AI Overviews Tracker — Brand Visibility in AI Answers

AI Overviews Tracker is an Apify Actor for marketers, SEO and GEO teams, brand managers, and AI agents that want to track a brand in AI-generated overviews. It accepts a brand name and commercial keywords, then returns one record per keyword x query x platform check. Each record includes whether the brand was mentioned, where it first appeared, whether it was recommended, the nearby sentiment, share of voice versus competitors, cited sources, and a response excerpt. This Actor is usable through Apify MCP and through the Apify API.

Best fit and connected workflows

This Actor fits workflows centered on commercial-intent AI visibility:

• GEO and brand monitoring audits for category keywords where AI overviews surface product recommendations.
• Competitive tracking across Perplexity, ChatGPT, Claude, and Gemini.
• Brand presence reviews for queries such as "suitable CRM for small business", "email marketing software", or "project management tools".
• Agent-driven reporting pipelines that read dataset rows and summarize visibility by platform, keyword, and template.

If your workflow starts from a brand name and a list of purchase-intent keywords, this Actor turns that input into structured checks at the query level.

Focused standalone workflow

This Actor is designed as a focused standalone workflow.

Practical scenario

A product marketer at a SaaS company wants to check whether the company appears in AI overviews for "payment processing software" and "payment API for developers". They enter the brand name, choose a few commercial keywords, and run the Actor on Perplexity, ChatGPT, and Gemini.

The returned records show the platform, keyword, query template, whether an overview was triggered, whether the brand was mentioned, the first sentence position, recommendation status, sentiment, share of voice, and cited sources. The marketer reviews a record where the brand appears in sentence 2 with neutral sentiment and moderate share of voice, then uses that result to decide which category terms deserve a deeper review.

Input fields

Field	Type	Required	Purpose
brandName	string	Yes	Brand, product, or company name to track in AI-generated overviews.
keywords	array of strings	Yes	Commercial keywords to query across AI platforms. Supports up to 20 keywords per run.
competitors	array of strings	No	Competitor brand names for comparison and share-of-voice analysis.
platforms	array of strings	No	AI platforms to query. Default: perplexity, chatgpt, gemini.
queryTemplates	array of strings	No	Query template categories such as best_of, comparison, and how_to_choose.
customQueries	array of strings	No	Extra custom questions that run in addition to query templates.
maxQueriesPerKeyword	integer	No	Maximum distinct queries per keyword across templates. Default: 3.
responseFormat	string	No	concise or detailed; controls excerpt length only.
webhookUrl	string	No	HTTPS endpoint that receives the run summary when the execution completes.
demoMode	boolean	No	Health-check mode that exits without making AI API calls.

Focused input example

{
  "brandName": "HubSpot",
  "keywords": [
    "CRM for small business",
    "email marketing software"
  ],
  "competitors": [
    "Salesforce",
    "Pipedrive"
  ],
  "platforms": [
    "perplexity",
    "chatgpt",
    "gemini"
  ],
  "queryTemplates": [
    "best_of",
    "comparison",
    "how_to_choose"
  ],
  "maxQueriesPerKeyword": 2,
  "responseFormat": "detailed"
}

Output fields

Each dataset item represents one keyword x query x platform check.

Field	Type	Meaning
run_id	string	Apify execution reference grouping results from the same run.
platform	string	AI platform queried: perplexity, chatgpt, claude, or gemini.
keyword	string	Commercial keyword submitted to the platform.
query	string	Full query text sent to the AI platform.
query_template	string	Template used to generate the query.
brand_name	string	Brand or product name being tracked.
overview_triggered	boolean	Whether the AI returned a rich informational overview.
overview_type	string	comparison, recommendation, explanation, or none.
overview_word_count	integer	Word count of the AI response for that query.
brand_mentioned	boolean	Whether the brand appeared in the overview response.
brand_position	integer or null	Sentence number where the brand first appears.
brand_recommendation	string	recommended, mentioned, or not_mentioned.
brand_sentiment	string or null	positive, neutral, or negative.
brand_context	string or null	1-2 sentences around the brand mention.
competitor_appearances	array	Per-competitor mention and context details.
share_of_voice	number	Brand share of all brand+competitor mentions in the overview.
cited_sources	array	URLs cited by the AI platform.
total_sources	integer	Number of source URLs cited.
overview_excerpt	string	First 300-550 characters of the AI response.
model_used	string	Exact AI model or provider route used for the check.
checked_at	string	ISO 8601 timestamp of the check.

Illustrative output record

{
  "run_id": "run_123",
  "platform": "perplexity",
  "keyword": "CRM for small business",
  "query": "What are the suitable CRM for small business solutions available?",
  "query_template": "best_of",
  "brand_name": "HubSpot",
  "overview_triggered": true,
  "overview_type": "recommendation",
  "overview_word_count": 184,
  "brand_mentioned": true,
  "brand_position": 2,
  "brand_recommendation": "recommended",
  "brand_sentiment": "positive",
  "brand_context": "The response highlighted HubSpot as a strong option for small teams. It also compared it with several other CRM tools.",
  "competitor_appearances": [],
  "share_of_voice": 1,
  "cited_sources": [
    "https://example.com/source-1"
  ],
  "total_sources": 1,
  "overview_excerpt": "HubSpot is often presented as a strong choice for small businesses seeking a CRM with marketing automation and sales tooling...",
  "model_used": "perplexity/sonar",
  "checked_at": "2026-01-01T12:00:00.000Z"
}

How it works

This Actor uses the supplied brand name, keywords, selected platforms, and query templates to generate commercial-intent AI overview checks.

