Résumé screening

Score a candidate across several dimensions in one call.

Run this demo ▶Get an API key →

The decisions Jev makes

In a single call, Jev evaluates each of these — in parallel, against the same input:

scoreexperience

How many years of professional software experience does the candidate have, as of today (2026)?

rates it on an ordered scale:

under 2
2–4
4–7
7–10
10+

scoredepth

Rate hands-on technical depth from what they personally built and owned — ignore titles and company names. When torn between two levels, pick the lower.

rates it on an ordered scale:

shallow
some depth
solid
deep, senior-level

noulmentorship

Does the résumé demonstrate mentoring experience?

returns a calibrated yes/no probability.

choiceprofile

Which talent profile fits best, judged holistically?

picks one of these options:

backend — backend / systems engineer
fullstack — full-stack generalist
ml — ML / AI engineer
platform — platform / infrastructure

The exact request

This is the real payload behind the live demo — copy it, change the state, and you're building:

{
  "model": "jev-latest",
  "state": "Candidate résumé — Priya Okafor.\nSenior Software Engineer, 2019–present, Meridian Health (San Francisco).\n- Rebuilt the claims-processing pipeline (Go, Kafka) cutting P99 latency 4.2s → 380ms.\n- Owned the on-call rotation and mentored 3 junior engineers to mid-level.\n- Shipped an internal LLM assistant for support agents (RAG over policy docs).\nEarlier: Software Engineer, 2016–2019, a fintech startup. BSc Computer Science.\nOpen source: maintains a popular Go rate-limiter library (2.4k stars).",
  "questions": {
    "experience": {
      "type": "score",
      "instructions": "How many years of professional software experience does the candidate have, as of today (2026)?",
      "criteria": [
        "under 2",
        "2–4",
        "4–7",
        "7–10",
        "10+"
      ]
    },
    "depth": {
      "type": "score",
      "instructions": "Rate hands-on technical depth from what they personally built and owned — ignore titles and company names. When torn between two levels, pick the lower.",
      "criteria": [
        "shallow",
        "some depth",
        "solid",
        "deep, senior-level"
      ]
    },
    "mentorship": {
      "type": "noul",
      "instructions": "Does the résumé demonstrate mentoring experience?"
    },
    "profile": {
      "type": "choice",
      "instructions": "Which talent profile fits best, judged holistically?",
      "criteria": {
        "backend": "backend / systems engineer",
        "fullstack": "full-stack generalist",
        "ml": "ML / AI engineer",
        "platform": "platform / infrastructure"
      }
    }
  }
}

Wire it into your code

Read the typed answers and branch in plain code — no parsing. Auto-handle the high-confidence cases and route the uncertain ones to a bigger model or a human. It's one API call and output is free, so ask every question you need at once.

Build your own

Every scenario above is a single API call. Try any of them free in the playground, then get a hosted key to ship it — no waitlist.

Run this demo ▶Get an API key →