> For the complete documentation index, see [llms.txt](https://support.quizkitapp.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://support.quizkitapp.com/ai-shopping-assistant/setting-up-ai-assistant/training-ai-responses.md).

# Training AI responses

Train AI Shopping Assistant to learn from your own questions and responses.

After you've synced your store, you can add custom responses to help train the AI Shopping Assistant chatbot to give accurate, on-brand answers to customer questions. 

This helps AI Shopping Assistant handle store-specific inquiries that go beyond the information it automatically learns from your synced products and collections. Use custom responses to share details like shipping times, return policies, or special promotions, and even link to relevant products or collections when it’s helpful. 

Over time, this can make AI Shopping Assistant more reliable, consistent, and aligned with your store’s tone of voice.

***

## Add a custom response

**Steps:**

1. From the AI Shopping Assistant dashboard, click **Train AI**.
2. Click **Add a new response**.
3. In the **Question** text box, enter a customer question such as `How long does shipping take?`
4.  In the **Response** text box, enter any details that you think will help the solve the customer's query. For example, `Shipping takes 5-7 business days. See our shipping policy for details.`
5. Optional: In the **Destination** **product page** text box, click the search bar, and check which products you want to recommend for this question, if applicable.
6. Click **Save**.


---

# 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://support.quizkitapp.com/ai-shopping-assistant/setting-up-ai-assistant/training-ai-responses.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.