jevrecipes

Recipe catalog / buying-intent

Grade buying intent

How strong is the purchase intent expressed in message, on a five-level rubric?

You need to rank or route inbound leads and replies by how close the sender is to buying, not just whether they are interested.

Explore this recipe interactively ยท Source and implementation guide

Use buying-intent in TypeScript

Install with npm install jev-recipes. Requires Node.js 22.9 or newer and ES modules. Set TYPESAFE_API_KEY in your server environment for live calls, which send input to TypeSafe and use API quota. See the installation guide.

import { buyingIntent } from 'jev-recipes/buying-intent';

const result = await buyingIntent({
  "message": "We've narrowed it down to you and one other vendor. Can you confirm whether the Team plan includes SSO, and what the annual price would be for 40 seats?",
  "context": "Reply from a prospect who attended a product demo last week.",
  "minConfidence": 0.8
});
console.log(result);

Input contract

FieldTypeNeeded
messagestringRequired
contextstringOptional
minConfidencenumberOptional
Full input and result schemas
{
  "input": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "message": {
        "type": "string"
      },
      "context": {
        "type": "string"
      },
      "minConfidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "required": [
      "message"
    ]
  },
  "result": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "model": {
        "type": "string"
      },
      "usage": {
        "type": "object",
        "properties": {
          "input_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          },
          "output_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          }
        },
        "required": [
          "input_tokens",
          "output_tokens"
        ],
        "additionalProperties": false
      },
      "status": {
        "type": "string",
        "enum": [
          "ready",
          "review"
        ]
      },
      "score": {
        "type": "number",
        "minimum": 0
      },
      "level": {
        "type": "integer",
        "minimum": 0,
        "maximum": 9007199254740991
      },
      "confidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "probabilities": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "number",
          "minimum": 0,
          "maximum": 1
        }
      },
      "intent": {
        "type": "string",
        "enum": [
          "none",
          "curious",
          "evaluating",
          "ready",
          "committed"
        ]
      }
    },
    "required": [
      "model",
      "usage",
      "status",
      "score",
      "level",
      "confidence",
      "probabilities",
      "intent"
    ],
    "additionalProperties": false
  }
}

Saved example result

This hand-authored response demonstrates the contract. It is not a model accuracy measurement. Run it without an API key: npx jev-recipes demo buying-intent.

{
  "model": "demo-fixture",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  },
  "status": "ready",
  "score": 2.06,
  "level": 2,
  "confidence": 0.84,
  "probabilities": {
    "0": 0.01,
    "1": 0.04,
    "2": 0.84,
    "3": 0.1,
    "4": 0.01
  },
  "intent": "evaluating"
}

Evaluation evidence

Earlier-evaluator measurement

jev-1.13.0 / 2026-09-27 / 25 held-out cases

Scoring revision 1.

96%All-case accuracy
1Sent for review
0Failed calls / cases

24 ready decisions, with 96% accuracy among those decisions.

95% case-level interval: 80% to 99%. Related synthetic cases are correlated.

Measured on these synthetic cases

This measurement uses an earlier or unverified recipe or evaluator version. Rerun with the current recipe and evaluator before treating these numbers as current.

Full report and missesDataset and labels

Use the evaluation guide to measure this decision on your own labeled cases.

Limitations

Related recipes