# AI visibility URL: https://serpel.app/docs/ai-visibility Updated: 2026-11-05 AI visibility in Serpel shows whether ChatGPT with web search and Google AI Overviews cite or mention your website when someone asks your prompts. You add prompts, Serpel checks them on demand or on your monitoring schedule, and each check stores the answer excerpt and its sources. Perplexity, Gemini and Claude are not measured. ## What does AI visibility measure? Serpel measures where an AI answer can mention your website: in ChatGPT with web search and in Google AI Overviews. For each prompt it records whether the answer links a page of your domain, which Serpel calls cited, whether your name or domain only appears in the text, which it calls mentioned, and which sources the answer lists. The [AI visibility feature page](https://serpel.app/features/ai-visibility) gives the overview, and the page on [AI Overview tracking](https://serpel.app/features/ai-overview-tracking) covers the Google side. - **2** AI surfaces measured: ChatGPT and Google AI Overviews - **2 credits** per ChatGPT answer: Charged for delivered answers only - **2 credits** per Google AI Overview: Only when the project setting is on - **50** prompts per project on Pro: Fewer on the other plans | Detail | ChatGPT with web search | Google AI Overview | | --- | --- | --- | | What Serpel sends | Your prompt, asked to ChatGPT with web search for the country and language of the prompt. | Your prompt as a Google search for the same country and language, on the device of your rank checks. Serpel reads the first 10 results and the AI Overview. | | What Serpel stores | The cited and mentioned result, an excerpt of about 700 characters and up to 10 sources. | Whether an AI Overview appears, the cited and mentioned result, an excerpt and up to 10 sources. | | Where you see it | **Cited in ChatGPT**, the prompt list and the prompt page. | **In Google AI Overviews**, the prompt list and the **Google AI Overview** section of the prompt page. | Serpel doesn’t query Perplexity, Gemini, Claude or any other assistant. An AI answer can change from one run to the next, so one check is one sample. Compare several checks in the history of a prompt before you act on a single result. Rank checks also record whether a Google AI Overview appears for each tracked keyword, which the [rank tracking guide](https://serpel.app/docs/rank-tracking) describes. ## How does Serpel decide whether you are cited or mentioned? Serpel evaluates every answer with fixed rules. No model judges the answer. The rules look at the sources the answer lists and at its text. **Cited, mentioned or not mentioned** - **Cited** (Link): A page of your domain, or of one of its subdomains, is among the sources the answer lists. A cited answer counts as mentioned too. Shown as **Cited**. - **Mentioned** (Name only): No source links your domain. Your domain or your project name appears in the text, or the answer names your domain as a brand. Shown as **Mentioned**. - **Not mentioned** (Absent): The answer has no link to you and doesn’t name you. Competitors can still be cited. Shown as **Not mentioned**. The domain counts as mentioned when its text appears anywhere in the answer, ignoring case. Your project name counts when it has at least 4 characters, differs from your domain and appears as a whole word. If ChatGPT writes your brand differently from your project name, rename the project under **Settings → General**. Serpel stores the same matching for Google AI Overviews, but the dashboard shows only three results for them. **Cited** means that a source of the AI Overview links your domain. **Not cited** means that Google shows an AI Overview and your website is not among its sources. **Not mentioned** means that Google shows no AI Overview for the prompt. Illustration: A ChatGPT answer that names a project in the text and lists its page as a source, shown with demo data. ## How do prompts work? A prompt is the question a customer would ask an AI assistant. Write it the way people ask, with a location, an occasion or a price range. A prompt needs 3 to 500 characters. Adding a prompt costs nothing and doesn’t start a check. When you add prompts in the dashboard, they use the country and language of the project. With the CLI or the API you can set a different country and language per prompt. How many prompts a project can hold depends on your plan: | Plan | Prompt slots per project | One check of all prompts, ChatGPT only | One check of all prompts, both surfaces | | --- | --- | --- | --- | | No subscription | 10 | 20 credits | 40 credits | | Starter | 25 | 50 credits | 100 credits | | Pro | 50 | 100 credits | 200 credits | 1. **Open AI visibility.** In the sidebar, open **AI visibility** under **Monitoring**. 2. **Click Prompt.** The button at the top right opens the dialog **Prompts for ChatGPT**. On an empty page, the button reads **Add prompts**. 3. **Enter your prompts.** Type one prompt per line in **Prompts, one per line**. The dialog shows how many slots are free and warns about prompts shorter than 3 or longer than 500 characters. Prompts that already exist are skipped. 4. **Add and check.** Click **Add prompt**. With several lines, the button reads **Add** and the number, for example **Add 3 prompts**. The answers arrive with the next check. To remove a prompt, use the bin icon **Remove prompt**. This also deletes its history. ## How do you run checks and monitoring? **What a check does** 1. **Ask ChatGPT**: Serpel sends the prompt to ChatGPT with web search for the country and language of the prompt. 2. **Evaluate**: Fixed rules decide cited, mentioned or not mentioned. Serpel keeps up to 10 sources and an excerpt. 3. **Search Google** (If switched on): With **Also check Google AI Overview** on, Serpel also searches the prompt on Google and evaluates the AI Overview. 