Understand
Read every resume, without reading every resume.
Resumes arrive as PDFs and Word files written to no standard at all. They are parsed into structured profiles, then scored against the role with deterministic checks first and semantic matching second — so the reason for a score is always inspectable.
What it does
The short version.
- Structured profiles from any formatPDF and Word resumes become comparable fields.
- Deterministic checks run firstHard requirements are decided in code, not by a language model.
- Every score is explainableSee which requirement drove a match before you trust it.
In detail
What is actually in here.
The modules behind this stage. Each one is specified and built against a written brief before it ships.
- Resume AI parsingExtraction into structured fields, with a review diff showing exactly what changed before anything is saved.
- AI matchingA deterministic scorer for hard requirements, combined with semantic matching for the rest.
The AI boundary
What the model offers, and what you own.
AI proposes
Extracted profile fields and a match score with its reasoning.
A person confirms
A recruiter accepts, edits or rejects the extraction on a review screen. Nothing reaches the candidate record unreviewed.
Connects to
Where this sits in the flow.
Source
Every requirement, candidate and application in one place.
Requirements live in email, candidates live in a spreadsheet, and nobody can answer 'who have we already spoken to for this role?' without asking three people.
Screen
First-round screening calls that actually happen.
Fifty shortlisted candidates and one recruiter means the fiftieth first call happens three weeks late, by which point the candidate has taken another offer.
End to end
The whole hiring flow, in order.
Every stage from a client requirement to a collected onboarding document, and what each role actually does.
Try it on one role.
Create a workspace and open a job. Nothing here requires you to migrate anything first.