Evaluate the whole batch against the same criteria. Open the quote behind every judgment. Keep a record you can defend.
Shortlist is live. Grade is in development.
This is Evalgist Shortlist screening three candidates against one criteria set. Every match carries the evidence it rests on — or shows that none was found.
Dr. S. Chen
All three required criteria are met with direct quotes. Strongest research record in the batch: 12 peer-reviewed papers, 4 years of teaching.
PhD in Computer Science, 2017. Thesis on distributed model inference.
Since 2019 I havetaught the undergraduate algorithms course, covering lectures and exam design.
12 peer-reviewed publications, including two journal articles as first author.
J. Smith
PhD met with a direct quote. Teaching is limited to one semester as an assistant, and no publications were found in the resume.
Completed my PhD in Computer Science in 2021.
Alongside my research I worked as ateaching assistant for Introduction to Programming (one semester).
No matching line found in the resume.
M. Johnson
PhD is in an adjacent field. No teaching record and no publications were found, so two of three required criteria are unsupported.
PhD in Computational Biology, 2019.
No matching line found in the resume.
No matching line found in the resume.
AI-assisted evaluation. The hiring decision is yours.
Every Evalgist product starts with criteria, cites the evidence, and leaves the decision to the reviewer. Evalgist Shortlist applies the method to resume screening. Evalgist Grade will apply it to grading student answers.
AI resume screening with quoted evidence.
Upload a vacancy and applications. Every candidate is compared against the same criteria, and you shortlist with the evidence open. Live now.
Explore ShortlistConsistent grading for exams and written assessments.
The same method applied to marking: one rubric across hundreds of answers — open-ended or against an expected answer — with the passages each grade relies on. In development — join the waitlist below.
Follow GradeA chat can score one resume. It will not hold one standard across two hundred, or hand you a packet for the meeting.
A chat re-interprets the standard with every prompt. A criteria set holds the same standard for every document in the batch.
A chat summarises. An evaluation cites the source line behind each judgment, so you can open the document and check.
A chat leaves a scrollback. An evaluation leaves an exportable record you can bring to the decision meeting.
Documents stay in EU projects, AI requests use zero-data-retention routing, and extracted text is deleted after analysis. Read how we handle data.
Evalgist Shortlist is live — try it on your next opening. Evalgist Grade is in development; leave an address and we will write when it opens.
Evalgist Grade
Evalgist started with one hiring round and a few hundred applications. Read the story.