> For the complete documentation index, see [llms.txt](https://help.sipgate.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.sipgate.com/documentation/en/behavior/wissensdatenbank.md).

# knowledge base

In addition to individual customer questions, you can provide your AI Agent with a knowledge base containing your own content, such as FAQs or product information.

The agent uses this content to better understand requests and derive suitable answers. The knowledge base can be expanded or updated at any time.

<figure><img src="/files/954b696d1202dad747c9a215c8f8a52d34d6076f" alt=""><figcaption></figcaption></figure>

### Preparing documents for the knowledge base optimally

So that your AI Agent can process the uploaded documents as well as possible, you should keep the following things in mind when preparing them.

#### **Structure & format**

* Use a clear structure with meaningful headings
* Use plain text instead of scanned documents
* Avoid tables where possible or convert them into plain text

{% hint style="info" %}
**Supported formats:** PDF, TXT, DOCX, Markdown, PPTX, XLSX, PNG and JPEG. One file per upload is possible, with a maximum of 10 MB.
{% endhint %}

#### **Content optimization**

* For extensive content, split it into several thematic documents
* Automatically generated document titles can be renamed at any time – meaningful titles make it easier to keep track later
* Avoid duplications with already stored customer questions

#### What does a good document look like?

{% columns %}
{% column %}
**Well suited:**

* Pure, clearly structured text documents with a clearly defined topic, because the AI Agent can evaluate text particularly reliably
* Meaningful headings for each section
* Files with copyable text, for example Markdown or PDF
  {% endcolumn %}

{% column %}
**Less suitable:**

* Content that consists mainly of tables, images, or graphics
* Scanned PDFs in which text is available only as an image
  {% endcolumn %}
  {% endcolumns %}

{% hint style="warning" %}
**Notes:**

* Do not upload process descriptions or behavioral instructions for the AI Agent into the knowledge base. Such procedures belong in playbooks, because playbooks specifically control conversation steps and behavior. Content from the knowledge base cannot be read out as process instructions.
* Only store information in the knowledge base that may also be passed on to callers. The AI Agent can use content from the knowledge base in conversations. Confidential, internal, or non-public information therefore does not belong in the knowledge base.
  {% endhint %}

### Expand and update the knowledge base

The knowledge base of your AI Agent can be expanded and updated at any time. If content changes, upload the updated version manually. New or changed documents will then be taken into account in future conversations.

If answers seem incomplete or unsuitable, download the document or edit it in the original source. Then upload the updated version to the knowledge base and delete the old document.

{% hint style="info" %}
**Note:** If the AI Agent uses inappropriate information in individual conversations, the sipgate [**Customer Support**](https://www.sipgate.de/support-anfrage) can check which knowledge document was used in the respective call. Have the date and time of the call ready for this.
{% endhint %}

### Knowledge base vs. playbooks – What is the difference?

The features serve different functions.

{% columns %}
{% column %}
**Knowledge base:**\
Determines, **what** the AI Agent can say.

So which information, facts, and answers are available to it.
{% endcolumn %}

{% column %}
**Playbooks:**\
Determine, **how** the AI Agent proceeds.

So which steps are carried out in a conversation, for example collecting callback data or forwarding a request to an employee.
{% endcolumn %}
{% endcolumns %}

{% hint style="info" %}
In the [**Enterprise plan**](/documentation/en/plans-and-costs/enterprise-tarif-leistungen-und-einfuhrungsprozess.md) Knowledge sources and processes can be connected and automated more individually. Our team supports you from conception to implementation.
{% 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 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://help.sipgate.com/documentation/en/behavior/wissensdatenbank.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.