Score: account churn-risk tier

The job

Jev judge eval (1 choice) over a fixed state : runnable via experimental_evaluate.

The prompt

Copy this into Muse and replace anything in [square brackets] with your own details.

// Score: account churn-risk tier — Jev judge eval (typesafe-ai/jev).
// A top account cut seats 40% and went quiet; the judge tiers churn risk.
// Model: typesafe-ai/jev via the Vercel AI Gateway ($0.042/1M input tokens).
// Auth: set AI_GATEWAY_API_KEY (vck_…) in the environment — never paste the key here.
// For zero-data-retention / no-training workloads, add
// providerOptions: { gateway: { … } } to the evaluate call below.

import { experimental_evaluate } from 'ai';

const result = await experimental_evaluate({
  model: 'typesafe-ai/jev',
  state: "Account: $96k ARR, renewal in 40 days. Signals: seats cut 40% last month, weekly active users down 60%, champion left (no replacement named), two support escalations unresolved, skipped last QBR.",
  questions: {
    "risk": {
      "type": "choice",
      "instructions": "Tier the churn risk of this account from the signals.",
      "criteria": {
        "high": "Multiple strong risk signals with renewal near — intervene now.",
        "medium": "One or two warning signs worth watching this quarter.",
        "low": "Healthy usage, engaged contacts, no negative signals."
      }
    }
  },
});

console.log(JSON.stringify(result, null, 2));