> For the complete documentation index, see [llms.txt](https://visi-digital-internasional.gitbook.io/geo-prospector/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://visi-digital-internasional.gitbook.io/geo-prospector/prospecting-workflows/multi-category.md).

# Multi-category search

Use Multi-Category Search to run several related business categories in one controlled job.

## Review selected categories

Each selected category is displayed as a separate chip. The category area wraps and expands automatically, allowing the complete selection to remain visible before the job starts.

Remove unintended categories before running the search.

## Example

Selected categories:

1. Software Company
2. Web Design Company
3. IT Consultant

Final target:

`30`

The initial allocation is approximately:

`10 + 10 + 10`

If one category returns fewer usable records, a balanced coverage pass can attempt to fill the remaining target from other available categories.

## Healthy execution pattern

```
Initial pass 1/3: Software Company
Initial pass 2/3: Web Design Company
Initial pass 3/3: IT Consultant
```

## Best practices

* Select categories that represent one market segment.
* Review all selected-category chips before starting.
* Expect some overlap between related categories.
* Keep Duplicate Filter enabled.
* Start with a moderate final target.
* Review category distribution before outreach.
* Wait for **Complete** before exporting data.

{% hint style="info" %}
A business can legitimately appear under more than one category. Duplicate Filter protects database quality while category labels help explain how the business was discovered.
{% endhint %}


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://visi-digital-internasional.gitbook.io/geo-prospector/prospecting-workflows/multi-category.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.