What does Jev AEO & GEO Visibility Enricher — AI Search return?

It returns 11 documented output fields: id, prompt, engine, answer, sourceUrl, capturedAt, deterministic, judgments, preferredEntity, decision and telemetry. Each field declares its type, a description of what it holds, and an example value.

What input does Jev AEO & GEO Visibility Enricher — AI Search require?

brand and responses are required. A further 5 inputs are optional. The full input schema, with types and defaults, is below.

Does Jev AEO & GEO Visibility Enricher — AI Search 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 AEO & GEO Visibility Enricher — AI Search?

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.

Jev AEO & GEO Visibility Enricher — AI Search

Enrich supplied answer-engine responses with brand stance and recommendation judgments.

Jev AEO & GEO Visibility Enricher — AI Search returns 11 documented output fields, including id, prompt, engine, answer and sourceUrl. Every field carries a declared type, a written description and an example value. 6 runs are recorded on Apify.

Run it on ApifyPay per result · no subscription

11: Output fields
7: Inputs
6: 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
prompt	string	The prompt this record resulted from.	Which CRM do you recommend for a small team?
engine	string	Engine that produced this result.	chatgpt
answer	string	The answer produced for the paired question.	The answer text, exactly as captured. The evidence the judgement was made on.
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
deterministic	object	Evidence computed from the text itself without a model — which entities are named and how often. The check on the model's judgement, and it is still available when the judgement call fails.	{"brandMentions":3,"competitorsNamed":["Northwind"],"evidence":"The brand is named three times, first."}
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}}
preferredEntity	string	Which entity the answer treats as preferred, resolved back to a name. Null where the answer names none clearly.	Example Brand
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",
  "prompt": "Which CRM do you recommend for a small team?",
  "engine": "chatgpt",
  "answer": "The answer text, exactly as captured. The evidence the judgement was made on.",
  "sourceUrl": "https://example.com/thread",
  "capturedAt": "2026-10-18T07:30:00Z",
  "deterministic": "{\"brandMentions\":3,\"competitorsNamed\":[\"Northwind\"],\"evidence\":\"The brand is named three times, first.\"}",
  "judgments": "{\"preferred_entity\":{\"choice\":\"brand\",\"confidence\":0.91}}"
}

03 — input

What you give it

Input	Type	Description
brand	stringrequired	Tracked brand name.
aliases	arrayoptional	Alternative names for the tracked brand.
competitors	arrayoptional	Named competitors to compare only in supplied answers.
responses	arrayrequired	Answers already collected from an approved source; this Actor does not query answer engines.
typesafeApiKey	stringoptional	Secret — supply your own value.
provider	stringoptional	Use fake only for contract tests; typesafe performs live Jev judgments.
confidenceThreshold	numberoptional	Minimum confidence required before a result is accepted rather than marked for review.

04 — run

Run Jev AEO & GEO Visibility Enricher 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.

Open on Apify ↗

Also in ai, marketing

05 — questions

Asked before running it

11 of 11 fields described

What does Jev AEO & GEO Visibility Enricher — AI Search return?: It returns 11 documented output fields: id, prompt, engine, answer, sourceUrl, capturedAt, deterministic, judgments, preferredEntity, decision and telemetry. Each field declares its type, a description of what it holds, and an example value.
What input does Jev AEO & GEO Visibility Enricher — AI Search require?: brand and responses are required. A further 5 inputs are optional. The full input schema, with types and defaults, is below.
Does Jev AEO & GEO Visibility Enricher — AI Search 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 AEO & GEO Visibility Enricher — AI Search?: 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.