Skip to content

For HR software and recruiting teams

AI resume screening with scores recruiters can check

Parse each application, rank the candidates against the job in one call, then open any score to see the requirement it rests on. HireLayer gives your screening feature its evidence; the decision stays with the recruiter.

A screening flow for a Customer Success Manager job. Forty-eight application CVs are parsed, the strongest ten are ranked with scores from 0.86 down, and the top candidate is explained criterion by criterion, with each status shown next to the requirement.

Why screening is hard to get right

Most teams already screen with filters and a fast read. The trouble starts when volume grows or someone asks why a candidate was set aside.

  1. 01

    The first applications get the attention

    With a few hundred CVs per role, recruiters read the top of the list closely and skim the rest.

  2. 02

    Keyword filters miss equivalent experience

    “Led a support team of six” does not contain “people management”, so a filter drops a candidate a recruiter would keep.

  3. 03

    A bare score does not survive a question

    A hiring manager asks why one profile ranks above another. “The tool said 0.82” is not an answer.

  4. 04

    Regulators expect explanations

    The EU AI Act lists filtering applications and evaluating candidates as high-risk. Screening needs reasons a person can review.

From application to reviewed shortlist

Your product keeps the jobs, the applications and the decision. HireLayer structures each document and returns scores with their reasons.

  1. Your system

    Step 1, your system: Applications arrive

    Your ATS or careers page receives the CV files for a job, as it does today.

  2. HireLayer

    Step 2, HireLayer API: Parse each CV

    One call per file returns the candidate record, stored under your application id for screening.

    POST /api/v4/resumes/parse

    • application_id
    • resume.work_experiences[]
    • resume.skills[]
  3. HireLayer

    Step 3, HireLayer API: Turn the job into criteria

    Once per job, the description becomes weighted requirements, each required, preferred or bonus. A recruiter adjusts them before screening starts.

    POST /api/v4/jobs/extract-criteria

    • job_id
    • criteria[]
  4. HireLayer

    Step 4, HireLayer API: Rank the pool

    Send the job and the candidates in one request, with precise_ranking on. Each comes back once, best first, with a rank, a score from 0 to 1, a verdict and a ranking reason.

    POST /api/v4/resumes/score

    • scores[].rank
    • scores[].ranking_reason
  5. HireLayer

    Step 5, HireLayer API: Explain the finalists

    Every score carries the evaluation of each criterion: met, partial, missing or unknown, with the evidence from the CV. The profiles a recruiter opens need no second call.

    • scores[].criteria[]
  6. Your system

    Step 6, your system: The recruiter decides

    Your interface shows the order and the reasons. Advancing or rejecting a candidate remains a person’s action, logged in your product.

Want the whole flow as a program you can run on your own CVs?

Read the screening guide

A ranked queue where every score opens up

What a screening view in your product can show with Resume Scorer results. Ranking reasons and explanations come from the API, in the job’s language; the decision buttons are yours.

A screening queue for a Customer Success Manager job in Lyon, built from Resume Scorer results. Four ranked candidates show a score and a one-line ranking reason. The first one is opened: each of the four weighted criteria has a status and the evidence found in the CV. Advance and reject buttons stay with the recruiter.

Rank three applications for one job

Resume Scorer takes the stored job and the parsed CVs by their ids, so there is no text to send. The answer is abridged: each score also carries a summary and the evaluation of every criterion.

application_id
Your application id, the one each CV was parsed under.
score · verdict
From 0 to 1, the weighted mean of the criterion scores, and an overall judgment from highly_relevant to not_relevant.
ranking_reason
Why the candidate holds this position, in the job’s language.
Request · cURL/api/v4/resumes/score
curl -X POST https://hirelayer.co/api/v4/resumes/score \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $HIRELAYER_API_KEY" \
  -d '{
    "job": { "job_id": "csm-lyon" },
    "resumes": [
      { "application_id": "app_1041" },
      { "application_id": "app_1042" },
      { "application_id": "app_1043" }
    ],
    "precise_ranking": true
  }'
Response · abridged
{
  "job": { "job_id": "csm-lyon", "title": "Customer Success Manager", "language": "en" },
  "precise_ranking": true,
  "scores": [
    {
      "rank": 1,
      "application_id": "app_1042",
      "score": 0.86,
      "verdict": "highly_relevant",
      "ranking_reason": "Four years of B2B SaaS account management and fluent English, shown by a role in London."
    },
    {
      "rank": 2,
      "application_id": "app_1041",
      "score": 0.71,
      "verdict": "relevant",
      "ranking_reason": "Solid SaaS customer experience, but the level of English is not stated."
    },
    {
      "rank": 3,
      "application_id": "app_1043",
      "score": 0.48,
      "verdict": "marginally_relevant",
      "ranking_reason": "Technical support profile, little evidence of account management."
    }
  ],
  "credits_used": 3
}

