AI-Powered Wiki

What is a knowledge source?

A knowledge source is a single valuable knowledge entry in the AI Wiki.

It can be established in different ways:

• as a manually created article
• as content from an externally connected source, for example, through a website connector
• as a file uploaded via the Files connector

Manually created articles are suitable for content that is deliberately formulated and technically verified. This includes work instructions, frequent questions, process descriptions, internal guidelines, or binding formulations.

Externally connected sources are suitable when existing content should be used regularly. Examples could be help centers, documentation pages, or public information sites.

Files are suitable for existing documents that should be centrally provided and made usable for AI-supported functions, for example, PDF documents, work instructions, or technical documents.

Why structure is important

Knowledge in the AI Wiki is not only stored but also technically classified. This is where groups and classifications come into play.

Groups form the thematic structure. They help to make content findable and bundle technically related information.

Classifications describe the type of content. This distinction is important because different contents are used differently:

• An FAQ answers a specific recurring question.
• A work instruction describes an operational process.
• A document contains background information or binding regulations.
• News inform about current changes and appear on the homepage.

If these types of content are properly separated, the knowledge base remains easier to check. At the same time, AI functions can better classify the content.

Website Connector

The Website Connector connects an external website to the AI Wiki.

Path in Enneo: Work tools → AI Wiki → Sources

During crawling, Enneo reads the connected website and adopts suitable content as knowledge entries. These then appear in the knowledge structure.

A connector is controlled via several settings:

• Source URL
• Include paths
• Exclude paths
• maximum number of pages
• frequency for re-crawling

The source URL defines which website is connected.

Include paths determine which areas of the website should be considered. Exclude paths exclude areas that are not relevant. These could include login pages, privacy policy pages, imprint, blog areas, or technical overview pages.

Examples:

• /help/* takes into account content in the help area.
• /faq/* considers FAQ pages.
• /login/*, /datenschutz or /imprint can be excluded.

The maximum number of pages limits the scope of the adopted content. The crawling frequency determines how regularly Enneo re-reads the source.

The connector technically provides content. However, it doesn't evaluate whether this content is technically suitable. This verification remains part of the editorial responsibility.

Crawling and Updates

During crawling, content from the external source is read out and made available in Enneo. The connector shows a status during this process, for example, running, completed, or faulty.

Re-crawling updates the adopted content based on the current connector configuration. Thus, changes on the external website can be adopted in Enneo.

If include or exclude paths, the source URL, or other connector settings are changed, the source should be re-crawled or processed again for the changes to take effect.

At the same time, the quality of the result depends on the external source. If URL structures, navigation, or content of the website change, the knowledge structure in Enneo can also change.

For stable results, connectors should be configured as precisely as possible. A narrowly defined source is easier to check and usually delivers better results than a very broadly connected website.

Files as a knowledge source

In addition to manually maintained articles and connected websites, files can also serve as knowledge sources in the AI Wiki.

Path in enneo: Work tools → AI Wiki → Sources

The Files Connector is used to centrally provide technically relevant documents and make them usable for AI-supported functions. Uploaded files are processed, turned into knowledge entries, and can subsequently be taken into account in proposed answers, chat contexts, or AI agents, provided they have been approved for this purpose.

Files can be uploaded via drag-and-drop, structured into folders, managed, and previewed if necessary. A clear folder structure helps to maintain larger knowledge bases in an understandable way and to review them specifically later.

Files should not be used as an unchecked storage. It is key that content, filename, and storage location are technically unambiguous.

If a file's content changes, the knowledge source must be processed again for the updated content to become effective in the system. Re-indexing ensures that not only the file itself, but also the search and AI contexts derived from it, are up to date.

Like with Website Connectors: The Connector technically provides content. The technical responsibility for accuracy, currentness, release, and structure remains with the responsible users.

Managing, editing and reprocessing files

In the Files Connector, files and folders can be managed. Depending on their permissions, users can upload files, move them, preview, replace, edit, or archive them.

The following actions are available for files:

• Upload file
• Open file in preview
• Replace file
• Edit file, if the format supports it
• Re-index file
• Reset file to the original status
• Archive or restore a file

If a file was edited directly in Enneo, a corresponding marking might be visible. This marking helps to recognize that the currently used content may no longer exactly correspond to the originally uploaded document.

Update

With Update, a file is reprocessed. This action is useful when content for knowledge search or AI-supported functions should be updated.

The file is then reprocessed for search and AI contexts. This is relevant, for example, if a file has been replaced or if the processing is specifically to be restarted.

Reset to Original

With Reset to Original, a manually edited file is reset to the originally uploaded state.

This action is useful if manual changes should be discarded or if the original content of the file should be used as the basis again.

Files and Media in ArticlesArticles can be supplemented with uploaded media, such as images or videos.

Media is useful when it makes a technical statement more understandable, such as form examples, process representations, or screenshots of specific states.

It's important to note that media should complement the text, not replace it.

For AI-supported functions, the textual content remains particularly relevant. Text can be clearly searched, processed, and incorporated into response contexts. Critical information should therefore always be included in the article text and not solely contained in a screenshot or video.

Visibility for AI features

The setting "Make the Knowledge Source Publicly Accessible" controls whether a knowledge source can be used for AI-supported functions.

If a knowledge source is released, it can be used, for example, in response suggestions, chat contexts, or AI agents.

If it is not released, it primarily remains part of the internal documentation in the AI Wiki.

This setting is technically relevant. A released knowledge source can influence the results of AI functions. Therefore, only content that has been reviewed, is current, and is clearly formulated should be released.

Contents that are confidential, outdated, incomplete, or technically ambiguous should not be released.

Utilization in the ticket context

Knowledge sources can be utilized in the ticket context if they are authorized for AI functions and are technically relevant.

Enneo can draw upon suitable content from the AI Wiki to support response suggestions, chat responses, or AI agents. Additionally, relevant knowledge content can become visible in the working context of a ticket, helping users quickly find relevant information.

Whether a knowledge source is actually considered depends on factors such as content, release, currentness, and technical relevance, among others.

Impact on AI agents

AI agents can use knowledge sources as context if they are accessible and technically relevant.

The quality of the agent results heavily depends on the quality of the knowledge base. Unclear formulations, contradictory articles, or unchecked connector content can lead to inaccurate results.

The AI Wiki is therefore more than just a storage facility for information. It controls which knowledge is available to AI and how this knowledge is technically classified.

A well-maintained AI Wiki improves the traceability and stability of AI-supported processing. A fuzzy knowledge base, on the other hand, can lead to inconsistent responses and misinterpretations.

Maintenance and Responsibility

A good knowledge base is not necessarily large, but reliable.

Manual articles should specifically verify the following points:

• Is the content technically correct?
• Is the article clearly formulated?
• Is the classification appropriate?
• Is the group sensibly chosen?
• May the content be used for AI functions?

For Connectors, the following additional questions should be asked:

• Is the external source technically reliable?
• Are Include and Exclude paths sensibly set?
• Is the maximum page count appropriately selected?
• Is the crawling frequency proper?
• Is there a need to crawl or index again after a change?

For files, the following additional points should be considered:

• Is the filename unique?
• Is the file stored in the appropriate folder?
• Is the content current and technically verified?
• Was the file reprocessed after changes?
• Is it clear whether the file is used in its original condition or in a manually edited version?

Changes to the AI Wiki not only affect documentation. They can also influence the quality of suggestions for responses, chat contexts, and AI agents.

Therefore, articles, connectors, files, and visibility settings should be maintained as technical system components.