AEO Tracker — AI Answer Mentions, Rank & Citations avatar

AEO Tracker — AI Answer Mentions, Rank & Citations

Pricing

from $40.00 / 1,000 aeo answer checks

Go to Apify Store
AEO Tracker — AI Answer Mentions, Rank & Citations

AEO Tracker — AI Answer Mentions, Rank & Citations

Track AEO across ChatGPT, Gemini, Claude and Perplexity: brand mentions, rank, own-site citations, sentiment and competitors. USD 0.04-0.05 per answer check.

Pricing

from $40.00 / 1,000 aeo answer checks

Rating

0.0

(0)

Developer

Muhammad Afzal

Muhammad Afzal

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

20 days ago

Last modified

Categories

Features

Limited permissions

Share

AEO Tracker asks ChatGPT, Gemini, Claude, and Perplexity your buyer questions with live web search and returns, for every answer, whether your brand was mentioned, where it was ranked, whether your own site was cited, the sentiment, and which competitors appeared. It is built for SEO teams, agencies, and product marketers who track answer engine optimization (AEO), and it costs USD 50 per 1,000 answer checks (USD 0.05 per check) on the FREE tier, with no start fee.

Free users: maximum 20 results per run.

What does the AEO tracker return?

You get one dataset row per question × answer engine, plus a run summary. Each row is one "AEO check":

FieldWhat it tells you
brand, brandDomainThe brand you track and the official domain used for citation matching
query, queryIndexThe buyer question that was asked and its position in the run
engineChatGPT, Gemini, Claude, or Perplexity
modelRequested, modelUsed, responseIdThe neutral label fixed-ai-model (the internal model is not exposed; modelUsed is null when no answer came back) and a response ID for audit trails
mentioned, mentionCountWhether the answer or its sources named your brand or domain, and how often
mentionContextThe sentence containing the first mention
citedtrue when a cited source URL is on your official domain
recommendationPositionYour explicit rank in a ranked recommendation, or null when the answer did not rank
sentimentpositive, negative, neutral, or mixed treatment of your brand
competitorMentionsCompetitors from your list that the answer named
citationsSource URLs and titles the answer was grounded on
summary, answerTextA short summary and the answer text (length-bounded)
usageToken counts for the answer
errorFailure reason, or null on success
checkedAtUTC timestamp

The OUTPUT record in the run's key-value store (copied to SUMMARY) adds an engineBreakdown per engine and a 0–100 visibilityScore.

How do I check my AEO score?

Run the Actor with your brand, domain, and 2–5 neutral buyer questions, then read visibilityScore in OUTPUT. The score is 70% mention rate plus 30% official-domain citation rate across successful checks, so a brand mentioned in every answer but never cited scores 70. The same formula is applied per engine in engineBreakdown, which shows where you are strong and where you are missing.

Treat the score as directional. Answers change between runs, so compare runs that use the same questions.

How do I track whether ChatGPT, Gemini, Claude, and Perplexity mention my brand?

Give the Actor neutral questions that do not name your brand, and it records whether each engine surfaces you on its own:

  1. Enter brandName and, for citation detection, brandDomain.
  2. Add up to 20 queries, or set industry and the Actor writes three category questions for you.
  3. List up to 30 competitors to see who appears next to you.
  4. Set maxChecks (1–50). Each question goes to ChatGPT, Gemini, Claude, and Perplexity in that order until the cap is reached, so 3 questions fill the default 12 checks.
  5. Export the dataset as JSON, CSV, or Excel, and open OUTPUT for the per-engine summary.
{
"brandName": "Notion",
"brandDomain": "notion.so",
"queries": [
"What are the best productivity tools for a small remote team?",
"Which productivity apps are easiest for teams to adopt?"
],
"competitors": ["Asana", "Coda"],
"maxChecks": 8,
"searchContextSize": "low"
}

Every engine answers through an API with live web search, using one fixed, cost-controlled model per engine that no input can change. You do not need an account or API key for any AI service.

What does an AEO check look like?

This row comes from a real check (truncated; citations shortened, model identifiers and token counts omitted):

{
"brand": "Notion",
"brandDomain": "notion.so",
"query": "What are the best productivity software options for a buyer comparing reputable providers?",
"queryIndex": 0,
"engine": "ChatGPT",
"mentioned": true,
"mentionCount": 1,
"mentionContext": "Notion combines notes, databases, wikis, and lightweight project tracking in a customizable workspace...",
"cited": false,
"recommendationPosition": null,
"sentiment": "positive",
"competitorMentions": [],
"citations": [
{ "url": "https://asana.com/resources/best-team-collaboration-software/", "title": "11 Best Team Collaboration Software Tools Compared" },
{ "url": "https://www.forbes.com/advisor/in/business/software/project-management-software/", "title": "Best Project Management Software Of 2025" }
],
"summary": "Notion is presented as a flexible all-in-one workspace, alongside reputable options suited to different productivity needs. No provider is explicitly ranked first.",
"error": null,
"checkedAt": "2026-10-26T07:41:37.690Z"
}

In that check Notion was mentioned but its own site was not among the sources, which is the gap AEO work tries to close.

