AI Shopping Tracker: which products ChatGPT, Perplexity, Gemini and Google's AI recommend

Shoppers now ask AI assistants what to buy. This Actor asks ChatGPT (OpenAI GPT with web search), Perplexity, Google Gemini, Claude, Grok and Google's AI Overview your shopping questions ("best robot vacuum for pet hair", "running shoes under $120 for beginners") and reads each answer into a ranked product list: product, brand, price, shop and the reason given, in the order the assistant recommends them. It shows whether your brands are recommended, and at what rank, which competitors win, and which shops and review sites the assistants cite.

Built for e-commerce brands, Amazon and DTC sellers, retail and category managers, agencies doing AI search (GEO) work and affiliate sites who need to know if AI shopping answers send buyers to them or to someone else, question by question and engine by engine.

What you get

Field	What it holds
Answer rows	question, engine, model, country, status, answer, products (rank, product, brand, price, currency, store, reason), productsCount, citations, shopsCited, aiCostUsd
Your brands	yourBrands: recommended or not, best rank, which of your products, named in the text, your site cited
Competitors	otherBrands: every other brand recommended, its best rank and products
SUMMARY	your brands' share of answers and average rank; the top brands and products across all answers; top brands per engine; total AI usage

What people use it for

• AI shelf share: how often each brand is recommended across the questions shoppers ask, and how high
• Competitor tracking: which rivals ChatGPT and Gemini put first for your category, week by week
• Product launches: whether a new product shows up in AI answers after launch
• Retail and affiliate: which shops and review sites the assistants cite for each category
• Pricing intelligence: the prices AI assistants quote for the products they recommend
• GEO reporting: before-and-after evidence for AI search optimisation work

How to use it

1. Enter shopping questions as shoppers ask them, and your brands (optional).
2. Pick the AI engines and the shopper's country.
3. Click Start. Schedule it weekly to track your AI shelf share.

Input

Field	Example	Notes
Shopping questions	What is the best robot vacuum for pet hair?	One per line
Your brands	Brand | brand.com	Optional; matched in the products and the text
AI engines	ChatGPT, Perplexity, Gemini	Also Claude, Grok, Google AI Overview
Shopper's country	US	Answers and prices follow it where the engine allows
Language	en	For Google's AI Overview
Answer length cap / Answers at once	2000 / 4	Advanced

Output

Each result is one row in the run's dataset (download it as JSON, CSV, Excel, XML or HTML, or read it through the API). An example row (values shortened):

{
  "kind": "shopping-answer",
  "question": "What is the best robot vacuum for pet hair?",
  "engine": "openai",
  "model": "openai/gpt-6.1-sol",
  "country": "US",
  "status": "ok",
  "products": [
    {
      "rank": 1,
      "product": "Acme RoboClean S9",
      "brand": "Acme",
      "price": 499,
      "currency": "USD",
      "store": "Example Mart",
      "reason": "strongest suction and a tangle-free brush"
    },
    {
      "rank": 2,
      "product": "Sample Vac X2",
      "brand": "Sample",
      "price": 329,
      "currency": "USD",
      "store": null,
      "reason": "best value for shedding pets"
    }
  ],
  "productsCount": 6,
  "yourBrands": [
    {
      "brand": "Sample",
      "recommended": true,
      "bestRank": 2,
      "products": [
        "Sample Vac X2"
      ],
      "mentioned": true,
      "cited": false
    }
  ],
  "otherBrands": [
    {
      "brand": "Acme",
      "bestRank": 1,
      "products": [
        "Acme RoboClean S9"
      ]
    }
  ],
  "shopsCited": [
    "amazon.com"
  ],
  "aiCostUsd": 0.087
}

A record named SUMMARY in the run's key-value store says what each input returned, with any notes (for example an account that does not exist), what was charged and how much traffic the run used.

