jev·agent
Get API access

Free tier

Send us your text, get a decision back

A key, one endpoint and eight rulesets that were tuned and measured before you arrived. You do not write question shapes, pick a model, or learn that a score is a weighted mean of rubric indices rather than a 0-1 float. That translation is the thing.

Quick answer · verified 2026-09-19

What is this, and how is it different from calling Jev directly?

Calling Jev directly means writing Choice, Score and Noul objects, discovering that option descriptions are the entire prompt surface, and finding out the hard way that score runs 0..n-1 rather than 0..1. That work is already done here.

You post text and a ruleset name. The rulesets are generated from the fixtures in our public benchmark, so the cost and latency published on this site are the numbers these exact questions produced — not a marketing approximation of them.

Free tier1,000 decisions / monthone decision = one question about one item
Signupan email addressno password, no account, no confirmation mail
Rulesets8the same ones measured in our public benchmark
You sendyour own textnot Jev question objects

One key per address. No password, no account, no confirmation email.

Make a call

bash
curl -X POST https://jev-agent.com/api/v1/classify \
  -H "Authorization: Bearer jv_live_…" \
  -H "content-type: application/json" \
  -d '{
    "ruleset": "support-ticket-triage",
    "items": ["Charged twice for September and cancelling Friday unless refunded."]
  }'
json
{
  "ruleset": "support-ticket-triage",
  "ruleset_version": 1,
  "results": [
    { "index": 0,
      "answers": {
        "queue":      { "choice": "billing", "confidence": 1, "probabilities": {…} },
        "severity":   { "score": 2.5, "legend": {"0":"Low","1":"Normal","2":"High","3":"Urgent"} },
        "churn_risk": { "noul": 0.95 }
      },
      "latency_ms": 1669 }
  ],
  "usage": { "decisions_charged": 3, "used": 3, "remaining": 997 }
}

The rulesets

Up to 20 items per request. Billing counts decisions, not requests: a ruleset asking three questions spends three per item, because that is what the upstream call actually costs. The catalogue is also readable without a key at GET /api/v1/classify.

RulesetWhat it decidesPer item
support-ticket-triageRoute an inbound ticket to a queue, grade its urgency, and flag churn risk.3
llm-model-routingDecide how much model capability a request actually needs, before you spend it.1
agent-tool-selectionPick which tool an agent should call next from a fixed toolset.1
content-moderationGrade harm on a four-band rubric and flag targeting and spam separately.3
phishing-detectionIndependent yes/no signals for an email — combine them yourself rather than trusting one verdict.5
rag-rerankingScore a retrieved passage for real relevance, not embedding similarity.1
agent-output-guardrailsVerification checks on a draft response before it reaches a user.4
lead-scoringScore fit and intent against a rubric so hot leads reach a human today.3

Limits and honesty