Skip to main content

AI Interview Studio — Recruiter Guide

The XeCubes AI Interview Studio lets you design, configure, and launch autonomous real-time voice and video technical interviews. The AI interviewer adapts questions dynamically, executes code in sandboxes, and generates comprehensive candidate scorecards.

How It Works​

sequenceDiagram
    autonumber
    actor Recruiter as Recruiter Dashboard
    participant Config as Interview Template
    actor Candidate as Candidate Browser
    participant Gateway as WebRTC Media Gateway
    participant AI as Realtime AI Interview Engine
    participant CodeBox as XEtest Sandbox

    Recruiter->>Config: Create Interview Template
    Recruiter->>Candidate: Send Interview Invitation
    Candidate->>Gateway: Connect WebRTC (Audio / Video / Screen)
    Gateway->>AI: Stream PCM Audio & Video Frames
    AI->>Candidate: Synthesized Voice Question (TTS, sub-350ms latency)
    Candidate->>Gateway: Candidate Answers Audio & Code
    Candidate->>CodeBox: Execute Code Snippet
    CodeBox-->>AI: Unit Test Results & Execution Output
    AI->>Candidate: Dynamic Follow-up Question
    Candidate->>Gateway: Session Completed
    AI->>Recruiter: Dispatches Scored Transcript & Video Highlights

Creating an Interview Template​

  1. Navigate to AI Interviews → Templates → Create New.
  2. Configure the template:
SettingDescription
Template Namee.g., "Senior Backend Engineer - System Design"
Competency AreasSelect from: System Design, Algorithms, Communication, Domain Knowledge, Leadership
Difficulty ProgressionAuto-escalate, Fixed, or Adaptive based on candidate responses
Duration15, 30, 45, or 60 minutes
Voice PersonaProfessional, Friendly, Technical
Code SandboxEnable/disable live coding with language restrictions
Proctoring LevelStandard (webcam + tab blur) or Strict (+ screen recording + audio anomaly)
  1. Save the template and attach it to one or more jobs.

Launching Interviews​

  • Individual: From a candidate's profile, click Schedule AI Interview and select a template.
  • Bulk: In the pipeline view, select multiple candidates and choose Bulk Schedule AI Interview.
  • Auto-trigger: Configure jobs to automatically send AI interview invitations when candidates pass the screening stage.

Reviewing Results​

After interview completion, the recruiter receives:

OutputDescription
Holistic ScoreWeighted average (0–100%) calibrated to role seniority.
Competency HeatmapVisual breakdown across all evaluated competency areas.
Full TranscriptSearchable verbatim text linked to time-stamped video replay clips.
Code SubmissionsAll code written during the interview with test results and complexity analysis.
Integrity ReportProctoring telemetry: face detection events, tab switches, paste operations.
AI RecommendationClear hire / no-hire justification with highlighted strengths and flags.

Best Practices​

  • Calibrate rubrics per role seniority — junior roles should weight code correctness higher, senior roles should weight system design.
  • Review transcripts for candidates near the decision boundary to catch nuances the score alone might miss.
  • Enable proctoring for remote assessments to maintain assessment integrity.