Pricing

• $0.12 per shopping answer: one engine's answer to one question, read into products and matched to your brands
• AI usage for the assistants (and the product reading, with the newest Gemini Flash) is billed to your Apify account by Apify's own OpenRouter gateway at OpenRouter's rates; on 12 October 2026 an answer cost about $0.007 with Gemini, $0.03 with Perplexity, $0.05 with Claude and $0.09 with ChatGPT's model
• Failed calls are free, and so are questions Google answers without an AI Overview

What typical jobs cost at the list price:

Job	Cost
10 questions on ChatGPT, Perplexity and Gemini	$3.60 + AI usage (about $1.25)
25 category questions, 3 engines, every week for a month	$36 + AI usage
1 question on all six engines	$0.72 + AI usage

On Apify's Scale and Business plans the per-event prices are lower (Store discounts). Set Maximum cost per run and the Actor stops cleanly when it is reached: you never pay more than that.

Tips

• Write questions the way shoppers ask them, with the budget and the use: "best running shoes under $120 for flat feet".
• AI answers vary from run to run: track the same questions every week and read the trend.
• Add your main competitors as brands too: their rows then show side by side with yours.

Use it through the API

Python

from apify_client import ApifyClient

client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("zaiq/ai-shopping-tracker").call(run_input={"questions": ["What is the best robot vacuum for pet hair?"], "engines": ["openai", "perplexity", "gemini"], "country": "US"})
for row in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(row)

JavaScript

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });
const run = await client.actor('zaiq/ai-shopping-tracker').call({"questions": ["What is the best robot vacuum for pet hair?"], "engines": ["openai", "perplexity", "gemini"], "country": "US"});
const { items } = await client.dataset(run.defaultDatasetId).listItems();

HTTP (one call, results back)

curl -X POST 'https://api.apify.com/v2/acts/zaiq~ai-shopping-tracker/run-sync-get-dataset-items?token=<YOUR_APIFY_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{"questions": ["What is the best robot vacuum for pet hair?"], "engines": ["openai", "perplexity", "gemini"], "country": "US"}'

Integrations and schedules

• Schedules: run it every hour, day or week from the Apify Console (Schedules) and keep a history of results.
• Make, Zapier, n8n, Google Sheets, Slack, Airtable: connect it through Apify's integrations, or send each finished run to a webhook.
• Datasets: results stay in the run's dataset; export them or read them by API whenever you need them.

Use it with AI agents (MCP)

Add Apify's MCP server (https://mcp.apify.com) to Claude, ChatGPT, Cursor, VS Code or any MCP client. The agent can find this Actor and run it for you: ask it for "which robot vacuums ChatGPT, Perplexity and Gemini recommend for pet hair, and whether my brand is one of them". AI agents can also pay for runs directly through Apify's agentic payments.

Limits

• Answers are what each engine's API returns with web search at run time; the consumer apps can differ (personalisation, history, location).
• Products are read from the answer text by an AI model; check unusual rows against the answer, which is kept in every row.
• Google AI Mode is not included yet.

Optional: weekly monitoring, competitor gaps and a report

Off by default and at no extra charge (no new events):

• Project name (projectName): keeps every run's results under that name and compares each run with the last one: mentions gained and lost per question and engine, citation-rate moves, cited sites gained and lost, and competitors that appeared (record CHANGES). Schedule the Actor weekly to follow the movement.
• Report (includeReport): a one-page REPORT.html with the visibility score and its formula, per-engine tables, competitor gaps (the questions where a competitor is named or cited and you are not, with the sites cited there) and a fix list drawn from the pages the engines cite.
• Cited pages to read (maxCitedPages, default 8): how many of the cited pages are read for the fix list.

FAQ

Do I need my own OpenAI or Perplexity key?

No. The engines run through Apify's own OpenRouter gateway and the AI usage is billed to your Apify account.

Which models are used?

Each engine's newest model at run time (the run log and every row name it).

Can I check another country?

Yes: set the shopper's country; engines that accept a location use it.

How are my brands matched?

In the products' brand and name, in the answer text, and in the cited sites when you give a domain.

Is the full answer kept?

Yes: every row has the full answer next to the products read from it.

Related Actors from Zaiq

• ai-answer-tracker: your brand's visibility in AI answers for any question
• amazon-product-scraper: the recommended products' prices and ratings on Amazon
• walmart-scraper: the same products on Walmart

Support

Questions, a site that changed, or a field you need? Open an issue on this Actor's Issues tab: we answer there, usually within a day.

---

Also found as: ai shopping tracker, chatgpt shopping, ai product recommendations, chatgpt product visibility, generative engine optimization ecommerce, ai shelf share, perplexity shopping, ai search visibility for brands.