Recipe catalog / spam-signal
Detect spam content
Is message unsolicited promotional, scam, or bulk content rather than a genuine contribution?
You need a yes/no gate before publishing, forwarding, or replying to community posts, comments, or inbound messages.
Explore this recipe interactively ยท Source and implementation guide
Use spam-signal 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 { spamSignal } from 'jev-recipes/spam-signal';
const result = await spamSignal({
"message": "Congratulations!! You have been selected for a $500 gift card. Claim now at bit.ly/claim-prize-4421 before it expires tonight!!!",
"context": "Reply posted in a community forum thread about troubleshooting a printer driver.",
"minConfidence": 0.8
});
console.log(result);
Input contract
| Field | Type | Needed |
|---|---|---|
| message | string | Required |
| context | string | Optional |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$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"
]
},
"probability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"verdict": {
"type": "string",
"enum": [
"spam",
"genuine"
]
}
},
"required": [
"model",
"usage",
"status",
"probability",
"confidence",
"verdict"
],
"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 spam-signal.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"probability": 0.97,
"confidence": 0.97,
"verdict": "spam"
}
Evaluation evidence
No verified live accuracy measurement is available. Evaluate representative cases before using this decision in your workflow.
Use the evaluation guide to measure this decision on your own labeled cases.
Limitations
- Judges content semantically. It does not check sender reputation, posting frequency, or where links lead.
- Removal, hiding, and appeal decisions belong in application code.
Related recipes
- turn-intent: Use turn-intent to classify what a genuine message is trying to do.
- response-needed: Use response-needed to decide whether a genuine message calls for a reply.