For the complete documentation index, see llms.txt. This page is also available as Markdown.

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.

Preparing documents optimally for the knowledge base

So that 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 running text instead of scanned documents

  • Avoid tables if possible or convert them into running text

Supported formats: PDF, TXT, DOCX, Markdown, PPTX, XLSX, PNG and JPEG. One file per upload is possible, with a maximum of 10 MB.

Content optimization

  • For extensive content, split it into multiple topic-based documents

  • Automatically generated document titles can be renamed at any time – meaningful titles make later overviews easier

  • Avoid duplicates with customer questions already stored

What does a good document look like?

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

Less suitable:

  • Content that mainly consists of tables, images, or graphics

  • Scanned PDFs in which the text is only available as an image

Expand and update the knowledge base

Your AI Agent's knowledge base 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 inappropriate, download the document or edit it in the original source. Then upload the updated version to the knowledge base and delete the old document.

Note: If the AI Agent uses inappropriate information in individual conversations, sipgate Customer support can check which knowledge document was used in the respective call. Have the date and time of the call ready for this.

Knowledge base vs. playbooks – What is the difference?

The features serve different functions.

Knowledge base: Determines, what the AI Agent can say.

That is, which information, facts, and answers are available to it.

Playbooks: Determine, how the AI Agent proceeds.

That is, which steps are carried out in a conversation, for example collecting callback data or forwarding a request to an employee.

In the Enterprise plan Knowledge sources and processes can be connected and automated more individually. Our team supports you from conception through implementation.

Last updated