Talent acquisition

The ATS stays. The model never leaves.

Staffing desks already have an ATS. Screening AI was the leak: CVs left the agency. Our engineers shipped parse, match and interview packs on Private AI Foundation inside the agency perimeter. A recruiter still owns reject and offer.

The problem we were given

The ATS already held the records. Screening AI was the leak: CVs left the agency into a public or bring-your-own-cloud model. One desk handles many employer clients. A mix-up of candidates across clients is a reportable incident. Auto-reject without a trail is a legal problem.

bizfylabs — use case

Candidate lifecycle screening inside agency perimeter

Agency Perimeter Screening & Shortlist Flow

If a CV never leaves the building, can a recruiter still see a ranked shortlist with a citation back to the page?

What our engineers built

Parse, match and pack-draft on Foundation, inside the agency perimeter.

CV and job description parse for PDF, DOCX and scan, with per-field citation back to the page. Match and rank with an explanation, not a silent score. Draft outreach and interview packs. A recruiter sends them. RBAC so client A candidates cannot retrieve into client B desks. Bias and audit log on the same install.

The ATS remains the system of record. No CV, phone or national ID in a prompt that can leave the building.

Enterprise boundaries / Guardrails

What it is not

It is not a new ATS. It does not auto-reject. It does not scrape job boards. Offer and reject stay with a named recruiter.

Why the cloud answer fails here

A staffing firm is a processor for thousands of employer clients. One CV in a public model is a reportable incident. Ranking without an audit trail is a legal problem, not a UX one.

Controls in this workflow

These controls run on Private AI Foundation. Every ask goes through the same path.

Work stays inside the customer perimeter. Inference does not require a network path out.
You hold the encryption keys in every tier that touches your data.
Every ask goes through the Model Gateway. There is no side door to a public model.
Policy and DLP evaluate the request before weights run.
RBAC names who may invoke which model class on which data class.
Each step writes confidence and a citation back to the source. Originals are preserved.
Consequential actions wait for a named approver. Nothing silent-posts to your core systems.
Immutable audit is written on the same install: who, what, which model, which policy, outcome.
Apache 2.0 and MIT weights only. Licence text and an SBOM ship on disk per release.

The paid proof of value

Thirty to forty-five days. Fixed fee. In the customer environment. One desk, one role family, agreed volume. Success criteria and conversion price agreed in writing before starting.

Success is time-to-shortlist, parse quality against a human, zero CV egress, and human-owned reject and offer. If it misses the threshold, the customer keeps the report and owes nothing further.

Key specs

Deployment: Agency on-prem / VPC
Egress: Zero CV egress
Audit: Bias + parse immutable log

Deploy in your perimeter

Talk to an engineer about air-gapped, on-prem or single-tenant deployment for this workflow.

Start with one desk and one role family.

A paid proof of value, 30 to 45 days, inside the agency. The ATS stays. The model does not leave.

Start a paid proof of value

The full stack on one machine, disconnected from the network.

In your office, on your documents, with the cable pulled out. No competitor's sales engineer can do this.

Start a conversation