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

2026-03-15

AI Summary

Current autonomous coding assistants often reduce software engineers’ cognitive engagement, fostering overreliance and cognitive passivity. This study addresses this issue through a qualitative user investigation involving task observations and interviews, systematically uncovering—for the first time—a persistent decline in cognitive investment during human-AI collaboration. It further identifies a critical gap in existing tools: the absence of interaction mechanisms that support reflection, validation, and sensemaking. Grounded in cognitive science and human-computer interaction theories, this work proposes a paradigm shift—reconceptualizing AI assistants from mere “task executors” to “thinking tools.” By integrating cognitive forcing functions to sustain deep reasoning, the research articulates actionable design opportunities that effectively enhance engineers’ cognitive engagement in AI-assisted programming.

Technology Category

• Humans and AI: Human-Computer Interaction
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Intelligent Robots: Cognitive Robotics

Application Category

• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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 are rapidly becoming embedded in everyday development workflows. Since software engineers 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 agentic coding assistant. Our findings reveal that cognitive engagement consistently declines as tasks progress, and that current agentic coding assistants' designs provide limited affordances for reflection, verification, and meaning-making. Based on these findings, e identify concrete design opportunities leveraging richer interaction modalities and cognitive-forcing mechanisms to sustain engagement and promote deeper thinking in AI-assisted programming.

Problem

• cognitive engagement
• agentic AI
• software engineering
• over-reliance
• sensemaking

Innovation

• agentic coding assistants
• cognitive engagement
• Tools for Thought
• cognitive-forcing mechanisms
• sensemaking