How much does AEO tracking cost?

AEO Tracker uses pay-per-event pricing, active since September 17, 2026, with no change scheduled. Model and web-search costs and Apify platform usage are included.

EventFREEBRONZESILVERGOLDPLATINUMDIAMOND
aeo-check: one successful question × engine answer$0.05$0.05$0.05$0.04$0.04$0.04

There is no Actor start fee: this Actor charges nothing per started GB of allocated memory, so you pay only for successful checks. Free users: maximum 20 results per run.

  • Default input (3 questions × 4 engines = 12 checks): 12 × $0.05 = $0.60 on FREE to SILVER, 12 × $0.04 = $0.48 on GOLD and above.
  • Store prefill (1 check): $0.05 on FREE.

Failed checks are saved with a non-null error and not charged. An answer that does not mention you is a valid, charged result. A maximum total charge set on the run stops the Actor when it is reached.

When should I use AEO Tracker, and when not?

Use it when the question is about your brand inside the answer: is it mentioned, ranked, cited, and described well by each engine?

Choose a sibling Actor when you need something else:

It does not read the consumer chat apps, logged-in sessions, or location-specific results, and it is not a Google rank tracker.

Use it from an AI assistant

AEO Tracker works from Claude, ChatGPT, Cursor, or any MCP client through Apify's MCP server. Add it as a single tool with https://mcp.apify.com/?tools=muhammadafzal/aeo-tracker, then ask, for example: "Run an AEO check for Notion (notion.so) on three questions about team productivity apps, compare it with Asana and Coda, and tell me which engines never mention it."

How do I run it from the API?

JavaScript (apify-client):

import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('muhammadafzal/aeo-tracker').call({
brandName: 'Notion',
brandDomain: 'notion.so',
industry: 'productivity software',
maxChecks: 4,
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
const summary = await client.keyValueStore(run.defaultKeyValueStoreId).getRecord('OUTPUT');
console.log(items.length, summary?.value.visibilityScore);

Python (apify-client 3.x):

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("muhammadafzal/aeo-tracker").call(run_input={
"brandName": "Notion",
"brandDomain": "notion.so",
"industry": "productivity software",
"maxChecks": 4,
})
for item in client.dataset(run.default_dataset_id).iterate_items():
print(item["engine"], item["mentioned"], item["cited"])

Apify schedules, webhooks, and integrations with Make, Zapier, n8n, and Google Sheets can run the same question set weekly and forward results.

Limits and reliability

  • Up to 20 questions, 30 competitors, and 50 checks per run.
  • Default run timeout is 300 seconds; each answer request times out after 120 seconds. Raise the run timeout for runs near 50 checks.
  • Paid runs retry a transient failure once; free-plan runs make one request per check.
  • sentiment, recommendationPosition, and summary come from the answering model. Mentions, citations, and competitors come from case-insensitive text matching, so short or generic brand names can match unrelated words; check mentionContext.
  • If AI access is rejected for the Actor, the run stops, keeps delivered rows, and charges nothing for unfinished checks.

FAQ

What is an AEO tracker?

An AEO tracker records whether AI answer engines mention, rank, and cite a brand for the questions buyers ask. AEO Tracker does this for ChatGPT, Gemini, Claude, and Perplexity and returns one row per answer.

Is AEO different from GEO?

The terms overlap. AEO usually means being the answer an assistant gives; GEO (generative engine optimization) covers the wider work of being cited and recommended. AEO Tracker measures answers; the Generative Engine Optimization Tool adds a prioritized action list.

Do I need an AI API key?

No. Model and web-search costs are paid by the Actor owner inside the aeo-check price. You only need an Apify account.

Why do results differ between runs?

Models vary their wording, web results change, and engines update their models. Read trends across several runs with the same questions.

How often should I run it?

Weekly or monthly with a fixed question set suits most teams. Use an Apify schedule so each run is comparable.

Does a missing citation mean the engine ignores my brand?

No. An answer can recommend you without linking your site. mentioned and cited are reported separately for that reason.

AEO Tracker sends ordinary questions to AI model APIs and records the answers; it does not access private accounts. AI answers can be wrong or outdated, so verify important statements against primary sources, and do not use the results to make misleading claims about competitors. No tool can guarantee how an AI product presents your brand.

Last verified: 2026-10-27