Smart CV library and candidate-to-need matching

Every CV in one place, the right shortlist for every role.

WhatsApp
Agent sheet
Category
HR and recruitment
Model
open, installed on your premises
Data
never leaves
Subscription
€0 per month
01Overview

CVs arrive by email, form and job board and end up in folders nobody reopens. The agent centralises them, reads them, and proposes a justified shortlist for each need.

The problem

An urgent need restarts a search from scratch when the right profile applied three months ago. Manual sorting is slow, subjective and impossible to trace.

Our answer

Ingestion from every channel, structured extraction (skills, experience, mobility, availability), semantic search on your server, shortlist per need with the ranking reasons, and queuing of selected candidates to the qualification call agent.

02How it works

Live in four steps.

  1. 01
    Sources and criteria

    Input channels and job-description criteria, formalised with your recruiters.

  2. 02
    Ingestion

    Reading of all past and future CVs, deduplication, vector store on your side.

  3. 03
    Matching

    Justified shortlist for each need, reviewable by the recruiter.

  4. 04
    Hand-off

    Selected candidates are queued for the qualification call.

03What you gain

Results you can measure.

A talent pool actually used

Every new need first queries existing applications.

An explained ranking

Every shortlisted candidate comes with the reasons for their place.

Personal data on your server

No CV sent to an external service.

04Frequently asked

What we get asked before signing.

What about GDPR?
Retention period, access rights and deletion are handled in the database; CVs never leave your infrastructure, which greatly simplifies your register.
Does the agent need an AI vendor subscription?
No. It runs on an open-source model, picked from the right family, installed on your server or VM. No API key, no token bill, no data sent outside.
What hardware is required?
From 8 GB of RAM on CPU for this kind of specialised task. We measure real throughput on your machine during the audit and write it into the proposal.
How long does setup take?
Two to six weeks depending on the connections to build. You validate an acceptance run on your real cases before going live.

Let's talk about your case for thirty minutes.

A conversation to understand your context, volumes and tools. You leave with a scope and an order of magnitude, no commitment.