Implementation facts visible in the contract:

1. It supports Perplexity, ChatGPT, Claude, and Gemini, with Perplexity, ChatGPT, and Gemini selected by default.
2. It generates queries from built-in templates such as best_of, comparison, how_to_choose, buyer_intent, feature_query, and versus, plus any customQueries.
3. It records one dataset item per keyword x query x platform combination.
4. It detects whether an overview was triggered, classifies the overview type, and tracks brand mention, sentence position, recommendation status, sentiment, and share of voice.
5. It stores cited sources, a response excerpt, the model or provider route used, and the check timestamp.
6. It can send a completion webhook with the run summary, and it stores a run summary in the key-value store under LAST_RUN_SUMMARY.

The dataset view is titled "AI Overview Brand Visibility" and surfaces the most practical fields for review: platform, keyword, template, overview presence, type, brand found status, position, recommendation status, sentiment, share of voice, total sources, and checked time.

Pricing

This Actor uses Pay per event pricing plus standard Apify platform usage.

The charged events in the live contract are:

• apify-actor-start
• overview-keyword-checked

The overview-keyword-checked event is billed for one keyword x one query x one AI platform queried. Apify platform usage is billed separately for compute. For current pricing details and the live Pricing tab, check the Actor page in Apify.

Example in words: if you run five keywords across three queries on four platforms, that is sixty overview checks plus one actor start event, and the total combines event charges with Apify platform usage.

Use with AI agents (MCP)

This Actor is an Apify Actor usable through Apify MCP. Its exact identity is khadinakbar/ai-overviews-tracker.

Tool description: submit a brand name, commercial keywords, and optional competitor, platform, query template, and webhook settings, then receive structured per-check records that agents can read for visibility analysis, reporting, and workflow branching.

Use khadinakbar/ai-overviews-tracker for brand visibility analysis. Track the brand name "HubSpot" across the keywords "CRM for small business" and "email marketing software", include competitors such as "Salesforce" and "Pipedrive", and query Perplexity, ChatGPT, and Gemini. Return the dataset rows and summarize which queries triggered overviews, where HubSpot appeared, and how share of voice differs by platform.

Output interpretation:

• brand_mentioned and brand_position show whether the brand appears and where it first appears in the overview.
• brand_recommendation distinguishes explicit recommendation language from plain mention.
• brand_sentiment captures nearby tone.
• share_of_voice shows the brand's portion of brand-plus-competitor mentions in that overview.
• cited_sources and total_sources preserve provenance for the platform response.
• overview_excerpt provides a compact response sample for review.

Scope, pagination, and cost guidance:

• Each dataset row represents one keyword x query x platform check.
• Larger input sets produce more dataset rows because queries expand across keywords and platforms.
• responseFormat changes excerpt length only, which helps tune review depth and storage size.
• demoMode supports integration checks and workflow validation before a live run.

Apify API example

import { ApifyClient } from "apify-client";

const client = new ApifyClient({
  token: process.env.APIFY_TOKEN,
});

const input = {
  brandName: "HubSpot",
  keywords: ["CRM for small business", "email marketing software"],
  competitors: ["Salesforce", "Pipedrive"],
  platforms: ["perplexity", "chatgpt", "gemini"],
  maxQueriesPerKeyword: 2,
  responseFormat: "detailed",
};

const run = await client.actor("khadinakbar/ai-overviews-tracker").call(input);

const { items } = await client.dataset(run.defaultDatasetId).listItems();

console.log("Run ID:", run.id);
console.log("Dataset items:", items);

Best results and outcome guidance

Use a brand name that matches how people and AI systems refer to the product in sentences. Pair it with commercial keywords that signal buying intent, such as category searches, comparison searches, and selection searches.

Helpful routing patterns:

• Use best_of for category discovery.
• Use comparison when you want competitive framing.
• Use how_to_choose for selection criteria coverage.
• Add versus when comparing your brand with alternatives.
• Increase maxQueriesPerKeyword when you want broader coverage across template types.
• Use demoMode for integration checks and workflow validation.

For cleaner review, start with a short keyword set and a narrow platform set, then expand once you see which categories produce the most useful overviews.

Design note

I found that the dataset contract centers each record on a single keyword x query x platform check, which makes the output easy to aggregate by platform, keyword, or template.

FAQ

Which inputs matter most for a first run?

brandName and keywords are required. A focused first run usually adds one or two platforms and a small set of query templates.

How is this different from domain citation tracking?

This Actor tracks brand visibility in commercial AI overview boxes. Domain citation tracking focuses on whether a URL is cited as a source.

Can I compare my brand with competitors?

Yes. Add competitor brand names in competitors and the Actor will capture mention, position, recommendation status, sentiment, and share of voice for each one.

Which platforms are available?

The live contract includes Perplexity, ChatGPT, Claude, and Gemini. Perplexity, ChatGPT, and Gemini are selected by default.

When should I use customQueries?

Use customQueries when you want exact wording across all platforms, or when you want to add a question that complements the built-in query templates.

Responsible use

Use this Actor for legitimate brand monitoring, competitive intelligence, and workflow automation. The results reflect AI-generated content at the time of the run and may vary across subsequent runs. Review the terms and policies for each AI provider used in the run.