AI voice agents for structured candidate assessments.
A Xebit assessment agent runs a structured interview by phone. Every candidate for a role gets the same questions in the same order and is scored against the rubric your hiring team defines. Each score comes with the transcript and the answer it was based on, so a recruiter can check it, and the hiring decision stays with a person.
How the call runs
See how one assessment call becomes evidence a recruiter can check.
Same questions, same rubric, every score tied to the answer it came from, and the decision left to a person.
Calling…
Agent is reaching the candidate
Live conversation
Assessment call
Workflow actions
Triggered during the call
How does the call run?
- 01
Define the rubric
Your hiring team sets the questions, what a strong and a weak answer look like for each, and how answers are scored.
- 02
Ask the same questions
Every candidate for the role hears the same questions in the same order, with the same follow up prompts, in the language they choose.
- 03
Score against the rubric
Each answer is scored against your rubric and stored next to the passage of the transcript it was based on.
- 04
Review the evidence
A recruiter sees scores, answers and the recording together, and can change a score they disagree with.
- 05
Decide with people
Shortlisting and the hiring decision stay with your recruiters and hiring managers.
What does the agent capture, and where does it go?
Captured on the call
- Answer to each rubric question
- Score per question against your rubric
- Transcript passage behind each score
- Language the assessment ran in
- Questions the candidate had for the recruiter
- Recording, transcript and summary
Then, in your systems
- Scores and evidence written to the candidate record in your ATS
- Assessments queued for recruiter review by webhook
- Interview scheduling triggered for candidates the recruiter advances
- Shortlist decisions left to the hiring team
When does a person take over?
The capabilities behind it.
Candidate Assessment questions
How does the agent keep scoring consistent?
Every candidate for a role hears the same questions in the same order and is scored against the same rubric your hiring team defines. Each score is stored with the transcript passage it was based on, so recruiters can see why it was given and correct it. Consistency comes from the structure, and people check the result.
Is the AI making the hiring decision?
No. The agent runs the assessment and scores answers against your rubric, but shortlisting and hiring decisions stay with your recruiters and hiring managers. They see the scores, the answers and the recording together, and can disagree with any score. The agent gives them structured evidence, not a verdict.
Who writes the questions and the rubric?
Your hiring team does. You decide the questions, the order, the follow up prompts and what a strong or weak answer looks like. Xebit runs them the same way for every candidate, in any language Gemini and OpenAI support in realtime, and you can set a different rubric for each role.
Bring your script. We will run it live.
We will set up the candidate assessment workflow on a live agent, connected to a test copy of your systems, so you can hear the call and see the record it leaves.