Using Biometrics to Understand AI-Assisted Coding Performance and its Perception

📰 ArXiv cs.AI

Learn how biometrics can measure AI-assisted coding performance and perception, and why it matters for software development

advanced Published 23 Jun 2026

Action Steps

Collect electroencephalography data using EEG sensors to measure cognitive load
Use eye-tracking software to analyze gaze patterns and attention
Apply machine learning algorithms to electrodermal activity data to detect emotional responses
Configure a within-subjects crossover design for a multisite study
Test the effectiveness of AI-assisted coding tools using biometric metrics

Who Needs to Know This

Software engineers, AI researchers, and product managers can benefit from understanding how AI-assisted coding affects developers' cognitive processes, to improve tool design and development workflows

Key Insight

💡 Biometrics can provide valuable insights into how AI-assisted coding affects developers' cognitive processes, enabling more effective tool design and development workflows

Key Takeaways

Learn how biometrics can measure AI-assisted coding performance and perception, and why it matters for software development

Full Article

Title: Using Biometrics to Understand AI-Assisted Coding Performance and its Perception

Abstract:
arXiv:2606.20598v1 Announce Type: cross Abstract: AI-based code assistants are transforming software development, yet we lack empirical evidence on how they affect developers' cognitive processes. We present a multisite study investigating the neurophysiological correlates of AI-assisted programming through a within-subjects crossover design. We recruited participants at two universities (Bari, Italy, and Copenhagen, Denmark) and collected electroencephalography, eye-tracking, electrodermal acti

Read full paper → ← Back to Reads