Matching that shows its work
AI matching scores candidate-to-job fit and explains why — citing the specific requirements and attributes behind every score, and flagging uncertainty instead of hiding it.
Evidence-based scoring
Every score comes with its reasoning attached
Instead of a bare number, matching surfaces the specific requirements it evaluated and the candidate attributes that support — or don't support — a strong fit, so recruiters can verify the score rather than take it on faith.
- Fit scores reference the job requirements they're based on
- Supporting and conflicting evidence shown side by side
- Scores update as job requirements or candidate data change
Uncertainty, not overconfidence
A low-confidence match says so
When evidence is thin — an incomplete profile, an ambiguous requirement, conflicting signals — matching flags that uncertainty explicitly instead of rounding to a falsely confident score.
- Uncertainty is a visible signal, not buried in the score
- Recruiters decide how to weigh a flagged, lower-confidence match
- No automated advance, rejection, or ranking decision is final
Candidate profile is missing recent role details. Score reflects partial evidence — review recommended.
How recruiters use it
A decision aid, not a decision-maker
Prioritize, don't filter blindly
Use fit scores to decide where to focus first — every candidate remains visible and reviewable.
Surface hidden fits
Matching can surface strong candidates against roles a recruiter hasn't manually reviewed yet.
Human review, always
Every submission and every hiring step still requires a person to act — matching never auto-decides.
FAQ
AI matching questions
Focus your time on the strongest fits
Evidence-backed matching that helps you prioritize — without ever deciding for you.