Publications & Research

Experiments with generative AI technologies in everyday IT engineering tasks

View on GitHub

Publications & Research

Documentation of our research findings, publications, and insights from our generative AI experiments.

Research Papers & Articles

Publications will be listed here as they become available.

Planned Publications

We are working on documenting our findings in the following areas:

  • AI-Assisted Software Development: Patterns and practices for effective AI integration in coding workflows
  • Administrative Automation with AI: Case studies in using generative AI for routine task automation
  • Educational Technology Enhancement: Applications of AI in learning and assessment tools
  • Quality Assurance in AI-Generated Content: Methods for validating and improving AI outputs

Technical Reports

Ongoing Documentation

Our technical findings are continuously documented in our project repositories:

  • Project READMEs: Each project contains detailed documentation of approaches and results
  • Experiment Logs: Regular updates on what we’re learning from our AI experiments
  • Best Practices Guides: Evolving documentation of effective AI usage patterns
  • Tool Evaluations: Assessments of different AI tools and their effectiveness

Research Areas

1. Prompt Engineering

  • Effective strategies for different types of tasks
  • Context optimization techniques
  • Multi-turn conversation patterns

2. AI Tool Integration

  • Workflow integration patterns
  • Tool selection criteria
  • Performance benchmarking

3. Quality Control

  • Validation methodologies for AI-generated content
  • Error detection and correction strategies
  • Human-AI collaboration models

4. Ethical Considerations

  • Responsible AI usage guidelines
  • Transparency and accountability measures
  • Privacy and security considerations

Conference Presentations

Future presentations will be listed here.

Potential Venues

We are considering sharing our work at:

  • Academic Conferences: Software engineering, AI, and educational technology conferences
  • Industry Events: Developer conferences and AI/ML meetups
  • Educational Forums: Teaching and learning technology symposiums
  • Open Source Communities: GitHub, developer community events

Datasets & Resources

Open Source Contributions

All our code and documentation is available under open source licenses:

  • Project Repositories: Complete source code with documentation
  • Templates and Tools: Reusable components for AI-assisted development
  • Experimental Data: Anonymized results from our experiments (where appropriate)
  • Best Practices Documentation: Guidelines and patterns we’ve developed

Research Data

Datasets and research materials will be made available as appropriate, following ethical guidelines and privacy requirements.

How to Cite Our Work

General Citation

Learning AI Project Team. (2025). Experiments in Generative AI for IT Engineering Tasks. 
GitHub Repository: https://github.com/csorbakristof/learning_ai

Project-Specific Citations

For citing specific projects or tools:

Learning AI Project Team. (2025). [Project Name]. 
Available at: https://github.com/csorbakristof/learning_ai/tree/master/[ProjectDirectory]

BibTeX Format

@misc{learningai2025,
  title={Experiments in Generative AI for IT Engineering Tasks},
  author=,
  year={2025},
  howpublished={\url{https://github.com/csorbakristof/learning_ai}},
  note={Accessed: [Date]}
}

Collaboration & Research Partnerships

Academic Collaboration

We welcome collaboration with:

  • Research Institutions: Universities and research labs working on AI applications
  • Industry Partners: Companies interested in practical AI implementation studies
  • Open Source Communities: Projects working on similar AI-assisted development tools

Contributing to Research

You can contribute to our research efforts by:

  • Participating in Experiments: Try our tools and provide feedback
  • Sharing Use Cases: Document your own AI-assisted development experiences
  • Code Contributions: Improve our tools and methodologies
  • Documentation: Help us document findings and best practices

Contact for Research Inquiries

For research collaboration, questions about our methodologies, or to discuss potential partnerships:

  • GitHub Issues: Use the “research” label for research-related discussions
  • Email: [Contact information to be added]
  • Academic Networks: [Professional profiles to be added]

Research Ethics

Principles

Our research follows these principles:

  • Transparency: Open documentation of methods and findings
  • Reproducibility: Providing sufficient detail for others to replicate our work
  • Ethical AI Use: Responsible development and deployment of AI technologies
  • Community Benefit: Sharing knowledge to benefit the broader community

Data and Privacy

  • All shared data is anonymized and follows privacy guidelines
  • Sensitive information is never included in public repositories
  • We respect intellectual property and licensing requirements
  • User consent is obtained for any data collection

This page will be updated as our research progresses and publications become available.