AI Brand Visibility Tracker — ChatGPT, Perplexity, Gemini
Ask AI assistants the questions your customers ask. Track brand mentions and competitor rank per answer; Perplexity runs include provider citations, while other modes label URLs found in the answer. Bring your own API keys.
AI Brand Visibility Tracker — ChatGPT, Perplexity, Gemini returns 12 documented output fields, including provider, model, sampleIndex, answerMode and citationMode. Every field carries a declared type, a written description and an example value. 48 runs are recorded on Apify.
Run it on ApifyPay per result · no subscription
- 12
- Output fields
- 18
- Inputs
- 48
- Runs
- 2026-10-16
- 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 |
|---|---|---|---|
| provider | stringnull | The AI provider this row measured. | openai |
| model | stringnull | The model that produced this answer. | gpt-4.1 |
| sampleIndex | integernull | Which sample run this row came from, when the same prompt is asked more than once. | 0 |
| answerMode | stringnull | Whether the answer came from the model's own knowledge or from live search. | <answerMode> |
| citationMode | stringnull | How citations were presented in the answer. | <citationMode> |
| brandCited | booleannull | Whether the brand was cited in the answer. | true |
| competitorsCited | stringnull | Competitor domains the answer cited. | <competitorsCited> |
| prompt | stringnull | The prompt this record resulted from. | <prompt> |
| mentioned | booleannull | Whether the brand was mentioned at all. | true |
| rankAmongTracked | integernull | Rank within the set this run tracked. | 0 |
| competitorsMentioned | stringnull | Competitors mentioned in the answer. | <competitorsMentioned> |
| citedDomains | stringnull | Domains the answer cited. | <citedDomains> |
02 — sample
One record
Assembled from the example values declared on the schema above, not invented at render time.
{
"provider": "openai",
"model": "gpt-4.1",
"sampleIndex": 0,
"answerMode": "<answerMode>",
"citationMode": "<citationMode>",
"brandCited": true,
"competitorsCited": "<competitorsCited>",
"prompt": "<prompt>"
}03 — input
What you give it
| Input | Type | Description |
|---|---|---|
| brandName | stringrequired | The brand or product name to look for in AI answers, e.g. Notion. |
| brandAliases | arrayoptional | Other names the AI might use for the same brand (old names, abbreviations, product lines). Counted as brand mentions. |
| brandDomain | stringoptional | For citation analysis only, e.g. notion.so. Perplexity rows can then show whether an official brand domain was cited. Leave blank if you only want name mentions. |
| competitors | arrayoptional | Competitor names to track in the same answers. Rank is the order of first mention among your brand and these names. |
| competitorDomains | objectoptional | Map each tracked competitor name to its official domain, e.g. {"Evernote": "evernote.com"}. Used only for provider-citation analysis. |
| topic | stringoptional | What your customers would ask about, e.g. 'note-taking apps'. Generates a 5-question panel (best/recommend/compare/choose/list). Ignored if you supply custom prompts below. |
| prompts | arrayoptional | Your own questions, one per line. If set, these replace the auto-generated panel. |
| openaiApiKey | stringoptional | Secret — supply your own value. |
| openaiWebSearch | booleanoptional | Optional and off by default. Uses OpenAI's Responses API web_search tool, forces a live search for each question, and records provider-returned sources. This can cost more than a normal model answer. |
| anthropicApiKey | stringoptional | Secret — supply your own value. |
| perplexityApiKey | stringoptional | Secret — supply your own value. |
| geminiApiKey | stringoptional | Secret — supply your own value. |
| models | objectoptional | Optional model per provider, e.g. {"openai": "gpt-4o", "anthropic": "claude-opus-5"}. Leave empty for the cost-efficient defaults. |
| runsPerPrompt | integeroptional | Repeat each provider-question pair to measure answer variation. Start with 1; use 5 or more before treating the displayed confidence range as a useful directional signal. Each sample uses your provider API and counts toward max answers. |
| promptSetVersion | stringoptional | Label this exact question panel, for example 2026-Q3. Change it when you intentionally change prompts, competitors, or measurement design; history comparisons will then safely start a new baseline. |
| historyStoreId | stringoptional | For recurring measurement, enter a reusable named Apify key-value store. The next compatible run then reports visibility and rank deltas. Leave blank for a one-off scan. |
| historyKey | stringoptional | Use a different key for each brand or market panel that shares the same history store. |
| maxItems | integeroptional | Hard limit on analyzed answers (providers × questions). Strictly enforced — you will never be charged for more than this. |
04 — run
Run AI Brand Visibility Tracker 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
12 of 12 fields described
- What does AI Brand Visibility Tracker — ChatGPT, Perplexity, Gemini return?
- It returns 12 documented output fields: provider, model, sampleIndex, answerMode, citationMode, brandCited, competitorsCited, prompt, mentioned, rankAmongTracked, competitorsMentioned and citedDomains. Each field declares its type, a description of what it holds, and an example value.
- What input does AI Brand Visibility Tracker — ChatGPT, Perplexity, Gemini require?
- brandName is required. A further 17 inputs are optional. The full input schema, with types and defaults, is below.
- Does AI Brand Visibility Tracker — ChatGPT, Perplexity, Gemini need an API key or login?
- Yes — openaiApiKey, anthropicApiKey and perplexityApiKey are marked secret and must be supplied by you. Nothing else in the input schema needs credentials.
- How do I run AI Brand Visibility Tracker — ChatGPT, Perplexity, Gemini?
- 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.