# Bot Management

In the top right, clicking the creation button brings up the dialog to enter the new bot’s details:

* the icon to immediatly identify it
* a label for identification
* a description
* its name (you can call him with his name!)
* the prompt (a default prompt is suggested, but it is important to customize it for better interaction!)
* some configurations for more granular management in the chat, such as enabling "Auto document selector" of documents, "Manual filters", and "Data scientist mode"
* the default language

<figure><img src="/files/iPfEUveAprHLHvI6RT9W" alt=""><figcaption></figcaption></figure>

For each bot, you can also:

* set the bot as the default for interactions via API
* upload a bot image
* modify any data set at the time of creation
* set filters (the area of the knowledge base to draw from) by selecting folders or document tags
* edit bot agentic filters
* duplicate the bot
* delete the bot (the default bot cannot be deleted)

<figure><img src="/files/sp6zG7uCqOVteM3NIOl1" alt=""><figcaption></figcaption></figure>

{% hint style="warning" %}
**Pay attention**

Once you create a bot, remember to set it among the available bots for each user you want to give access to!
{% endhint %}

### Defining parameters inside agentic filters

When selecting **Edit Bot Agentic Filters**, administrators can configure a dedicated set of parameters that control **how documents are indexed and searched**. These parameters are **directly associated with the Knowledge Base (KB) structure** (e.g., collections, folders, categories, or any hierarchical taxonomy you use), ensuring that retrieval and grounding behavior follows the same organizational logic used to manage content.

<figure><img src="/files/o9v5S9nE5NQJQbvNuxXT" alt="" width="563"><figcaption></figcaption></figure>

<figure><img src="/files/RW6LGM61pZq7l9JS5imB" alt="" width="563"><figcaption></figcaption></figure>

Within **Edit Bot Agentic Filters**, administrators can define detailed parameters that the assistant must use to correctly interpret user inputs and to scope document retrieval inside the Knowledge Base. Each parameter includes:

* **A Description:** A textual description of what the parameter represents.
* **A Prompt rule** (validation + expected format):  the **validation logic** the assistant uses to check whether the value provided by the user is valid.
* **Examples** for user guidance
* **Configuration controls:**
  * **Max attempts:** it's possible to defines the **maximum number of times** the assistant will attempt to obtain the required parameter(s) from the user
  * **Active: t**he **Active** toggle allows administrators to **enable or disable a specific parameter** without deleting it.
  * **Mandatory: f**f a parameter is marked as **Mandatory**, it becomes a **required condition to start the conversation flow** (or to start the search/grounding phase, depending on your implementation).


---

# Agent Instructions: 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:

```
GET https://40factory.gitbook.io/wilson/3.10/wilson-academy/settings/bot-management.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.