PDF · DOCX · ZIP → XLSX · CSV4 credits per resume — a 25-resume batch is 100 creditsBeta
A stack of resumes → one side-by-side candidate matrix, with an evidence quote behind every criterion.
What do you need?
Files are deleted after processing
EXAMPLE
RESUMES.ZIP — 25 FILES
arrow_forward
CANDIDATE-MATRIX.XLSX
R. Alvarez — 6 years — Python: yes
Evidence: "built Django services…" Experience
S. Okafor — ~4 years — AWS: partial
…25 rows, 5 criteria, 2 files
What you get
check_circleOne row per candidate, in upload order
check_circleSkills, roles, experience, education, and certifications extracted
check_circleYes / partial / no / unclear verdict on every criterion you set
check_circleA verbatim evidence quote citing the resume section behind each verdict
check_circleBoth Excel (.xlsx) and CSV, every time
How it works
1Upload the stackDrop in PDF and DOCX resumes — or one zip of the whole folder — and list the role's must-have and nice-to-have criteria in plain English.
2One profile per resumeEach resume is read in full (scans included), its skills, roles, experience, education, and certifications extracted, and every criterion judged with a verbatim quote citing its section.
3Download the matrixOne spreadsheet, one row per candidate, ready to sort and filter — as Excel and CSV, with a note that hiring decisions require human review.
Who uses this tool
The same file, different jobs. Tap a prompt to try it.
HIRING MANAGERS
Screen a stack before lunch
Forty resumes become one sortable sheet — who meets the must-haves, with the quote to prove it.
RECRUITING AGENCIES
A shortlist you can defend
Every verdict carries a verbatim quote and its resume section, so clients can check the call.
STARTUPS
First hires without an ATS
No recruiting stack needed — zip the inbox attachments and get a matrix back.
HR & TALENT
The same bar for everyone
One fixed set of criteria applied identically to every resume — no drift between reviewer moods.
STAFFING & CONTRACTING
Match candidates to the req
Certifications, clearances-as-stated, and date ranges pulled into columns you can filter.
NONPROFITS & EDUCATION
Committee-ready packets
A side-by-side matrix the whole hiring committee reads in one sitting, resumes attached for review.
SECURITY
Built for sensitive documents
Bank statements, medical files, case records. Security isn't a feature we added — it's the foundation.
lock
Encrypted in transit
Encrypted in transit over TLS 1.2+, and stored in access-controlled, encrypted object storage. Files are protected the moment they leave your browser.
admin_panel_settings
Your files stay yours
Workspaces are isolated per account. Role-based access shows teammates only what they need.
auto_delete
Deleted, not stored
Files are deleted after processing. Everything runs on our own hardware and is never sent to an outside AI service, so your data is never used to train models.
dnsProcessed on our own hardwareauto_deleteDeleted after processinglockEncrypted in transit
Questions
You list the role's must-have and nice-to-have criteria in plain English. Each resume is read in full and every criterion gets a yes / partial / no / unclear verdict backed by a short verbatim quote and the resume section it appears in — and if nothing in the resume supports a criterion, the cell says "no evidence in resume" rather than inventing one.
No — the extraction is hard-blocked from recording protected characteristics: age, race, gender, religion, nationality, citizenship, disability, marital status, or photos, even when the resume states them. Only the job-related criteria you provide are evaluated, and no instruction can loosen that rule.
No, and both files say so: the matrix is an organizational screening aid. Every verdict carries a quote so you can check it against the resume, and hiring decisions require human review of the underlying resumes.
Yes — PDF pages are rendered to images and read by our vision models, so photographed and scanned resumes work just like digital exports. DOCX resumes are read directly.
Yes. Files are processed on our own servers, never sent to a third-party AI cloud, never used for training, and auto-deleted 7 days after the job finishes.