Developers' Experience with Generative AI -- First Insights from an Empirical Mixed-Methods Field Study

TL;DR

This study explores developers' experiences with Generative AI in real work environments, revealing how different interaction modes affect efficiency, accuracy, and workload through a mixed-methods approach.

Contribution

It demonstrates a feasible mixed-method study design and provides initial insights into developers' subjective and behavioral responses to GenAI interactions.

Findings

Moderate use of in-code suggestions or chat prompts improves efficiency and reduces workload.

Chat interactions enhance task accuracy.

Excessive or combined use diminishes benefits.

Abstract

With the rise of AI-powered coding assistants, firms and programmers are exploring how to optimize their interaction with them. Research has so far mainly focused on evaluating output quality and productivity gains, leaving aside the developers' experience during the interaction. In this study, we take a multimodal, developer-centered approach to gain insights into how professional developers experience the interaction with Generative AI (GenAI) in their natural work environment in a firm. The aim of this paper is (1) to demonstrate a feasible mixed-method study design with controlled and uncontrolled study periods within a firm setting, (2) to give first insights from complementary behavioral and subjective experience data on developers' interaction with GitHub Copilot and (3) to compare the impact of interaction types (no Copilot use, in-code suggestions, chat prompts or both in-code suggestions and chat prompts) on efficiency, accuracy and perceived workload whilst working on different task categories. Results of the controlled sessions in this study indicate that moderate use of either in-code suggestions or chat prompts improves efficiency (task duration) and reduces perceived workload compared to not using Copilot, while excessive or combined use lessens these benefits. Accuracy (task completion) profits from chat interaction. In general, subjective perception of workload aligns with objective behavioral data in this study. During the uncontrolled period of the study, both higher cognitive load and productivity were perceived when interacting with AI during everyday working tasks. This study motivates the use of comparable study designs, in e.g. workshop or hackathon settings, to evaluate GenAI tools holistically and realistically with a focus on the developers' experience.