> For the complete documentation index, see [llms.txt](https://docs.maker.co/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.maker.co/maker-greatstore/knowledge/testing-answers.md).

# Testing answers

The **Knowledge** screen has a chat beside your sources. Ask it a policy question, a shipping question, or anything your catalogue cannot answer, and see how your sources respond.

{% hint style="warning" %}
Testing here uses the same AI as your live store, so it draws from your credits like any other message. See [Usage & credits](/maker-greatstore/insights-and-usage/usage-and-credits.md).
{% endhint %}

## What to try

* A question you know is answered — confirms the source was processed
* A question that is nearly answered — shows how it handles partial information
* A question with no source at all — shows what a shopper gets when you have a gap

## Reading the result

If an answer is wrong or thin, the fix is usually in the source rather than the phrasing: make the document state the answer plainly, in the words a shopper would use.


---

# 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://docs.maker.co/maker-greatstore/knowledge/testing-answers.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.