Z
ZeroHR
AI resume screening

AI screening you can audit.
Hosted, or on your infrastructure.

Most AI screeners hand you a ranked list and ask you to trust it. ZeroHR shows you how it understood the role, waits for your approval, and then shows its evidence for every score it gives.

The mechanic

It cannot score anyone until you approve.

This isn't a setting or a best practice — it's enforced in the software. Scoring is locked until the hiring brief is approved, and locked again until the rubric is approved. There is no path around it, for us or for you.

That's the difference between an AI you have to trust and one you can check.

How it works

Four steps. Two of them are yours.

The agent does the reading. You keep the judgement calls — and the veto.

01

It reads the role

Drop in a job description. The agent works out seniority, industry, the shape of the team, and what the minimum requirements really are — then writes it down as a brief.

02

You approve the brief

Read what it understood. Fix what it got wrong. Nothing proceeds until you say so — this is a gate, not a notification.

03

You approve the rubric

It proposes weighted criteria for the role. Edit them, reweight them, add your own, or have it rewrite one. The rubric is yours before a single resume is opened.

04

Then it scores

Each resume is scored against your rubric — with the evidence for every criterion, and a flag when the evidence is thin.

Defensible

Every score can be traced back to a line in the resume.

When a candidate asks why they were rejected — or a regulator does — 'the AI decided' is not an answer. This is.

Evidence, per criterion

Each criterion gets a score and the specific evidence behind it — quoted from the resume, not paraphrased into a vibe.

Thin evidence gets flagged

When the evidence is absent or tangential, the score is marked for human review instead of quietly counting. The model admits what it doesn't know.

The maths is not the model's

The weighted total and the recommendation are computed in code, at temperature zero. Same resume, same rubric, same answer — every time.

Contact details are redacted before a resume is sent for scoring. The model judges the experience, not the name, the address, or the phone number.

Honest economics

You can see what every screening costs.

Every AI call is metered — which step, which model, how many tokens, what it cost. It's in the product, per job, down to the call. Not a line item on an invoice you can't reconstruct.

Self-hosted

If resumes can't leave your network, run it inside your network.

Some teams can't send candidate data to anyone else's cloud — and most vendors' answer to that is simply no. We're building ZeroHR to deploy on your own infrastructure, running local models, so candidate data never leaves your walls.

This is offered as a bespoke deployment — we scope it with you before we commit to it.

See how it works

Screening you can show your work on.

ZeroHR is early, and we're working closely with the first teams using it. If that sounds like yours, we'd like to hear from you.

Talk to us