The HireLayer APIs behind this workflow

Start with the core APIs, add the others when a feature needs them. All six products share one API key and one credit balance.

What changes for recruiters and your product

  • Every application gets read

    The pool is ranked against the same job, so a strong CV at the bottom of the inbox is not missed.

  • Equivalent experience counts

    Requirements are evaluated from what the CV describes, not from a list of exact keywords.

  • Scores that can be explained

    Each status points to a sentence in the CV, so a recruiter can answer a hiring manager or a candidate.

  • A person stays in charge

    HireLayer returns an order and reasons. Your product records who advanced or rejected each candidate.

AI resume screening: frequently asked questions

What is the best AI resume screening API to add to an ATS?

Look for an API that scores each applicant against the job’s own requirements and shows the evidence for every score rather than a bare similarity number. HireLayer covers the whole flow: Job Criteria Extractor turns the job into weighted criteria, and Resume Scorer ranks the candidates in one call and explains each one requirement by requirement. Resume Scorer also takes resume text, so it can sit behind the resume parser your ATS already uses. Scoring costs 1 credit per resume, plus 1 when the resume is a file to parse, criteria are free, and the free plan includes 50 credits a month.

Is resume parsing the same as resume screening?

No. A resume parser turns a CV into structured fields such as contact details, experience, education and skills. Screening compares each candidate with a specific job and says who meets its requirements. Most resume parsing APIs stop at the first step; HireLayer adds the second with Resume Scorer.

What is AI resume screening?

AI resume screening reads the CVs submitted for a job and orders them by how well they meet its requirements, so recruiters review the strongest applications first. With HireLayer, each score comes with a summary, and a status and an explanation for every requirement.

Does HireLayer reject candidates automatically?

No. The APIs return ranks, scores and explanations. Whether a candidate advances is decided in your product, by a person. A required criterion that a CV clearly lacks lowers its score, but never removes a candidate on its own.

How many applications can be screened at once?

Resume Scorer takes up to 100 resumes in one request and ranks them by score, with precise_ranking comparing the 10 best against each other. For a larger pool, preselect with Talent Pool Search or your own rules, or split it into several calls: scores for the same job stay comparable.

Is AI resume screening high-risk under the EU AI Act?

Yes. Annex III of the AI Act lists AI used to filter applications and evaluate candidates as high-risk. Under the Digital Omnibus, those rules apply from 2 December 2027. They call for human oversight and records of how the system was used, which per-criterion explanations and request ids help you document.

How much does screening one job cost?

Screening 10 applications takes 10 credits to parse the CVs and 10 to score them, explanations and best-first order included: 20 credits. The job’s criteria are free, a CV already scored against the job costs nothing again, and the precise ranking of the top 10 adds 1 credit per call. The free plan includes 50 credits a month.

Can recruiters screen candidates from ChatGPT or Claude?

Yes. The HireLayer MCP server exposes parsing, matching and ranking as tools in Claude, ChatGPT, Cursor and VS Code, so a recruiter can rank a shortlist in a conversation without an integration project.

What language are rationales and explanations written in?

Criteria, summaries, explanations and ranking reasons follow the job’s language (English, French, German, Spanish or Portuguese; English for any other), and evidence quotes the CV in its own language. CVs and jobs can be in other languages.

Screen one real job with it

Take a job you are hiring for, parse its applications and compare the order with your recruiters’ own. The free plan includes 50 credits a month, shared by all six products.