How Software Engineers Engage with AI: A Pragmatic Workflow

TL;DR

This paper introduces a pragmatic workflow and decision model for software engineers to effectively and confidently incorporate AI tools like GitHub Copilot and ChatGPT into their development processes, enhancing decision-making and quality.

Contribution

It presents a novel, structured workflow and decision model based on field observations, guiding engineers in iterative AI use during software development.

Findings

The workflow improves decision clarity when using AI tools.

Field observations validate the workflow's practical applicability.

Engineers can better manage AI-generated artifacts with structured guidance.

Abstract

Artificial Intelligence (AI) tools such as GitHub Copilot and ChatGPT are increasingly used in software engineering (SE) for tasks such as code, test, and documentation generation. However, engineers often face uncertainty about when to trust, refine, or discard AI-generated artifacts. We present a pragmatic workflow, complemented by a four-quadrant decision model, that formalizes how developers iteratively prompt, inspect, refine, and, when needed, fall back to manual work. The workflow and decision model were derived from a grey literature review and field observations across three industrial settings in T\"urkiye and Azerbaijan. Two real-world scenarios demonstrate the workflow's practical value, showing how engineers navigate key decision points when using AI. Our approach offers lightweight, structured guidance to support more deliberate and quality-aware use of AI tools in everyday SE tasks.