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

arXiv: https://arxiv.org/abs/2510.11516 · HTML: https://mlsanity.com/paper/2510.11516/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [Productivity Assessment of Neural Code Completion](https://mlsanity.com/paper/2205.06537/) (2022)
- [A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges](https://mlsanity.com/paper/2303.17125/) (2023)
- [Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces](https://mlsanity.com/paper/2309.14459/) (2023)
- [How Novices Use LLM-Based Code Generators to Solve CS1 Coding Tasks in a Self-Paced Learning Environment](https://mlsanity.com/paper/2309.14049/) (2023)
- [What's Wrong with Your Code Generated by Large Language Models? An Extensive Study](https://mlsanity.com/paper/2407.06153/) (2024)
- [Designing for Responsible Trust in AI Systems: A Communication Perspective](https://mlsanity.com/paper/2204.13828/) (2022)
- [In-IDE Code Generation from Natural Language: Promise and Challenges](https://mlsanity.com/paper/2101.11149/) (2021)
- [Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions](https://mlsanity.com/paper/2308.02312/) (2023)
- [Investigating and Designing for Trust in AI-powered Code Generation Tools](https://mlsanity.com/paper/2305.11248/) (2023)
- [AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation](https://mlsanity.com/paper/2305.12050/) (2023)
- [A Study on Developer Behaviors for Validating and Repairing LLM-Generated Code Using Eye Tracking and IDE Actions](https://mlsanity.com/paper/2405.16081/) (2024)

## Abstract (arXiv)

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 .