Code review risk

Flag risky pull requests for extra human review.

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:

scorerisk

How risky is it to merge this pull request as-is?

rates it on an ordered scale:

trivial, safe to auto-merge
low risk
needs a careful review
high risk, could cause incidents

noultouches_money

Does this change touch payments, billing or other money-handling logic?

returns a calibrated yes/no probability.

choicerequired_reviewer

Which reviewer should this be assigned to?

picks one of these options:

any — any teammate can review
senior — a senior engineer should review
payments_owner — the payments code owner must review

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": "Pull request title: 'quick fix: bump payment retry limit'\nFiles changed: services/billing/charge.py (+3 -1)\nDescription: 'raising max retries from 3 to 8 so failed cards get retried more, should reduce churn'. No tests added. Author is a first-time contributor.",
  "questions": {
    "risk": {
      "type": "score",
      "instructions": "How risky is it to merge this pull request as-is?",
      "criteria": [
        "trivial, safe to auto-merge",
        "low risk",
        "needs a careful review",
        "high risk, could cause incidents"
      ]
    },
    "touches_money": {
      "type": "noul",
      "instructions": "Does this change touch payments, billing or other money-handling logic?"
    },
    "required_reviewer": {
      "type": "choice",
      "instructions": "Which reviewer should this be assigned to?",
      "criteria": {
        "any": "any teammate can review",
        "senior": "a senior engineer should review",
        "payments_owner": "the payments code owner must review"
      }
    }
  }
}

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 →