> For the complete documentation index, see [llms.txt](https://docs.airops.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.airops.com/insights/prompts/query-fanouts.md).

# Query Fanouts

See the search queries AI platforms use while researching answers to your tracked prompts.

A query fanout is a search query an AI platform uses while researching an answer. **Query Fanouts** shows the queries AirOps observes for your tracked prompts, helping you understand how a platform expands a question into searches for supporting information.

## How to configure the view

1. Open **Insights → Prompts → Query Fanouts**.
2. Choose the date range you want to analyze.
3. Filter by platform, topic, prompt, tag, prompt intent, or prompt type.
4. Search for query text, or filter by observation count, prompt count, or last observed date.
5. Sort the table to find frequent queries or queries shared across several prompts.

Coverage depends on the query data AirOps collects from each platform. Platforms without query fanout data are disabled in the platform selector. The view includes observed ChatGPT queries; it does not represent every search an AI platform performs.

## Read the table

| Column            | Meaning                                                                                                                                            |
| ----------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Query fanout**  | The search query observed while the platform researched an answer.                                                                                 |
| **Observations**  | How many times AirOps observed the query within the selected dates and filters. The change compares it with the preceding period of equal length.  |
| **Prompts**       | The number of distinct tracked prompts associated with the query. Hover to see up to 10 originating prompts and a count of any additional prompts. |
| **Platforms**     | AI platforms where AirOps observed the query.                                                                                                      |
| **Topics**        | Topics associated with its originating prompts.                                                                                                    |
| **Last observed** | The most recent observation within the selected scope.                                                                                             |

A query can appear more than once for the same prompt, so observations and distinct prompts measure different things. A percentage change is unavailable when the previous period has no observations.

The **Query Fanouts** column in [Your prompts](/insights/prompts/your-prompts.md) provides a prompt-level view. Hover over its count to preview queries for that prompt; the selected platform filter applies there too.

## Inspect the originating prompts

Click a query fanout to open its detail panel. The panel lists the tracked prompts associated with that query, including each prompt's topic, observation count, platforms, and last observed date.

Use the date, platform, and topic controls to narrow the results. Scroll the table to load more prompts. This lets you inspect the full matching set beyond the table's hover preview.

## Example

For a tracked prompt such as “Which project management tools work well for distributed teams?”, a platform might search for product comparisons, pricing, or integrations. Search those terms in Query Fanouts and inspect the originating prompts to understand which research questions recur across your tracked set.

Use this evidence to review content coverage. An observed search query does not guarantee that the platform cites a particular page or mentions your brand.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.airops.com/insights/prompts/query-fanouts.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.