Career GPS 2.0 — full ATS + 6 AI agents. Free, forever. See everything included →

OrinAI Interviewagent://ai-interview@tanca v1.4

It scores the interview. Then it hides the score from you.

Orin runs the structured first round against your competency framework, records and transcribes it, and evaluates afterwards — then holds that evaluation until your panel has submitted their own. Show a panel a number first and their judgment bends toward it. So they don’t see one.

Start freeSee how the hold works
  • Your panel decides first
  • Asks for a person, it stops
  • Recordings auto-delete
18:24
00:00Technical depth
05:12Problem structuring
10:44Communication
15:02Leadership experience
Panel submissions
Lê Minh HoàngSubmitted09:34
Nguyễn Thị LanSubmitted09:51
Phạm Văn KhôiNot yet
Waiting — 2 of 3 panel members submitted
AI evaluation
Held until your panel submits
Panel: 2 of 3 submitted
No number here. Not greyed out — not present.
  1. 01Check the file is read and structured before the interviewInternal
  2. 02Run the structured first round against your competency frameworkExternal
  3. 03Evaluate afterwards, and hold the evaluation sealedInternal
  4. 04Turn what it found into probing questions for the panelInternal
  5. 05Write the evaluation to the employee record after a hireInternal

An AI score shown too early replaces the interview it was meant to support.

Anchoring isn’t a weakness some interviewers have. It’s what happens to people. Put a number in front of a panel before they deliberate and their assessment moves toward it — including the panel members who would tell you, sincerely, that it didn’t.

What you end up with is an AI decision with three human signatures on it. You’ve paid for the panel’s time, you’ve kept the appearance of human judgment, and you’ve quietly stopped having any.

The fix is not a better model. It’s sequence. The panel goes first.

20 hrs
of first-round calls per opening [CONFIRM]
0
numbers visible to your panel before they submit
18 min
for a structured, recorded, evidenced first round [CONFIRM]
What it takes on

Five tasks, each labelled with what it can reach.

Turn any of them off individually.

01Internal

Check the file first

Confirms the CV has been read and structured before the interview, so questions are grounded in what the person actually wrote.

Never: interviews on an unread file.

02External

Run the first round

Conducts a structured interview against the skills in your competency framework, with follow-up questions generated from the answers given.

Asks first: before recording anyone — separate consent.

03Internal

Evaluate, and hold it

Produces a level per competency with evidence pinned to the recording — and keeps the whole evaluation sealed until your panel submits.

Never: releases early, for anyone, including admins [CONFIRM].

04Internal

Turn the held score into questions

Converts what it found into suggested probing questions for the panel — the gaps worth testing, without revealing the conclusion.

Never: shows the score inside the question set.

05Internal

Write it to the employee record

If the person is hired, the interview evaluation is stored with them so it can be compared with real performance at ninety days.

Never: writes anything for a candidate who wasn’t hired.

Nothing here can close a candidate’s application. That class of action exists and always belongs to a person.

Sequence, not speed

Your panel submits first. Then the AI’s opinion unlocks.

Every competitor sells the opposite — instant scores, waiting for you when you open the file. That is exactly the arrangement that makes a panel’s judgment worthless, and we’d rather demo badly than ship it.

01

The interview happens.

Recorded, transcribed, structured against your framework.

02

The panel interviews and submits.

Independently, without seeing anything from the AI.

03

The evaluation unlocks.

Only when the last panel member has submitted.

04

Two opinions, side by side.

Yours first, then a second one with its evidence attached.

Before panel submits
Waiting — 2 of 3 panel members submitted
AI evaluation
Held until your panel submits
Panel: 2 of 3 submitted
After all three submit
Released 14/06/2026 09:42, after all 3 panel members submitted
AI evaluation
82/ 100Match
Technical depthL4
08:52
We use event sourcing for the order state machine and a separate read model for the API.
Directly demonstrates L4 system design
Problem structuringL3
12:08
I’d probably start with the database and work outward from there.
Approach stated but not walked through — gap against L4
CommunicationL4
Leadership experienceNot covered
Not covered in this interview
View full profile

What this costs us, and why we did it anyway.

