Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

InterPilot: Exploring the Design Space of AI-assisted Job Interview Support for HR Professionals

Zhengtao Xu, Zimo Xia, Zicheng Zhu, Nattapat Boonprakong, Yu-An Chen, Rabih Zbib, Casimiro Pio Carrino, Yi-Chieh Lee

TL;DR

InterPilot is a prototype system that augments interviews through intelligent note-taking and post-interview summary, adaptive question generation, and real-time skill-evidence mapping, and implications for designing future real-time human-AI collaboration in professional settings are discussed.

Abstract

Recruitment interviews are cognitively demanding interactions in which interviewers must simultaneously listen, evaluate candidates, take notes, and formulate follow-up questions. To better understand these challenges, we conducted a formative study with eight HR professionals, from which we derived key design goals for real-time AI support. Guided by these insights, we developed InterPilot, a prototype system that augments interviews through intelligent note-taking and post-interview summary, adaptive question generation, and real-time skill-evidence mapping. We evaluated the system with another seven HR professionals in mock interviews using a within-subjects design. Results show that InterPilot reduced documentation burden without increasing overall workload, but introduced usability trade-offs related to visual attention and interaction complexity. Qualitative findings further reveal tensions around trust and verification when AI suggests highly specific technical questions. We discuss implications for designing future real-time human-AI collaboration in professional settings, highlighting the need to balance assistance granularity, attentional demands, and human agency.

InterPilot: Exploring the Design Space of AI-assisted Job Interview Support for HR Professionals

TL;DR

InterPilot is a prototype system that augments interviews through intelligent note-taking and post-interview summary, adaptive question generation, and real-time skill-evidence mapping, and implications for designing future real-time human-AI collaboration in professional settings are discussed.

Abstract

Recruitment interviews are cognitively demanding interactions in which interviewers must simultaneously listen, evaluate candidates, take notes, and formulate follow-up questions. To better understand these challenges, we conducted a formative study with eight HR professionals, from which we derived key design goals for real-time AI support. Guided by these insights, we developed InterPilot, a prototype system that augments interviews through intelligent note-taking and post-interview summary, adaptive question generation, and real-time skill-evidence mapping. We evaluated the system with another seven HR professionals in mock interviews using a within-subjects design. Results show that InterPilot reduced documentation burden without increasing overall workload, but introduced usability trade-offs related to visual attention and interaction complexity. Qualitative findings further reveal tensions around trust and verification when AI suggests highly specific technical questions. We discuss implications for designing future real-time human-AI collaboration in professional settings, highlighting the need to balance assistance granularity, attentional demands, and human agency.
Paper Structure (16 sections, 2 figures, 1 table)

This paper contains 16 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Formative Study
  3. InterPilot System
  4. User Evaluation Study
  5. Study Design and Measurements
  6. Results
  7. Mental Workload and Usability Trade-offs
  8. Scaffolding Question Depth & Breadth
  9. Enhancing Objectivity with Evidence
  10. Discussion
  11. Balancing AI Support and Attention Demand
  12. Bridging the Verification Gap: From Scripting to Diagnosis
  13. Limitations and Future Work
  14. Statistical Summary
  15. System Implementation
  16. ...and 1 more sections

Figures (2)

  • Figure 1: Overview of InterPilot system interface. The system supports HR professionals' interview workflow through three main components: (A) Intelligent Note-taking & Summary, (B) Adaptive Question Generation, and (C) Real-time Skill & Evidence Mapping. Sub-labels (e.g., A.1, B.1) correspond to specific features detailed in Section \ref{['sec:user_interface']}.
  • Figure 2: Example interviewer view during a mock interview session. The left panel shows the video conferencing platform (e.g., Zoom), while the right panel displays the InterPilot interface.