> 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, product information, or process descriptions.
The agent uses this content to better understand requests and derive suitable answers. The knowledge base can be expanded or updated at any time.
### Preparing documents for the knowledge base optimally
To ensure your AI Agent can process the uploaded documents as effectively as possible, you should keep the following points in mind when preparing them.
#### **Structure & format**
* Use a clear structure with meaningful headings
* Use continuous text instead of scanned documents
* Avoid tables if possible or convert them into continuous text
* Images and graphics are not evaluated by the AI Agent
#### **Content optimization**
* For extensive content, split it into several topic-based documents
* Automatically generated document titles should not be changed manually
* Avoid duplicates with customer questions already stored
### Automatically captured knowledge
When creating an AI Agent, content from the stored company website can be automatically imported. This information serves as the basis for the agent's context and initial customer questions.
### Expand and update the knowledge base
Your AI Agent's knowledge base can be expanded and updated at any time. New documents, adjusted FAQs, or changed product information are automatically taken into account in future conversations.
If answers seem incomplete or inappropriate, you can specifically revise the underlying content. Clear topic structures and unambiguous wording help the agent reliably assign information and output it appropriately.
### Knowledge base vs. playbooks – what's 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:**\
Define, **how** the AI Agent proceeds.
So which steps are followed in a conversation, for example capturing callback details or forwarding a request to an employee.
{% endcolumn %}
{% endcolumns %}
Both areas work together and complement each other: the knowledge base provides the content, while playbooks control the structure and flow of the conversations.
{% hint style="info" %}
In the [**Enterprise plan**](/documentation/en/plans-and-costs/enterprise-tarif-leistungen-und-einfuhrungsprozess.md) knowledge sources and processes can be represented in even greater detail.
{% 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=&goal=
```
`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.