AI · Empirical study/review of generative-AI use in software engineering

Copiloting the future: How generative AI transforms Software Engineering

Information and Software Technology · 2025

Leonardo Banh, Florian Holldack, Gero Strobel

Summary

Examines how generative AI changes software-engineering work and developer productivity.

For your marketing

Possible founder application

Pilot AI assistance with measurement of task completion, review rework, defects, security, and learning—not speed alone.

Reported result

What the study found

Examines how generative AI changes software-engineering work and developer productivity.

Research question

What the authors investigated

How does the study’s stated design explain its reported outcome in this setting?

Design

Empirical study/review of generative-AI use in software engineering

Sample and setting

Software developers using GitHub Copilot and related tools; abstract-only

Scope and transfer

Limitations to keep in view

Rapidly changing tools and early evidence limit long-term conclusions.

Research sources

abstract_only

Study strength

3.5/5 Abstract-level evidence is useful for framing questions; verify full methods before transfer.

How this was assessed

The 1–5 evidence-check score is a practical reading aid, not a formal peer review or a probability that a conclusion is true. It combines design strength (2 points), sample reporting (1), comparison/control clarity (1), and how much of the paper could be checked (1). Access affects how confidently this directory can assess a study, not the study's underlying quality. Blinding is reported separately because it is not relevant to every design.

Design transparency · 2/2

Based on the reported study design in the retrieved source.

Sample and setting · 1/1

The sample context is stated; a numerical count is preserved only when reported.

Outcome clarity · 1/1

The finding is summarized from publisher or article metadata.

Access for checking · 0.5/1

Only abstract or bibliographic access was confirmed.

Double-blind? The retrieved publisher record does not establish whether participants or outcome assessors were blinded.