AI Interview for Business
All templates

AHM Operator

Workflow on top — drag to reorder. Voice / prompt / models below.

id-ID10 sessions

Workflow (interview script)

3 main 0 followups
  1. 1
    main

    Sekarang {{candidate_first_name}} menetap di mana? apakah di Jakarta atau di luar Jakarta?

    order #0
  2. 2
    main

    Dari CVnya, sebelumnya sebagai {{cv_last_role}} di {{cv_last_employer}}, itu ngapain aja?

    order #1
  3. 3
    main

    kemampuan kamu di CV: {{cv_skills}} banyak, berarti udah banyak pengalaman, base Salary yang kamu harapkan di angka berapa?

    order #2

First message (greeting)

212 chars

System prompt

700 chars

The workflow's main questions get appended to this prompt at dispatch time. KB context is fetched live by the agent — don't hard-code it here.

Session settings

Workflow has 3 main questions — agent uses that count. Stored config value (10) is ignored while workflow is set.

Kandidat harus grant izin kamera di device check; kalau decline, dia nggak bisa lanjut. Cocok untuk posisi customer-facing / hiring real (per AHM HR — verify identity).

Subtitle live muncul di bawah avatar — pertanyaan AI dan ucapan kandidat yang baru di-transcribe. Bantu kandidat yang gak fasih bahasa atau lingkungan ribut. Transcript tetap kerekam buat grading walau toggle off.

Interviewer avatar

Mood

Models

Pulled from lib/agent-catalog.ts — the dashboard's allowlist of providers the agent has plugins for. Adding a new model here without installing the matching livekit-plugins-* in the agent will crash dispatch.

Language model (LLM)

Default. Stronger reasoning than 2.5 with comparable latency at thinking_level=low. Global endpoint only (no asia-southeast1).

0 (deterministic)0.4 (default)2 (chaotic)

Voice (TTS)

Lowest latency; slightly less natural.

You can paste a custom voice id (e.g. an ElevenLabs cloned voice) into a future input — it stays saved even if not in this list.

0.5×1.0× (default)2.0×

Eleven applies VoiceSettings.speed in [0.8 – 1.2]; values outside that range are clamped at dispatch.

More variableMore stable

Lower values let the voice sound livelier; higher values keep tone tightly consistent across the call.

LowHigh

How closely the output should match the source voice. Too high can amplify any noise in the original sample.

Region only applies to Google Chirp 3. ElevenLabs runs from ElevenLabs' own infrastructure and ignores this.

Transcription (STT)

wawancara selesaiterima kasih atas waktunyasampai jumpa lagisampai jumpa

Press Enter or comma to add.

30456090120

Press Enter or comma to add.

Custom post-processing prompt

2997 chars · ok

Templates (klik untuk pakai)

Variabel tersedia: {{transcript}}, {{candidate_name}}, {{language}}, {{salary_budget_min}}, {{salary_budget_max}}, {{salary_currency}}, {{preferred_locations}}, {{psychology_guidance}}. The system enforces strict JSON; markdown / preamble in the response will fail to parse.