Short answer

Prioritize research and development of GenAI applications for requirements engineering and software design, while ensuring that all GenAI tools are developed with robust mechanisms for accuracy, transparency, and sustainability.

Field: Innovation & Design
Source: arXiv (Cornell University) (2023)
Method: Literature Review and Focus Groups
Evidence: Strong effect

Generative AI (GenAI) tools are rapidly integrating into software development, offering potential for automation and decision support across all project phases, though research is currently concentrated on implementation and quality assurance. This innovation & design research insight is drawn from a 2023 study published in arXiv (Cornell University). Using Literature review and focus groups, researchers explored how this design variable affects real-world outcomes. The key design takeaway: Prioritize research and development of GenAI applications for requirements engineering and software design, while ensuring that all GenAI tools are developed with robust mechanisms for accuracy, transparency, and sustainability.

Study

Innovation & DesignRecentStrong effect

Generative AI is Reshaping Software Engineering: A Research Agenda for Future Innovation

arXiv (Cornell University) · 2023

Key Findings

01GenAI can support automation and decision-making in all software development activities.
02Current research is heavily skewed towards software implementation, quality assurance, and maintenance.
03Areas like requirements engineering, software design, and software engineering education require more research attention.
04Key considerations for GenAI implementation include industry assessment, dependability, accuracy, data accessibility, transparency, and sustainability.

Application

Design takeaway

How to apply

When developing new software engineering tools or processes, consider how GenAI can be leveraged, and identify which stages of the development lifecycle are currently underserved by existing GenAI solutions.

Project actions

01When exploring GenAI for your design project, consider its potential beyond just code generation.
02Investigate how GenAI could assist in early-stage design activities like requirements gathering or conceptualization.

Method & Evidence

AimWhat are the current applications, limitations, and open challenges of Generative AI in software engineering, and what research agenda can guide future development?

MethodLiterature Review and Focus Groups

ProcedureA five-month literature review and focus group study was conducted to identify research questions and areas for GenAI in software engineering.

ContextSoftware Engineering

Variables

IV["Type of Generative AI tool","Software engineering activity (e.g., requirements, design, implementation, maintenance)"]

DV["Efficiency of the activity","Quality of the output","User satisfaction","Accuracy of AI suggestions"]

CV["Complexity of the software project","Experience level of the software engineer","Specific GenAI model used"]

Strengths & Limitations

Strengths

+Provides a comprehensive overview of GenAI in software engineering.
+Identifies specific research gaps and future directions.

Limitations

The rapid pace of AI development means that research findings can quickly become outdated.

Reliability & validity

The reliability of findings from focus groups can be enhanced through triangulation with literature review data. Validity is strengthened by the breadth of research questions identified across multiple software engineering areas.

Think critically

Given the current research bias towards implementation, how can designers proactively drive innovation in the application of GenAI to the earlier, more conceptual stages of software development?

Design Principles

"Embrace a holistic approach to GenAI integration in design, considering its impact across the entire product lifecycle and addressing critical factors like dependability and sustainability."

Understanding the current landscape and identifying research gaps in GenAI for software engineering is crucial for designers and engineers. This insight highlights areas ripe for innovation, such as requirements engineering and software design, and emphasizes the need to address critical considerations like accuracy, transparency, and sustainability in future tool development.

What This Means for Your Design

New AI tools can help write code and find bugs, but we need more research on how they can help with planning projects, designing systems, and teaching people about software.

How to use in your project

1.Reference this research to justify the exploration of novel AI applications in your design process, especially if focusing on areas like requirements engineering or system design.

Add to My Project

Quick Cite

Paragraph starter

The integration of Generative Artificial Intelligence (GenAI) into software engineering presents significant opportunities for innovation, as highlighted by research indicating its potential to automate and support decision-making across all development phases. However, current research focus remains predominantly on implementation and quality assurance, with less attention paid to crucial areas such as requirements engineering and software design. Future design projects can leverage this insight by exploring GenAI applications in these underserved domains, while critically evaluating and addressing the dependability, accuracy, transparency, and sustainability of these tools.

Source

arXiv (Cornell University)

Generative Artificial Intelligence for Software Engineering -- A Research Agenda

journal · 2023

View source

Questions About This Research

What does the research say about generative ai is reshaping software engineering: a research agenda for future innovation?: Prioritize research and development of GenAI applications for requirements engineering and software design, while ensuring that all GenAI tools are developed with robust mechanisms for accuracy, transparency, and sustainability. Evidence: arXiv (Cornell University) (2023).
Why does "Generative AI is Reshaping Software Engineering: A Research Agenda for Future Innovation" matter for design?: Understanding the current landscape and identifying research gaps in GenAI for software engineering is crucial for designers and engineers. This insight highlights areas ripe for innovation, such as requirements engineering and software design, and emphasizes the need to address critical considerations like accuracy, transparency, and sustainability in future tool development.
How can designers apply this research?: Prioritize research and development of GenAI applications for requirements engineering and software design, while ensuring that all GenAI tools are developed with robust mechanisms for accuracy, transparency, and sustainability.
What were the main findings?: GenAI can support automation and decision-making in all software development activities.. Current research is heavily skewed towards software implementation, quality assurance, and maintenance.. Areas like requirements engineering, software design, and software engineering education require more research attention.. Key considerations for GenAI implementation include industry assessment, dependability, accuracy, data accessibility, transparency, and sustainability.
What research method was used?: Literature Review and Focus Groups.
How strong is the evidence?: Evidence strength is rated Strong effect, based on a 2023 journal from arXiv (Cornell University).
What should I do differently in my next project?: When developing new software engineering tools or processes, consider how GenAI can be leveraged, and identify which stages of the development lifecycle are currently underserved by existing GenAI solutions.
What are the limitations?: The research agenda is based on a snapshot of current literature and focus group discussions, and the rapid evolution of GenAI may necessitate ongoing updates.