XERPIUM AI INTERVIEW — Rekrutmen AI

Ringkasan

Ekosistem Rekrutmen AI

XERPIUM AI INTERVIEW adalah solusi rekrutmen berbasis AI — mencakup CV screening otomatis (skor 0-15, bias redaction, rekomendasi), adaptive AI interview (backend-governed, difficulty scoring, 9-level recommendation, risk flags), dan candidate portal self-service.

📝

CV SCREEN

Otomatis & Tanpa Bias

🎤

INTERVIEW

Adaptive AI Engine

📊

SCORING

9-Level Recomendation

🌐

PORTAL

Candidate Self-Service

CV Screening

AI CV Screening Engine

📝 Screening Pipeline

Pipeline — Extract → Normalize → Strip Bias → Token Safety → LLM → Parse → Decide → Save
6-State Analysis — Pending → Processing → Completed / Partial / API Failed / Extraction Failed
File Support — PDF via pdfplumber (primary), PyPDF2 (fallback); DOCX via python-docx; .doc via latin-1
Token Limit — 4000 character safety limit per section
Retry — Max 3 retries per LLM call; safe retry with cached extracted text (no re-extraction)
Partial Result — Missing JSON keys filled from defaults, never drops valid fields

🔎 Scoring & Recommendation

3 Dimensions — Experience (0-5), Skill (0-5), Education (0-5) = Total (0-15)
Confidence Index — 0.0 - 1.0 with label: High Fit, Moderate Fit, Low Fit
Recommendation — Recommended (≥12), Review (≥8), Reject (<8)
Backend Override — System forces recommendation based on score, not just LLM output
Summary — Executive summary, strengths, weaknesses, HR insight, interview focus area
Auto Interview — Button to auto-create interview invitation for recommended/review candidates

🔒 Bias Redaction

Auto-Stripped — Email, phone number, gender, religion, age, photo — semua dihapus sebelum LLM
Section-Aware — Token limit diterapkan per section CV, bukan per total
Structured Log — Operation log dalam JSON untuk audit
Partial Mode — Jika LLM gagal sebagian, backend tetap melanjutkan dengan data valid
Retry Analysis — Analisis ulang dengan tombol action (safe — pakai cached text)
Bias-Free Scoring — Skor murni berdasarkan kompetensi dan pengalaman

📋 Applicant Integration

hr.applicant — Extended dengan AI fields: ai_cv_score, ai_cv_recommendation, ai_cv_confidence
Processed Flag — ai_cv_processed: sudah diproses atau belum
Auto Button — action_process_ai_cv_review() — satu klik proses CV
AI Summary — Executive summary, strengths/weaknesses, HR insight
Interview Focus — ai_interview_focus_area — rekomendasi topik interview
Status — Processing status per applicant, real-time feedback

AI Interview

Adaptive AI Interview Engine

🎤 Interview Engine

Adaptive Loop — Backend-governed: LLM = text generation only; Backend = ALL decisions
State Machine — Pending → Running → Evaluating → Done — full lifecycle
Difficulty Scoring — Easy (0.8x), Medium (1.0x), Hard (1.2x) multiplier
Intent Detection — Relevant, Partially Relevant, Irrelevant, Clarification Request, Off-Topic
Controlled Retry — Max 3 retries per question
Escalating Hints — 3 levels: Soft → Structured → Final — hints increase gradually
Off-Topic — Max 3 irrelevant answers → question skipped

📈 Scoring & Evaluation

Per Question Score — Objective progress + question scores + difficulty multiplier
Critical Gate — Jika critical question fails, recommendation capped at 'borderline'
Risk Flags — 5 flags: fundamental_knowledge_gap, failed_easy_question, high_hint_dependency, multiple_off_topic, system_evaluation_error
9-Level Recommendation — 1-9 scale + harmonization + risk downgrade
Evaluation Status — Full / Partial / Failed — transparan
Heuristic Fallback — Scoring alternatif saat LLM gagal
Performance Tier — Final tier setelah harmonisasi dan risk adjustment

📜 Question Bank & Survey

Survey Integration — survey.survey extended: ai_active, ai_mode (fixed/adaptive), ai_passing_score
Per Page — ai_weight, ai_min_score, ai_description
Per Question — ai_difficulty (easy/medium/hard), ai_critical_flag, ai_followup_hint, ai_evaluation_hint
Weights — ai_question_weight (default 5.0), ai_question_min_score (default 2.0)
Topic Locking — Backend decides topic order, LLM never skips
Language — Indonesian & English with language lock — prevents switching

🌐 Candidate Portal

Portal URL — /ai-interview/{access_token} — secure per-candidate link
Invitation — Draft → Sent → Started → Done → Expired (7-day default)
Auto Invitation — Send otomatis dari CV screening untuk recommended candidates
Early Termination Protection — LLM tidak bisa generate closing statements; backend kontrol penuh
Output Sanitization — Forbidden opening phrases blocked/replaced
Flow Integrity — Flow integrity failure logging untuk debugging

Comparison

Mengapa XERPIUM AI INTERVIEW?

Aspek	ATS Manual / Standar	XERPIUM AI INTERVIEW
CV Screening	HR baca manual, bias	✓ AI otomatis, bias redaction, 0-15 scoring
Bias	Gender, usia, agama	✓ Auto-stripped, murni kompetensi
Interview	Manual, tidak konsisten	✓ Adaptive AI, difficulty scoring, risk flags
Scoring	Subjektif	✓ 9-level, backend-governed, harmonized
Portal	✗ Tidak ada	✓ 24/7 self-service, token-based access
Integrasi	ATS terpisah	✓ FULL XERPIUM: applicant, survey, recruitment