Instant scores demo better. A buyer clicks once and sees a number, and that feels like the product working. Holding it back means the first thing a prospect sees is a lock. We accepted that, because a panel that has already been anchored is a panel you’re paying for and no longer using — and because a hiring decision that can’t be shown to have been made by people is a decision that’s hard to defend to anyone who asks.

The hold applies to everyone with access, including administrators. There is no override. [CONFIRM this is true before publishing it.]

Before they submit

Not a number. A better set of questions.

Holding the score back doesn’t mean the panel walks in unprepared. The agent converts what it found into suggested probing questions — the two or three areas where the first-round answers were thin, phrased as things to ask rather than conclusions to confirm.

“Ask about a time they led a design end to end” is useful. “System design: level 3” would have decided the conversation before it started. The first version helps a panel interview better; the second replaces them.

The questions never contain the score, the level, or a hint of the direction. That’s checked as part of how they’re generated. [CONFIRM]

  • Areas to probe, not conclusions
  • No score, level or direction leaked
  • Generated from the first-round answers
Panel briefing — Trần Quốc Bảo, Warehouse Team Lead
Prepared 14/06 09:12
Walk me through how you’ve handled a process breakdown that affected multiple team dependencies.
First-round answer described the outcome but not the decision-making.
Tell me about a time you had to rebuild trust with a team after a difficult period.
Team-leadership examples were cited but not developed past team size.
Describe a situation where the right call and the fast call were different, and how you made the decision.
Problem-structuring approach was stated; ask for a worked example.
The AI’s own evaluation is sealed until all panel members submit.
A briefing, deliberately not a verdict.
The stop rule

One sentence from the candidate ends it.

If a candidate says they’d rather speak to a person, the interview stops there. Not a form to fill in, not a request that gets reviewed, not a note added to a file. It ends, and the role’s recruiter is notified to take it over.

Nobody has to justify the request or explain why. Being assessed by a machine is something a person is entitled to decline, and a right that requires an argument isn’t one.

It’s also the honest test of everything else on this page. A product that means what it says about human decisions will let a candidate opt out of the machine at any moment, at no cost to them.

  • Stops immediately, mid-interview
  • No reason required
  • Their application is unaffected
Interview paused

No problem. We’ve let the hiring team know, and someone will contact you to arrange a conversation. This doesn’t affect your application.

Nothing from this session is scored. [CONFIRM whether a partial session is discarded or retained — and say which, plainly.]

Told plainly, and it costs them nothing.
The evaluation

A level per competency, pinned to the second it came from.

Questions come from the skills in your competency framework, and results come back as a level per skill against the level that role requires — the same five-level scale as your assessments and your performance reviews.

Every judgment carries an evidence pin: a timestamp and the sentence that produced it. Click it and the recording jumps there. A number you can’t interrogate is a number you can’t defend to the candidate who asks.

Competencies the interview didn’t reach are shown as not covered, rather than scored as absent.

  • Levels, not a percentage
  • An evidence pin on every judgment
  • Gaps in coverage shown, not filled in
82/ 100Match
Technical depthL4
04:18
We use event sourcing for the order state machine.
Problem structuringL3
08:52
I’d probably start with the database.
Gap against level 4
CommunicationL4
12:33
The risk wasn’t in the code, it was in the assumption.
LeadershipL3
15:11
We moved two people into different squads after that quarter.
Commercial awarenessNot covered
Not covered in this interview
Including what it didn’t manage to assess.
See the AI Interview module
Quality of hire

The evaluation doesn’t stop mattering on the hire date.

When someone is hired, the interview evaluation goes onto their employee record. At ninety days their actual performance is assessed on the same five-level scale, and the two are compared.

Which produces the answer nobody in this market currently has — not whether AI interviewing works in general, but whether it works in your company, for your roles.

If the relationship turns out to be weak, that’s what the report will show. We’d rather hand you a number that undermines our own scoring than have you discover it in year three.

  • Evaluation follows the hire
  • Compared at 90 days on the same scale
  • Reported to you, either way
  • Requires Tanca HRM
Interview
L4 System Design
90 days
Review
L4
Your own hires, your own roles. [CONFIRM this reporting ships.]

