Beyond Autocomplete: Designing CopilotLens Towards Transparent and Explainable AI Coding Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Runlong, Zhang, Zeling, Almazroua, Boushra, Liut, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915505609113600
author Ye, Runlong
Zhang, Zeling
Almazroua, Boushra
Liut, Michael
author_facet Ye, Runlong
Zhang, Zeling
Almazroua, Boushra
Liut, Michael
contents AI-powered code assistants are widely used to generate code completions, significantly boosting developer productivity. However, these tools typically present suggestions without explaining their rationale, leaving their decision-making process inscrutable. This opacity hinders developers' ability to critically evaluate outputs, form accurate mental models, and calibrate trust in the system. To address this, we introduce CopilotLens, a novel interactive framework that reframes code completion from a simple suggestion into a transparent, explainable interaction. CopilotLens operates as an explanation layer that reconstructs the AI agent's "thought process" through a dynamic, two-level interface. The tool aims to surface both high-level code changes and the specific codebase context influences. This paper presents the design and rationale of CopilotLens, offering a concrete framework and articulating expectations on deepening comprehension and calibrated trust, which we plan to evaluate in subsequent work.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20062
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Autocomplete: Designing CopilotLens Towards Transparent and Explainable AI Coding Agents
Ye, Runlong
Zhang, Zeling
Almazroua, Boushra
Liut, Michael
Human-Computer Interaction
Artificial Intelligence
AI-powered code assistants are widely used to generate code completions, significantly boosting developer productivity. However, these tools typically present suggestions without explaining their rationale, leaving their decision-making process inscrutable. This opacity hinders developers' ability to critically evaluate outputs, form accurate mental models, and calibrate trust in the system. To address this, we introduce CopilotLens, a novel interactive framework that reframes code completion from a simple suggestion into a transparent, explainable interaction. CopilotLens operates as an explanation layer that reconstructs the AI agent's "thought process" through a dynamic, two-level interface. The tool aims to surface both high-level code changes and the specific codebase context influences. This paper presents the design and rationale of CopilotLens, offering a concrete framework and articulating expectations on deepening comprehension and calibrated trust, which we plan to evaluate in subsequent work.
title Beyond Autocomplete: Designing CopilotLens Towards Transparent and Explainable AI Coding Agents
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2506.20062