🔭 AI Search Visibility Tracker: does ChatGPT recommend your brand?

Measure how often ChatGPT, Perplexity, Gemini and Claude mention, rank and cite your brand versus your competitors, with statistics you can trust.

More and more buyers skip Google and ask AI: "What's the best CRM for a small team?" If the AI names three competitors and not you, you lose that customer and never find out. This Actor asks the AI engines the questions your buyers ask, as many times as you choose, and turns the answers into a visibility score, share of voice, rankings, cited sources and a to-do list.

• ✅ Bring your own keys (OpenAI, Perplexity, Gemini, Anthropic): you pay the AI vendors at cost, plus a small per-answer fee. Try it first with the free demo.
• ✅ 4 engines, all with live web search: ChatGPT · Perplexity · Gemini · Claude
• ✅ 95% confidence intervals. AI answers change from run to run, so we sample each question several times and report an honest range instead of one lucky screenshot.
• ✅ Beautiful HTML report, plus JSON and a dataset of every answer
• ✅ Weekly trend tracking with Apify Schedules

---

🤔 What is AI search visibility (GEO)?

Generative Engine Optimization (GEO), also called AEO or LLM SEO, is the practice of getting your brand recommended in AI-generated answers. Traditional SEO tools cannot see inside ChatGPT. This Actor measures it directly:

Metric	What it tells you
Visibility score (0–100)	One number to track over time, overall and per AI engine
Mention rate ± 95% CI	How often you appear in answers, with a statistical range
Share of voice	Your share of all brand mentions, compared with competitors
Rank / recommended first	Whether you are listed first, third, or not at all
Citation rate	How often the AI cites your own website as a source
Prompt gaps	The exact questions where competitors appear but you don't
Source opportunities	The review sites and blogs AI cites when it recommends competitors, so you know where to get listed
Untracked competitors	Brands the AI keeps recommending that you didn't list
Sentiment	The tone of the text around each mention

🚀 Quick start (2 minutes)

1. Enter your brand, for example Notion | notion.com.
2. Add competitors, one per line.
3. Enter your category, for example project management software. We generate realistic buyer questions for you in English, Chinese, Korean or Japanese.
4. Paste the API keys of the engines you want to measure.
5. Click Start, then open the HTML report in the Output tab.

💡 Just want to see the output? Run it with no keys. You get a free demo report built on fictional brands.

⬇️ Input example

{
  "brand": "Notion | notion.com | Notion AI",
  "competitors": ["ClickUp | clickup.com", "Asana | asana.com", "Monday.com | monday.com | monday"],
  "category": "project management software",
  "useCases": ["remote teams", "startups"],
  "engines": ["chatgpt", "perplexity", "gemini"],
  "samplesPerPrompt": 3,
  "country": "United States",
  "projectName": "notion-weekly"
}

⬆️ Output

• HTML report (key-value store → REPORT): KPI cards, recommendations, leaderboard, per-engine heatmap, prompt gaps, source opportunities
• Summary JSON (OUTPUT): all metrics, ready for dashboards and APIs
• Dataset: one row per AI answer, containing engine, prompt, whether you were mentioned, rank, whether you were cited, sentiment, every brand in order, cited domains, full answer text and the search queries the AI ran

Example dataset row:

{
  "engine": "Perplexity", "prompt": "What are the best project management software options right now?",
  "brandMentioned": true, "brandRank": 2, "brandCited": true, "brandSentiment": 0.5,
  "brandsMentioned": ["ClickUp", "Notion", "Asana"],
  "citedDomains": ["zapier.com", "notion.com", "g2.com"]
}

💵 How much does it cost?

You pay only for answers that were successfully analysed. Failed calls and demo runs are free.

Mode	Price per AI answer	100 answers	Who pays the AI vendor
Bring your own keys	$0.015	$1.50	You, at the vendor's cost price

A typical weekly check of 8 questions × 3 engines × 2 samples = 48 answers costs $0.72 plus the AI vendors' own costs on your keys. Use Max answers per run to cap your spend.

🎯 Who is it for?

• Marketing and SEO teams tracking brand presence in AI search
• Agencies producing monthly GEO reports for clients (schedule it and share the HTML report)
• Founders checking whether AI recommends their product or a competitor's
• PR and content teams deciding which publications to target, based on source opportunities

🔁 Track trends weekly

Give your runs a projectName and create an Apify Schedule, for example every Monday. Each report then shows how every metric changed since the last run, plus new gaps and closed gaps. Connect the dataset to Google Sheets, Slack, Looker Studio or Make through Apify integrations.

🧠 How it works

1. Each question is sent to each engine through its official API with web search turned on: the OpenAI Responses API with web search, Perplexity Sonar, Gemini with Google Search grounding, and Claude with web search.
2. Each answer is scanned for brand names and aliases. Word boundaries prevent false matches, so "Monday" does not match "Mondays". The scan also records list positions, cited URLs and sentiment.
3. Results are aggregated into the metrics. The visibility score is 100 × (0.5·mention rate + 0.3·avg(1/rank) + 0.2·citation rate).

🤖 Use it from AI agents (MCP): Claude, Cursor & any MCP client

This Actor works as a ready-made connector for AI assistants. Add one URL and your agent can call it on its own:

https://mcp.apify.com?tools=lsso/ai-search-visibility-tracker

• Claude (claude.ai / Claude Desktop): Settings → Connectors → Add custom connector, paste the URL above, sign in to Apify.
• Cursor / VS Code / any MCP client: add it to your MCP config:

{ "mcpServers": { "ai-visibility": { "url": "https://mcp.apify.com?tools=lsso/ai-search-visibility-tracker" } } }

• Claude Code: claude mcp add --transport http ai-visibility "https://mcp.apify.com?tools=lsso/ai-search-visibility-tracker"

Sign-in uses Apify OAuth in the browser, so you never paste a token into the config. Then just ask:

"Does ChatGPT recommend my brand (Acme CRM) when people ask for the best CRM for small teams? Compare with HubSpot and Pipedrive."

"Which websites do Perplexity and Gemini cite when they answer questions about project management tools?"

"Give me a to-do list to get my product mentioned more often in AI answers."

Results include a visibility score, share of voice and a prioritized to-do list, ready for the agent to explain. You pay only for results, same as a normal run.

❓ FAQ

Is this the same as what I see in the ChatGPT app? It is very close. The Actor uses the vendors' official APIs with live search, which is the same retrieval technology. The consumer apps may add personalisation or memory, so treat the results as a repeatable, market-level measurement.

Why sample each question several times? AI answers are non-deterministic. One run can show you at #1 and the next can leave you out entirely. Sampling gives a real rate with a confidence interval.

Is it legal? Does it scrape anything? Nothing is scraped. All data comes from the vendors' official APIs. No logins are used and no personal data is collected.

Can I use my own API keys? Yes. Keys are stored as secret inputs, used only for your run, and never written to the results. BYOK runs are billed at the lower rate.

Which languages are supported? Questions can be generated in English, Chinese, Korean and Japanese, and you can write custom questions in any language. You can also set the answer language and market with language and country.

Can I use it from an AI agent, n8n or Make? Yes. Call it through the Apify API or the Apify MCP server, and read OUTPUT for machine-readable results.

📝 Changelog

• 1.2 (2026-09-24): Built-in access removed; the Actor now always runs on your own keys (or the free demo), so the per-answer fee stays low and predictable.
• 1.1: Built-in AI access (no keys needed). Automatic fallback when a free Gemini key has no search quota. Smarter retries on rate limits.
• 1.0: First release: 4 engines, confidence intervals, source opportunities, trend tracking, HTML report.