"I'm Not Reading All of That": Understanding Software Engineers' Level of Cognitive Engagement with Agentic Coding Assistants

TL;DR

This study investigates how software engineers interact cognitively with agentic coding assistants, revealing declining engagement over tasks and highlighting design improvements for fostering deeper reasoning and reflection.

Contribution

It provides empirical insights into engineers' cognitive engagement with ACAs and proposes design opportunities to enhance human-AI collaboration in programming.

Findings

Cognitive engagement declines as tasks progress.

Current ACAs offer limited support for reflection and verification.

Design opportunities include richer interactions and cognitive-forcing mechanisms.

Abstract

Over-reliance on AI systems can undermine users' critical thinking and promote complacency, a risk intensified by the emergence of agentic AI systems that operate with minimal human involvement. In software engineering, agentic coding assistants (ACAs) are rapidly becoming embedded in everyday development workflows. Since software engineers (SEs) create systems deployed across diverse and high-stakes real-world contexts, these assistants must function not merely as autonomous task performers but as Tools for Thought that actively support human reasoning and sensemaking. We conducted a formative study examining software engineers' cognitive engagement and sensemaking processes when working with an ACA. Our findings reveal that cognitive engagement consistently declines as tasks progress, and that current ACA designs provide limited affordances for reflection, verification, and meaning-making. Based on these findings, we identify concrete design opportunities leveraging richer interaction modalities and cognitive-forcing mechanisms to sustain engagement and promote deeper thinking in AI-assisted programming.