Four sources, four switches, one log.

Data it can read
Candidate records and CVsread
Competency libraryread
Interview panel calendarread
Salary bands by job graderead

Read-only. Nothing writes back.

Capabilities you switch
Read hiring module data
Draft inside Tanca
Send reminders by Zalo OA
Look up standardised legal texts

Each one is a separate switch. An agent doing three things you want beats one doing four where one makes you uneasy.

The run log
Interview conducted — 6 questions, 18:24External09:02:11agent://ai-interview@tanca v1.4
Evaluation produced — sealedInternal09:21:04agent://ai-interview@tanca v1.4
Panel briefing generated — no score includedInternal09:21:09agent://ai-interview@tanca v1.4
Released after 3 of 3 panel submissionsInternal14:40:22agent://ai-interview@tanca v1.4
Candidate requested a person — handed to Phạm Thu HàExternal09:11:47agent://ai-interview@tanca v1.4
Sealed, then released. Both on the record.

Interviews use your monthly allowance.

Shared across all six agents.

Draws on your AI allowance

[CONFIRM] interviews / month included
One unit is one completed interview, however many questions it contains.
  • An interview a candidate ended early doesn’t count [CONFIRM]
  • Recordings and evaluations stay available at zero remaining
  • Credits are self-serve

Unlimited and free

  • Reviewing evaluations
  • Watching recordings
  • Reading transcripts
  • Evidence pins
  • Panel briefings
  • Sharing with your team
  • Everything in Pipeline, Talent Pool, Assessments, Competency Framework, Pre-Onboarding and Reports

At zero remaining, new interviews pause. Nothing already recorded or evaluated is lost.

This is one of five.

Zola

Sourcing & Multi-channel Posting

Adapts and publishes roles across every channel, tracks cost per qualified applicant.

Learn more

Iris

Screening & Pipeline

Reads CVs against your competency framework and routes candidates to the right next step.

Learn more

Orin

AI Interview

Conducts a scored first-round interview against the role’s competency requirements.

You’re reading this one

Remy

Offer & Negotiation

Drafts and tracks offer letters, with salary band checks before anything goes out.

Learn more

Hana

Onboarding & Probation

Manages the checklist from signed offer to the end of probation.

Learn more

They share one allowance, one log and one queue.

Measured inside the product.

Food retail chain · 22 stores

18hBefore 47h

of first-round calls removed per opening, per month [CONFIRM]

Logistics company · 3 warehouses in the south

3.2dBefore 9d

from application to first human interview [CONFIRM]

Contact centre · recruitment hub

87%

agreement between held AI evaluation and panel assessment [CONFIRM]

You’ll see the same figures in your own run log from the first role.

Questions people ask.

Why hide the score from us?

Because seeing it first changes what your panel concludes, reliably, including for people who are sure it doesn’t. The panel submits, then the evaluation unlocks as a second opinion.

Can an administrator unlock it early?

No. There’s no override. [CONFIRM]

What if only two of three panel members submit?

It stays sealed. You can remove a panel member from the requirement, which is recorded in the log. [CONFIRM]

What does the panel get before they submit?

Suggested probing questions generated from the first-round answers, with no score, level or direction in them.

What if a candidate wants a human?

The interview stops immediately and the recruiter takes over. No reason required, no effect on their application.

Does the AI decide anything?

No. It conducts, evidences and offers a second opinion. Stage-closing actions always belong to a person.

How long are recordings kept?

[CONFIRM] days by default, configurable, deleted automatically. Candidates are told the number before they start.

Do you assess tone, confidence or cultural fit?

No, and we won’t. It assesses the competencies in your framework.

How many interviews are included?

[CONFIRM] per month, shared across the six agents.

What happens to the evaluation if we hire them?

It goes onto their employee record and is compared with their performance at ninety days, on the same scale.

Let your panel go first.

A structured, recorded, evidenced first round — and an opinion that waits its turn.

Start free
  • Panel decides first
  • Asks for a person, it stops
  • Recordings auto-delete