CVsprings scores candidates with a transparent, rules-based engine — no language model ever reads your candidates' data. Same CV, same job profile, same result. Every time. Provable.
Each candidate assessment shows exactly which rules fired, which skills matched, and why. No black box, no "the model decided." Your client asks why — you answer in one click.
The extraction and scoring engine is fully deterministic. Re-run any assessment months later for an audit and get byte-identical results. Try that with an LLM-based screener.
Every action is logged against a formal assessment schema aligned with EU AI Act traceability requirements. Export the full audit trail per candidate or per role.
No candidate data is sent to third-party AI providers — because there are none in the pipeline. Processing is GDPR-scoped by design, with per-candidate deletion on request.
One pass through the engine: a role defined explicitly, a candidate scored with every point traced to the line that earned it, the audit log, and the bias report. Nothing is edited between steps.
Most screening tools put a language model between your candidates and your shortlist. It reads the CV, forms an impression, and returns a score it cannot explain and will not repeat. Run the same CV twice and you can get two different answers.
Under the EU AI Act, screening candidates is high-risk — when it's done by an AI system. The obligations that follow are not light: risk management, data governance, technical documentation, logging, human oversight, conformity assessment. And a good part of that lands on you, the agency deploying the tool, not only on the vendor who built it.
So we made the unfashionable choice: a rules engine you configure. The thresholds, the weights, the knockouts are yours, written down in advance, applied the same way to every candidate. No model reads the CV. Nothing infers, because there is nothing to infer from — the rules are the rules, and they run exactly as written.
Which is the point. Every score comes with the rule that produced it. The audit trail is attested by the server, not supplied by the browser. And a determinism check runs before every release: same CV, same rules, same score, or the build doesn't ship.
Less magical. Entirely defensible.
That trial link can’t be used any more — it may have expired or already been started. You can still start on any plan below, or book a demo and we’ll set one up for you.
Send us 3 anonymised CVs and your job spec. In a 15-minute call we run them through the engine in front of you — twice, so you can watch the outputs match.
No slideshow, no generic sample data. You leave the call knowing exactly what CVsprings says about your candidates, and why.
Prefer to look before you talk? Start with our one-page EU AI Act checklist for recruitment tooling — no form needed.