Connect sources
SharePoint, file servers, DMS, wikis, specialist systems – with their permissions.
Knowledge management with AI: Find company knowledge, with sources instead of guesswork.
Documents, policies, project knowledge and specialist information become searchable – with roles, source references and traceable access.
In short: A knowledge system connects approved internal sources. RAG means answers from your own documents, with the source. Permissions from the source systems still apply. Unsupported answers must be detected and limited.
Starting point
Where time is lost today.
- Scattered knowledgeFolders, SharePoint, PDFs and people – every answer is somewhere else.
- Hunting for versionsYour staff spend a long time looking for the right, current version.
- The same questionsNew staff ask questions that have been answered many times before.
- Knowledge leavesWhen people leave, whatever was only in their heads disappears.
- Permissions forgottenSearch tools show what the user shouldn’t actually see.
How it works
What the solution does, step by step.
Prepare content
Split and structure content, then add metadata and freshness indicators.
Adopt permissions
If you may not see a document, you get no answer from it either.
Index
Make content searchable both semantically and exactly.
Search and answer
A question in natural language, an answer from the passages found.
Show the source
Answers should refer to the document used; missing results should be clearly marked.
Before – after
What changes in day-to-day work.
Examples from the workflow – no percentages, as only a measurement in your business can provide those.
| Situation | Today | With the solution |
|---|---|---|
| New staff | ask colleagues, search the shared drive | ask the knowledge system, get an answer with a source |
| Policies | “Where was that written again?” | answer with a linked document |
| Version | three files, one is valid | current version identified, outdated ones flagged |
| Access | all or nothing | permissions from the source system |
Benefit
What this use case improves.
Less time searching
Answers instead of folder paths.
Knowledge available
Even when the person who knew it isn’t there.
Source reference
Answers should be verifiable against the sources cited.
Controlled access
Permissions are adopted or mapped explicitly.
In action
What working with it looks like.
Sample images from our visual library – the interfaces shown are illustrations, not client data.
Responsibility
What stays with people.
Maintaining the sources, assessing the answer and any action that follows from it. The system finds and provides evidence; it does not decide.
The solution prepares, sorts and hands over – your staff make decisions and grant approvals, following rules you set.
Systems & integrations
Where the solution connects.
For example – what exactly gets connected depends on interfaces and permissions and is checked in the AI potential assessment.
- SharePoint
- File servers
- DMS
- Google Drive
- Microsoft 365
- Wikis
- Project databases
Building blocks & products
The technology behind it.
Solution building blocks are the technical components the solution is built from. Products are only named where they fit the task.
RAG / knowledge systems
The solution building block for search with sources and permissions.
View building blockDocument AI
Prepare and structure documents.
View building blockAI agents
Use knowledge from within agents.
View building blockKnowledge Assistant
Search internal documents by asking a question; every answer with a source.
View product
Control, data & operation
Control stays part of the system.
Depending on the product and interfaces, we run the solution on your premises, in a Swiss cloud or as a combination. Before the pilot, we clarify data flows, access rights and compliance requirements. Background: Private AI and On-premise & hybrid (running on your own servers or a mix of both).
| Topic | Implementation |
|---|---|
| Data | Internal documents – internal to confidential, depending on the source. |
| Approvals | Information only, no actions; actions run through agents with their own approval. |
| Roles & permissions | Permissions are adopted from the source systems or mapped explicitly in the knowledge layer. |
| Logging | Queries, sources used and answers are traceable; gaps and outdated documents are visible. |
| Operating model | Running on your own servers or in a private cloud is possible; the operating model depends on the data sources and security requirements. |
Industries
Where this use case is typical.
- Accounting & fiduciary
- Manufacturing
- Healthcare
- Real estate
- cross-industrythe workflow is not tied to a single industry
Standard approach
How a trial run (pilot) can start.
The pilot does not cover the whole process straight away. We pick a clearly defined part, set approvals and success criteria and test it with real data and the people who work with it. This approach is the same for every use case.
- Choose a processA clearly defined part of the workflow that takes up time today and can be measured.
- Clarify data and systemsWhich data, which interfaces, which permissions – and what is missing.
- Implement a defined workflowWith defined approvals and success criteria, not the whole process at once.
- Measure in real operationWith real data and the people who work with it; then expand or stop.
Related use cases
Related pages.
Frequently asked questions
Frequently asked questions: company knowledge
Does the system make up answers?
The aim is to base answers on approved sources. Uncertainty and missing evidence must be made visible.
Who sees which documents?
Permissions must be adopted from the source systems or mapped explicitly in the knowledge layer.
Do documents have to go to the cloud?
Not necessarily. The right operating model depends on data sources, architecture and security requirements.
Which companies is this use case suitable for?
Companies whose knowledge is documented but hard to find – with several storage locations, clear permissions and recurring questions about the same documents.
Next step
Check this task for your business.
Describe your current workflow in two sentences. We check the benefit, data situation, integration effort and risks and show whether a product, a solution building block or a custom solution makes sense.