Solutions / Interview questions

Interview question generator

A structured interview guide built from the CV in front of you and the role you are actually hiring for — questions, follow-ups and a scorecard every interviewer fills in the same way.

HR Recruiting Automation
3–5 minutes
per guide, instead of 40–60
Every candidate
interviewed on one scale
Scored evidence
in the ATS, not in a notebook
Who it is for

Hiring managers and recruiters running five or more interviews a week, where preparation currently happens in the ten minutes before the call.

Short answer

Paste a CV and a job spec, get a guide for that specific conversation: what to probe given this candidate’s gaps, the follow-ups that catch a rehearsed answer, and a scorecard tied to the competencies the role was opened for. The same structure reaches every interviewer, so two candidates for one role are compared on the same evidence rather than on who happened to interview them.

The problem

The guide gets written in the ten minutes before the call, or it does not get written at all.

01

Preparation loses to the calendar

Forty minutes of reading a CV and drafting questions does not survive a day with six interviews in it. So the interview is improvised — and the improvisation is different every time.

02

Every interviewer asks something else

One probes architecture, the next asks about the last job, the third talks culture for half an hour. Two candidates for the same role end up with two incompatible sets of evidence, and the decision defaults to whoever felt better in the room.

03

The notes never become a comparison

Impressions land in a notebook or a Slack DM, in prose. A week later nobody can reconstruct why candidate B was rejected, and the next round re-asks the same questions.

How it works

From trigger to result, step by step.

01

Encode the role, not the job ad

We sit with the hiring manager and write down what the role is actually hired on — four to six competencies, each with what a strong answer looks like. This is the part that makes the questions useful, and it is the part a generic prompt cannot do for you.

02

Read the CV against the spec

The model marks overlap and gaps: what the candidate claims, what the role needs, what is vague or missing. Those gaps drive the questions, which is why the guide differs from candidate to candidate.

03

Generate the guide

Eight to twelve ordered questions, each with a follow-up and a note on what a strong versus a weak answer sounds like — plus the two or three things worth verifying because the CV is thin on them.

04

Attach the scorecard

Every question maps to one competency on a defined scale, with room for the evidence behind the score. A number without the quote that produced it is an opinion with a decimal point.

05

Deliver where the hiring happens

The guide is attached to the candidate in your ATS and posted to the interviewer before the call; the filled scorecard comes back onto the candidate record, so the hiring committee reads comparable evidence instead of four sets of prose.

Before / after

What changes on the ground.

Today, by hand
×Prep happens in the ten minutes before the call
×Every interviewer asks a different set
×Notes are prose in a notebook or a DM
×Decisions rest on who felt better in the room
With the automation running
A guide per candidate in three to five minutes
One competency scale across every interviewer
Scored evidence stored on the candidate record
Two candidates compared on the same criteria
What you get

Delivered, not demoed.

A competency model per role, agreed with your hiring managers
Per-candidate guides generated from CV and spec, with follow-ups
A scorecard tied to competencies, on a defined scale
ATS integration so guides and scores live on the candidate record
The prompts and templates in your hands — you edit the questions without us
Built with

We build in your stack rather than moving you onto ours. The list below is what this solution most often connects to — other systems are a scoping question, not a blocker.

Python OpenAI Anthropic Greenhouse Workable Google Docs Slack PostgreSQL
Time to production2–3 weeks
Build priceFixed quote
First stepFree mini-audit
Honest limits

When this is not the right solution.

·If you hire a couple of people a quarter, a good template document and thirty minutes of preparation will serve you better than a system somebody has to maintain.
·If your interviewers do not want structure, the guide gets opened and ignored. This works where hiring managers have agreed to interview the same way — it does not create that agreement.
·It does not decide who to hire, and it should not. It produces evidence in a comparable form; the judgement, and the responsibility for it, stay with the people in the room.

Questions we get about this one

No. The gaps between this CV and this spec drive them, so a candidate with no team-lead experience is asked different things from one who led fifteen people. The competency frame stays fixed; the questions inside it move.

Bring us the process that hurts.

The mini-audit is free: we take your version of this process apart and tell you plainly whether automating it pays. If it does, you get a scope and a fixed price.