Information Regarding the resource management of the Knowledgebase and a description of central functions
Resources are the central sources for agents. They are part of the knowledge base and form the basis for the answers that the agents give in customer communication. This article describes how resource management takes place in the hub and which settings are possible.
- Resource management - Adding resources
- Ressource management - Information retrieval interval
- Resource management - Connect resources and agents
- Description of functions - Retrieval Augmented Generation
- Missing Knowledge
Resource management – Adding resources
Resources are added in the Knowledge Base Management area. It is accessed in the hub by clicking on the menu item knowledge base.
This area contains all resources that are used by the specific agents and the standard AI agent.
Click on the Add button to open an input screen. The source type is selected and then added by inserting the URL or PDF/CSV or creating the text document/question/answer pair. There are two ways to open the input mask:
1. Click on the button in the top right corner: 
2. Click the button RAG and then the button Add in the section information retrieval:
Here specific settings regarding the scraping of websites can be added by clicking the toggle labeled expert options (see more).
If a resource is to be completely removed, it is selected by ticking the box on the left-hand side. A Delete field then appears, which can be used to permanently remove the resource.
Ressource management – Information retrieval interval
The refresh interval allows you to set regular cycles for (re)checking a stored URL. Cycles of 7, 14 and 30 days can be set.
This setting ensures that changes to the website are automatically transferred to the knowledgebase and that the agents always take the latest version of the website into account in their responses.
To set the interval, click on the button with the three dots to the right of the source. Clicking on the Edit plan button opens the input mask, which is used to set the update interval.
Resource management – Connect resources and agents
The agent and source are linked by selecting the desired agent via the drop-down menu in the top right-hand corner and activating the resource for the selected agent. Activation takes place via the toggle in the Used? column.
If a resource is no longer up-to-date, it must be replaced or deactivated in order to prevent outdated information from being displayed. The first step is to select the agent via the drop-down menu. It is then deactivated using the toggle in the Used? column.
If the resource is to be removed completely, it must be deleted as described above.
A resource does not necessarily have to be deleted. Removing the link to the agent is sufficient for the agent to no longer access the resource.
If the resource becomes relevant again elsewhere, it is sufficient to reactivate the link.
Description of functions – Retrieval Augmented Generation
The section is opened by clicking the RAG button. 
The setting options available here can be used to influence the generative AI and thus the responses of the agents.
- Information retreival: Enables relevant resources to be added. The specific description can be found under 1. resource management - adding resources.
- Knowledge check: As part of the knowledge check, the content of the resources is checked to generate answers. The AI agent only responds to the user's query if it contains sufficient facts to generate a meaningful answer. If the knowledge check fails, i.e. if there is not enough information, a “not understood” message is displayed in the chat. The knowledge check is a protection against hallucination and incompletely correct answers from the Generative AI. The setting is (de)activated by ticking the corresponding box in the moinAI Knowledge Base in the RAG → Knowledge check area. The setting applies immediately to the preview after saving. Publishing is necessary for the setting to also apply to the live environment.
If the knowledge check is activated, the automation rate may decrease. In specific terms, this means that the rate of requests that are not understood may increase selectively because borderline cases do not receive a response.
- Instructions: Instructions instruct the agent to include an informative addition such as “Information is provided without guarantee” or to follow other specific, content-related instructions. These are specific, content-related instructions and not instructions on the tone of voice/general communication guide lines.
The instructions are inserted in the text field. After saving, the instructions are active in the preview, but not in the live environment. In order for the instructions to also apply to the live chatbot, it is necessary to publish the adjustments (Cloud-Button besides the button RAG). - Answer generation: There are various large language models (LLMs) to choose from. These models form the technical basis for text generation and each have different capabilities. Selecting a specific LLM therefore serves to ensure the best possible use case-related functionality of the AI agents.
Customer Success Management provides advice and information on the different models. The selection of a specific model is made by moinAI. The availability of the models is licence-dependent.
- Data extraction: Data extraction makes it possible to save information. This stored information can then be used in subsequent actions. The data is, for example, e-mail addresses or customer numbers. Other data is conceivable depending on the use case. Extracting the data has a positive effect on the user experience. As soon as the setting option for data extraction is available in the moinAI Hub, we will provide information about the specific setting here and in the Help Center.
Missing Knowledge
If the AI cannot answer a question, it is either because the query was not understood or because there is no resource available in the knowledge base to answer it. In both cases, the element Not understood is executed in the conversation.
In the moinAI Hub, these dialogues can be viewed via the Knowledge Base menu item using the sidebar icon in the top right-hand corner. The Missing knowledge section opens.
This lists all queries where the chatbot thought there was information in the knowledge base.
Clicking on the speech bubbles on the right opens the entire chat history. These are indicators of missing topics that should be added to the resources and included in the knowledge base.
