Work

Cracking CodeWhisperer: Analyzing Developers' Interactions and Patterns During Programming Tasks

Year: 2025

Type: preprint

Abstract: The use of AI code-generation tools is becoming increasingly common, making it important to understand how software developers are adopting these tools. In this study, we investigate how developers engage with Amazon's CodeWhisperer, an LLM-based code-generation tool. We conducted two user studies with two groups of 10 participants each, interacting with CodeWhisperer - the first to understand which interactions were critical to capture and the second to collect low-level interaction data using a custom telemetry plugin. Our mixed-methods analysis identified four behavioral patterns: 1) incremental code refinement, 2) explicit instruction using natural language comments, 3) baseline structuring with model suggestions, and 4) integrative use with external sources. We provide a comprehensive analysis of these patterns .

Source: arXiv (Cornell University)

Authors: Javahar, Jeena, Budhrani, Tanya, Basha, Manaal, de Souza, Cleidson R. B., Beschastnikh, Ivan, Rodriguez-Perez, Gema

Institutions: University of British Columbia, Universidade Federal do Pará

Language: English

Topic: Software Engineering Research

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Conselho Nacional de Desenvolvimento Científico e Tecnológico

OpenAlex ID: W7091186576

Cites:

Cited by:

Related to: