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

# AI Shopping Assistant

Use conversational product discovery to guide shoppers to relevant products.

The AI Shopping Assistant is a conversational product-discovery experience for FactFinder NG. Shoppers describe what they need in their own words, and the assistant turns that into a shortlist of relevant products from your catalog, with your ranking rules and campaigns still in effect.

**Keyword search works well when shoppers know what to type**. It works less well when they describe a goal ("something warm for a week of hiking in Norway"), an occasion, or several requirements at once. **The assistant complements your search for these shoppers**: it clarifies what they need and guides them to products they can act on. **It does not replace your existing search**.

What it can do for your shop:

* Increase shopper confidence and shorten the path to a decision.
* Improve discovery for complex and high-consideration products.
* Reduce repetitive product-advice requests to your sales and service teams.

<figure><img src="https://1825417961-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJAWI9K5DGdc6Ueyin3Ii%2Fuploads%2FaCs3uSJpR3UxracYyjp6%2Fimage.png?alt=media&amp;token=93628976-e067-4231-ad7a-699e4c065f36" alt=""><figcaption></figcaption></figure>

### Explore the documentation

<table data-card-size="large" data-view="cards"><thead><tr><th></th><th data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Understand the assistant</strong><br>Explore its product-discovery capabilities and how it handles shopper requests.</td><td><a href="/ai-shopping-assistant/ai-shopping-assistant/understand-the-assistant.md">Understand the assistant</a></td></tr><tr><td><strong>Get started</strong><br>Check requirements and prepare the assistant setup.</td><td><a href="/ai-shopping-assistant/ai-shopping-assistant/get-started.md">Get started</a></td></tr><tr><td><strong>Data privacy, limitations, and FAQ</strong><br>Review data processing, current scope, and common questions.</td><td><a href="/ai-shopping-assistant/ai-shopping-assistant/data-privacy-limitations-and-faq.md">Data privacy, limitations, and FAQ</a></td></tr><tr><td><strong>Analytics and reporting</strong><br>Understand the metrics and reporting available for the assistant.</td><td><a href="/ai-shopping-assistant/ai-shopping-assistant/analytics-and-reporting.md">Analytics and reporting</a></td></tr></tbody></table>

{% hint style="info" %}
**Availability:** The AI Shopping Assistant is available to selected customers. The assistant focuses on product discovery. Scope, features, and setup steps may change as capabilities evolve. If you're interested in testing this feature, contact our customer service team at <service-desk@fact-finder.com>.
{% 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 by asking a question.

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

```
GET https://docs.fact-finder.com/ai-shopping-assistant/ai-shopping-assistant.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.