4. **Charge**: You pay for each result that was delivered. Failed checks cost nothing. To check one prompt, open it and click **Check prompt**. To check all prompts, press Ctrl+K or Cmd+K on **AI visibility** and choose **Check prompts**. Both show the credit estimate. The check runs in the background, a banner shows its progress, and only one check runs per project at a time. Monitoring checks all prompts on your schedule, together with your tracked keywords, and then writes a report. You set the frequency and the time under **Settings → Monitoring**. A schedule needs at least one tracked keyword or one prompt. The [monitoring and reports guide](https://serpel.app/docs/monitoring-and-reports) explains schedules, reports and notifications. ## How do you read the AI visibility page? | Area | What it shows | | --- | --- | | **Cited in ChatGPT** | In how many of the checked prompts ChatGPT links your website, with the change since the previous check. | | **In Google AI Overviews** | In how many of the checked prompts the Google AI Overview links your website. The detail line tells you when tracking is off in the project settings. | | **Mentioned, not cited** | Prompts where your name appears in the answer but no source links you. | | **Total sources** | The number of sources across all latest answers. | | **Prompts** | One row per prompt with the latest result (**Cited**, **Mentioned**, **Not mentioned**, **Failed** or **Not checked yet**), the Google AI Overview result and the badges **Newly cited** and **No longer cited**. | | **Cited sources** and **ChatGPT result** | The domains that ChatGPT links most often in the latest answers, and a chart of the results across all prompts. | | Prompt page | The **Latest answer**, the **Sources of the answer**, the **Google AI Overview** section and the **Check history** with the last 60 checks per platform. | Illustration: The AI visibility page with summary tiles, the result per prompt and the most cited sources, shown with demo data. **Cited** is the strongest result: the answer used a page of yours as a source. **Mentioned** means the answer names you but links no page of yours, so open **Sources of the answer** to see which pages it used instead. With **Not mentioned**, the same list shows who the assistant cites for that prompt. The badges **Newly cited** and **No longer cited** mark changes between two checks. Use **Cited sources** to see which domains ChatGPT links most often for your topics, and compare several checks before you draw conclusions from one. ## What does an AI visibility check cost? A check costs 2 credits per prompt for the ChatGPT answer. The Google AI Overview adds 2 credits per prompt, but only when **Also check Google AI Overview** is on. It is on by default and sits under **Settings → Ranking check**. A check of 10 prompts costs up to 20 credits with ChatGPT alone and up to 40 credits with both surfaces. Serpel reserves the maximum when a check starts and charges only for results it delivered, so a failed check is free. If Serpel serves a recent stored answer for the same prompt, the prompt page marks the answer as served from the cache, and it is charged like any other delivered result. Reading results in the dashboard, with the CLI or over MCP is free. [Credits and billing](https://serpel.app/docs/credits-and-billing) lists every price and explains reservations. ## How do you use AI visibility from the CLI, API or MCP? The CLI and the REST API cover everything above. Over MCP an agent can only read the stored results. The [CLI](https://serpel.app/docs/cli) adds prompts, runs checks and prints the summary. The [REST API](https://serpel.app/docs/api) returns the same data as JSON, and its reference also lists the endpoints for a prompt’s history and for removing prompts. The MCP tool `get_ai_visibility` returns up to 25 prompts per call and never starts a check. The [Claude Code guide](https://serpel.app/docs/mcp/claude-code) shows how to connect an agent. | Task | CLI | API | MCP | | --- | --- | --- | --- | | Add prompts | `serpel ai add --project --prompt "…"` | `POST /projects/{id}/ai-prompts` (`rankings:write`) | Not available | | List prompts with results | `serpel ai prompts --project ` | `GET /projects/{id}/ai-prompts` (`rankings:read`) | `get_ai_visibility` | | Check prompts | `serpel ai run --project --wait` | `POST /projects/{id}/ai-prompts/run` (`rankings:write`) | Not available | | Summary | `serpel ai status --project ` | `GET /projects/{id}/ai-visibility` | `get_ai_visibility` | | Crawler access and llms.txt | `serpel ai status --project ` | `GET /projects/{id}/ai-visibility` | Not available | | History of a prompt | `serpel ai history ` | See the API reference | Not available | ```bash serpel ai add --project --prompt "best espresso beans for home" serpel ai run --project --wait serpel ai status --project ``` ## What can go wrong? | What you see | Why | What to do | | --- | --- | --- | | A prompt shows **Failed** | The check couldn’t deliver an answer, for example because the data provider returned an error. The prompt page shows the message under **Last request failed**. Temporary outages are retried automatically. | Wait for the retry, or click **Check prompt** again. Failed checks cost nothing. | | ChatGPT names your brand but the result reads **Not mentioned** | Your project name is shorter than the minimum, differs from how ChatGPT writes your brand, or isn’t a whole word in the text. | Rename the project under **Settings → General** to your brand name. | | A prompt can’t be added | All slots of your plan are in use, the prompt has fewer than 3 or more than 500 characters, or it already exists, in which case Serpel skips it. | Remove a prompt you no longer need, shorten the text, or upgrade your plan. | | The Google AI Overview stays empty | **Also check Google AI Overview** is off, or Google shows no AI Overview for that prompt in that country. | Switch the setting on under **Settings → Ranking check**, then check the prompt again. | | A check can’t be started | A check is already running for the project. | Wait until the banner at the top of the page has finished, then start the next check. | ## Where to go next - [Monitoring and reports](https://serpel.app/docs/monitoring-and-reports): Check prompts and keywords on a schedule and get a report. - [SerpelBot](https://serpel.app/docs/serpelbot): See how your robots.txt treats AI crawlers. - [Rank tracking](https://serpel.app/docs/rank-tracking): Track Google positions and the AI Overview per keyword. - [Credits and billing](https://serpel.app/docs/credits-and-billing): Prices, plans and how reservations work.