This side is for filling a role — rank people who applied. If you are looking for a job and need to score your resume, open Score my resume. Paper packets: Asset desk.
Stop opening every applicant file. Shortlist first.
Paste the job you are hiring for. Drop the whole stack of resumes. Get a ranked sheet by match score and keyword hits — open only the people who clear the filter. Export CSV for the interview list.
What you walk away with
A ranked table of applicants: match score, required-keyword hits from the role, contact found, and a shape check for files that break ATS parsing. Highest match first. Interview list from the top — not from the whole pile.
Screen the whole stack
Rank
Candidate file
Match score
Keyword matches
Contact found
Dates found
Amounts found
Shape check
Matches
How the ranking works. Each applicant is scored against the role for keyword coverage (the same signal ATS and first-pass screeners use), plus contact signals and a parse shape check. Highest match first. Export the interview shortlist as CSV.
How it works
1 · Drop the job and the whole stackSelect every applicant file at once. Rank them against the role you are filling.
2 · Each file runs the same real intentsEntities pulls contact info; find/extract count keyword matches; profile catches a malformed file before it's scored at all — once per resume, in order.
3 · One ranked table, highest match firstEvery row traces back to a real match in real text — no opaque "AI score." Export the whole list as a CSV when you're done.
Common questions
Does this replace your judgment as the hirer?No — it replaces the first pass. Keyword matches and contact signals surface so you only open the applicants worth the interview hour.
Is this a black-box AI score?No. Every number shown is a literal count from a real, named intent (a keyword match count, an entity count, a shape check) — nothing here is an opaque model output.
What if the resume is a scanned image, not text?The Shape Check column flags a near-empty extraction so you know to re-request a text-based file before trusting a zero score.