> For the complete documentation index, see [llms.txt](https://docs.crobox.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.crobox.com/how-to-guides/sagent/setup/general.md).

# General

Create Sagent and configure its core settings.

The **General** section establishes Sagent's identity, catalog scope, and response defaults. These settings affect which products Sagent discusses and how shoppers experience each conversation.

Configure these settings before testing conversations. Then connect product data and configure the remaining setup areas.

### Before you begin

Make sure product data is available in Crobox. You also need access to **Experiences** and a catalog containing the intended assortment.

If product data is not available yet, first review:

* [Setting up a Product Feed](/how-to-guides/product-data/setting-up-a-product-feed.md)
* [Manage and Transform Product Properties](/how-to-guides/product-data/manage-and-transform-product-properties.md)
* [AI Enricher Properties (text-based)](/how-to-guides/product-data/ai-enricher-properties-text-based.md)

### Configure General settings

Open **Setup → General**. Configure the following fields, then click **Save**.

<details>

<summary>Chatbot Name</summary>

This is Sagent's internal name in the experience overview. It helps teammates identify the correct Sagent.

It does not control the shopper-facing chat title. Set that in **Content → General → Chat Title**.

</details>

<details>

<summary>Product Categories</summary>

Select the product categories Sagent should cover. This limits Sagent's conversation and recommendations to the intended assortment.

Choose only categories supported by the connected catalog. Add categories when shoppers should discover products across them.

</details>

<details>

<summary>Match visitor's language</summary>

Enable **Match visitor's language** to let Sagent respond in the visitor's active language. This affects AI-generated conversation responses.

Enable it only for locales with synced product data and reviewed static translations. Otherwise, shoppers can encounter incomplete product or interface content.

</details>

<details>

<summary>Max Chat Message Length</summary>

Set the maximum length of a shopper message. Messages beyond this limit show the **Input Text Too Long Error** from **Content**.

Use a limit that supports detailed questions without allowing excessively long input. Test the error message after changing this value.

</details>

<details>

<summary>Chat Reasoning Effort</summary>

Set how much reasoning Sagent applies before responding. Higher effort can support complex product questions.

Higher effort can also increase response time. Start with the default, then test simple and complex shopper requests.

</details>

<details>

<summary>Chat Verbosity</summary>

Set how detailed Sagent's answers should be. Lower verbosity keeps product discovery fast. Higher verbosity gives shoppers more explanation and trade-off detail.

Use a level that matches the category. Test it with the selected **Chat Reasoning Effort** and your target language.

</details>

{% hint style="info" %}
Next, configure the catalog in [Products](/how-to-guides/sagent/data/products.md). Review [Knowledge](/how-to-guides/sagent/data/knowledge.md) after syncing.
{% endhint %}

### Test the data connection

Open **Setup → General** and start a preview conversation. Confirm Sagent can access the intended product data before configuring other tabs.

### Frequently asked questions

<details>

<summary>Does Chatbot Name change the shopper-facing title?</summary>

No. **Chatbot Name** identifies Sagent internally. Set the shopper-facing title in **Content → General → Chat Title**.

</details>

<details>

<summary>When should I enable Match visitor's language?</summary>

Enable it when each visitor language has a synced catalog data and reviewed static interface translations.

</details>


---

# 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.crobox.com/how-to-guides/sagent/setup/general.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.