> ## Documentation Index
> Fetch the complete documentation index at: https://manual.botric.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Prompts

> Every tracked prompt, every platform's answer, and whether you were named or cited.

The **Prompts** tab is the raw evidence behind your GEO score. For each prompt you see what every AI platform actually said, and where you landed.

## The four outcomes

Each prompt/platform pair resolves to one of four states. This is the vocabulary the whole report uses.

| Outcome              | Meaning                                                                         |
| -------------------- | ------------------------------------------------------------------------------- |
| **Named and cited**  | The brand appears in the answer and a brand URL is a source. No gap.            |
| **Named, not cited** | The engine names the brand but sourced the answer elsewhere. **Content gap.**   |
| **Cited, not named** | A brand page is a source but the brand goes unnamed. **Positioning gap.**       |
| **Not mentioned**    | Invisible for this prompt — no name in the answer, no brand URL in the sources. |

<Tip>
  *Named, not cited* is the most fixable state. The model already knows who you are — it just didn't have a page of yours worth quoting. That's a content problem with a clear answer.
</Tip>

## Filtering

Narrow the list by:

* **Platform** — ChatGPT, Gemini, Claude, Perplexity, Copilot, Grok, DeepSeek, Meta AI, Mistral, Poe, AI Overview.
* **Outcome** — mentioned, not mentioned, cites you, cites a competitor, cites both, neither.
* **Intent type** — Informational, Commercial, Comparison, Buyer intent, Branded, Locational, Adjacent, Direct, General.

## Intent types

Every prompt is classified by what the person asking actually wants.

| Intent            | Example shape                           |
| ----------------- | --------------------------------------- |
| **Informational** | "What is …"                             |
| **Commercial**    | "Best tools for …"                      |
| **Comparison**    | "X vs Y"                                |
| **Buyer intent**  | "Pricing for …", "How much does … cost" |
| **Branded**       | Prompts naming your brand directly      |
| **Locational**    | "… in `<city>`"                         |
| **Adjacent**      | Neighbouring problems your buyers have  |
| **Direct**        | Straightforward product questions       |

Coverage across intent types matters as much as raw volume: winning every informational prompt while losing every comparison prompt is a losing position.

## Reading an answer

Open any prompt to see the full response from each platform, the sources it cited, which competitors it named, and the sentiment of your mention. **Draft reply** turns a weak answer into a content brief.

## Managing tracked prompts

Prompt Explorer, reachable from the toolbar, holds the tracked prompt set:

* **Tracked prompts** are generated and refilled by Botric to your plan's cap on every run.
* **Add-on prompts** are yours — fixed slots per site, available on paid plans. Locked slots show as **Locked**.

<Note>
  A run bills the full tracked cap plus your add-on prompts, regardless of how many prompts are currently visible. See [How credits work](/reference/credits).
</Note>

Saved prompts don't appear in results until the next run. When that happens, the overview shows a **stale prompts** banner.

## Next steps

<CardGroup cols={2}>
  <Card title="Prompt Research" icon="telescope" href="/discoverability/prompt-research">
    Trial a prompt before you track it.
  </Card>

  <Card title="Content gaps" icon="puzzle-piece" href="/discoverability/ai-visibility/content-gaps">
    Turn losing prompts into a content plan.
  </Card>
</CardGroup>