Jev Review Intelligence Pro — Advanced Classifier
Enrich supplied review records with typed themes, severity, refund intent, and actionable-detail judgments.
Jev Review Intelligence Pro — Advanced Classifier returns 8 documented output fields, including id, sourceUrl, capturedAt, rating and text. Every field carries a declared type, a written description and an example value. 7 runs are recorded on Apify.
Run it on ApifyPay per result · no subscription
- 8
- Output fields
- 4
- Inputs
- 7
- Runs
- 2026-10-15
- Last run
01 — output
What it returns
Every field the extractor writes to its dataset, with its type, a written description and an example value.
| Field | Type | What it holds | Example |
|---|---|---|---|
| id | string | Stable identifier from the source. Use it to link records across runs. | EXAMPLE-0001 |
| sourceUrl | string | The page or endpoint this row was read from. | https://example.com/thread |
| capturedAt | string | ISO 8601 timestamp of when this record was captured or archived. | 2026-10-18T07:30:00Z |
| rating | number | Average rating as reported by the source. | 4 |
| text | string | Plain text content of this record. | The item's text, as its author wrote it. |
| judgments | object | The model's structured answers. **Null when the judgement call failed**, so it must be null-checked before it is read. | {"preferred_entity":{"choice":"brand","confidence":0.91}} |
| decision | object | The classified decision, with a status and the reason for it. On a failed call the status is 'failed' and the answers are null. | {"status":"clear","preferredEntity":"Example Brand","confidence":0.91,"reason":"Named first and unambiguously."} |
| telemetry | object | What the call cost and how it went — model, latency, attempts and estimated cost. Null when no call succeeded. | {"provider":"typesafe","model":"example-model","templateId":"tpl-1","latencyMs":1840,"attempts":1,"inputTokens":820,"outputTokens":96,"estimatedCostUsd":0.00004} |
02 — sample
One record
Assembled from the example values declared on the schema above, not invented at render time.
{
"id": "EXAMPLE-0001",
"sourceUrl": "https://example.com/thread",
"capturedAt": "2026-10-18T07:30:00Z",
"rating": 4,
"text": "The item's text, as its author wrote it.",
"judgments": "{\"preferred_entity\":{\"choice\":\"brand\",\"confidence\":0.91}}",
"decision": "{\"status\":\"clear\",\"preferredEntity\":\"Example Brand\",\"confidence\":0.91,\"reason\":\"Named first and unambiguously.\"}",
"telemetry": "{\"provider\":\"typesafe\",\"model\":\"example-model\",\"templateId\":\"tpl-1\",\"latencyMs\":1840,\"attempts\":1,\"inputTokens\":820,\"outputTokens\":96,\"estimatedCostUsd\":0.00004}"
}03 — input
What you give it
| Input | Type | Description |
|---|---|---|
| reviews | arrayrequired | Already-collected reviews. Collection permission remains the caller's responsibility. |
| typesafeApiKey | stringoptional | Secret — supply your own value. |
| provider | stringoptional | Use fake only for contract testing. |
| confidenceThreshold | numberoptional | Minimum confidence required before a result is accepted rather than marked for review. |
04 — run
Run Jev Review Intelligence Pro on your own input
It runs in the cloud on Apify. Nothing to install, and you are billed per result returned rather than per attempt.
05 — questions
Asked before running it
8 of 8 fields described
- What does Jev Review Intelligence Pro — Advanced Classifier return?
- It returns 8 documented output fields: id, sourceUrl, capturedAt, rating, text, judgments, decision and telemetry. Each field declares its type, a description of what it holds, and an example value.
- What input does Jev Review Intelligence Pro — Advanced Classifier require?
- reviews is required. A further 3 inputs are optional. The full input schema, with types and defaults, is below.
- Does Jev Review Intelligence Pro — Advanced Classifier need an API key or login?
- Yes — typesafeApiKey is marked secret and must be supplied by you. Nothing else in the input schema needs credentials.
- How do I run Jev Review Intelligence Pro — Advanced Classifier?
- It runs on Apify. Start it from its listing with the inputs above, or call the Apify API with the Actor's ID. Results land in a dataset you can export as JSON, CSV or Excel, or read through the Apify API into your own pipeline.