key Findings

01LLMs offer significant potential to enhance learning and development tools for computer science students.
02Over-reliance on LLMs can hinder the development of essential foundational skills in programming and problem-solving.
03Clear guidelines and strategies are needed to regulate LLM use and uphold academic integrity.
04Balancing AI assistance with active learning is critical for producing competent and ethical software professionals.

Application

Design takeaway

Design learning experiences and tools that guide users to leverage LLMs as collaborators for complex tasks, rather than as shortcuts that bypass fundamental skill development.

How to apply

When designing educational modules or professional training, create assignments that require students to critically evaluate, refine, and integrate LLM-generated outputs, rather than simply accepting them.

Project actions

01When using LLMs for research or coding assistance, document exactly how you used them and why.
02Focus on projects where LLMs can help with complex or tedious parts, freeing you up to concentrate on the core design or problem-solving aspects.

Method & Evidence

AimWhat are the ethical challenges and strategic solutions for integrating Large Language Models (LLMs) into computer science education to balance AI assistance with foundational skill development?

MethodLiterature Review and Case Study Analysis

ProcedureThe study involved a comprehensive review of existing literature on LLM use in education and an analysis of guidelines from global institutions regarding AI integration. It also drew upon practical teaching experiences in computer science.

ContextComputer Science Education

Variables

IV["Level of LLM integration (e.g., free use, guided use, no use)","Type of computer science task (e.g., algorithm design, debugging, documentation)"]

DV["Student's foundational skill proficiency (e.g., problem-solving, debugging ability)","Quality and originality of the final output","Student's perceived learning and confidence"]

CV["Student's prior experience with programming","Complexity of the assigned task","Specific LLM tool used"]

Strengths & Limitations

Strengths

+Addresses a highly relevant and current issue in technical education.
+Provides a balanced perspective on the benefits and drawbacks of LLM integration.

Limitations

The rapid pace of AI development means that any specific LLM used in a project might be outdated by the time of review. The effectiveness of LLMs can also vary greatly depending on the specific task and the user's prompt engineering skills.

Reliability & validity

The reliability of findings may be affected by the variability in student prompt engineering skills and the constantly evolving nature of LLMs. Validity could be enhanced by using standardized skill assessments and diverse task types.

Think critically

To what extent does the reliance on LLMs for generating code or design solutions stifle a student's ability to debug, innovate, or adapt to novel challenges not covered by the AI's training data?

Design Principles

"Augment, don't automate, core skill acquisition."

As LLMs become more prevalent, design practitioners must understand how to leverage these tools without compromising the development of core competencies. This is crucial for creating educational pathways and professional development programs that foster both innovation and fundamental expertise.

What This Means for Your Design

Using AI like ChatGPT for coding can be helpful, but it's important to make sure you still learn the basics yourself, otherwise, you might not become a good programmer.

How to use in your project

1.Discuss the ethical considerations of using AI tools in your design process and how you navigated them.
2.Justify your decision to use or not use LLMs for specific tasks, explaining the impact on your learning and the final outcome.

Add to My Project

Quick Cite

Paragraph starter

The integration of Large Language Models (LLMs) into technical design projects presents a dual challenge: harnessing their power for efficiency while safeguarding the development of fundamental skills. This research highlights the necessity of establishing clear protocols for LLM usage, ensuring that AI serves as a collaborative tool that augments, rather than replaces, critical thinking and core competency acquisition. By thoughtfully structuring design tasks and learning objectives, practitioners can leverage LLMs to enhance complex problem-solving without compromising the foundational expertise required for robust and ethical design.

Source

Applied Sciences

Large Language Models in Computer Science Classrooms: Ethical Challenges and Strategic Solutions

journal · 2025

View source

Questions About This Research

What does the research say about llm integration in computer science: balancing skill development with ai assistance?: Design learning experiences and tools that guide users to leverage LLMs as collaborators for complex tasks, rather than as shortcuts that bypass fundamental skill development. Evidence: Applied Sciences (2025).
Why does "LLM Integration in Computer Science: Balancing Skill Development with AI Assistance" matter for design?: As LLMs become more prevalent, design practitioners must understand how to leverage these tools without compromising the development of core competencies. This is crucial for creating educational pathways and professional development programs that foster both innovation and fundamental expertise.
How can designers apply this research?: Design learning experiences and tools that guide users to leverage LLMs as collaborators for complex tasks, rather than as shortcuts that bypass fundamental skill development.
What were the main findings?: LLMs offer significant potential to enhance learning and development tools for computer science students.. Over-reliance on LLMs can hinder the development of essential foundational skills in programming and problem-solving.. Clear guidelines and strategies are needed to regulate LLM use and uphold academic integrity.. Balancing AI assistance with active learning is critical for producing competent and ethical software professionals.
What research method was used?: Literature Review and Case Study Analysis.
How strong is the evidence?: Evidence strength is rated Moderate effect, based on a 2025 journal from Applied Sciences.
What should I do differently in my next project?: When designing educational modules or professional training, create assignments that require students to critically evaluate, refine, and integrate LLM-generated outputs, rather than simply accepting them.
What are the limitations?: The rapid evolution of LLM technology means that guidelines and strategies may need continuous updating. The study's findings are primarily based on existing literature and expert opinion, with limited empirical data on long-term student outcomes.