AI Brand Visibility Tracker — ChatGPT, Perplexity, Gemini, Claude & Grok

Does AI recommend your brand — or your competitors? More and more buyers ask ChatGPT, Perplexity, Gemini or Claude for recommendations instead of searching Google. This Actor asks those AI assistants the questions your customers ask and measures how often they mention, rank and cite your brand compared with competitors. It also tracks how that changes week by week.

✅ No API keys needed · ✅ Each AI uses its own built-in web search · ✅ $0.05 per AI answer, pay only for what you use

What you get

Metric	Meaning
Mention rate	% of AI answers that mention your brand
Share of voice	Your share of all brand mentions vs tracked competitors
Average position	Where you appear in the AI's list (1 = first brand named)
Citation rate	% of answers that link to your website as a source
By engine	All of the above separately for ChatGPT, Perplexity, Gemini, Claude, Grok
Gaps	Questions where competitors are recommended and you are not. Your GEO to-do list
Sentiment	How each AI describes you: positive / neutral / negative, with a one-line reason
Top cited sources	Which websites AIs trust in your category. Get featured there
Change since last run	Week-over-week movement when you run it on a schedule

Plus a visual HTML report you can send to your boss or client, and every raw AI answer.

Why it's more accurate than one-off checks

AI answers are random: ask ChatGPT the same question twice and you can get different brands. Set Samples per prompt to 3–5 and the tracker asks each question several times, so you get a real probability of being mentioned instead of a coin flip.

How to use

1. Enter your brand, its domains, and 3–10 competitors (Asana, asana.com, one per line).
2. Add the questions your buyers ask, e.g. "best project management tool for small teams". Don't include your brand name. Or describe your category and let the Actor generate realistic questions.
3. Pick the AI engines and run.
4. Open the Visual report in the Output tab.
5. Schedule it weekly (Schedules → Create) to track trends. The Change since previous run section fills in automatically.

Pricing (pay per event)

Event	Price
AI check (one answer from one engine)	$0.05
AI check with your own OpenRouter key	$0.005
Visibility report (once per run)	$0.05

Example: 10 prompts × 4 engines × 1 sample = 40 checks + report = $2.05 per run, about $8.20/month if you run it weekly. Sentiment analysis and prompt generation are free.

Set Max cost per run and the Actor never spends past it. It checks your budget before each AI call.

Example answer record

{
  "type": "answer",
  "engineName": "Perplexity",
  "prompt": "What is the best tool for team documentation?",
  "brandMentioned": true,
  "brandPosition": 2,
  "brandCited": true,
  "brandsMentionedInOrder": ["Confluence", "Notion", "Coda"],
  "competitorsMentioned": ["Confluence", "Coda"],
  "citations": [{ "url": "https://www.notion.so/product/wikis", "domain": "notion.so", "brand": "Notion" }],
  "sentiment": "positive",
  "sentimentReason": "Recommended as the most flexible option for growing teams.",
  "answer": "…full AI answer…"
}

The last dataset item (type: "summary") holds the aggregated metrics, also saved as OUTPUT in the key-value store.

Notes & limitations

• Answers come from each vendor's API with native web search (via OpenRouter), using current fast models by default (override in Model overrides). The consumer apps (chatgpt.com etc.) may personalise answers for logged-in users, so treat results as a strong, consistent signal rather than a pixel-perfect copy.
• Brand detection is exact-match on your brand name and aliases, so add common spellings as aliases.
• Use User country and Answer language to measure visibility in a specific market.

FAQ

Is this GEO / AEO / LLM SEO? Yes. It's the measurement part of Generative Engine Optimization: find out where you stand, fix the gaps, track the results.

Can AI agents use it? Yes. It works through Apify's MCP server, and every output field is documented.

Need another engine or metric? Open an issue on the Issues tab. Fixes usually ship within 48 hours.