Make internal information accessible with AI, relevant sources and appropriate access permissions.
Discuss your challengeYour team regularly searches procedures, manuals or other internal documents. An AI knowledge assistant or RAG system is relevant when answers need to come from your own sources and users need to see what an answer is based on.
A selection of sources, example questions and access rules for a first use case. I define how citations, updates and responses to missing information should work.
Give employees one entry point to the information they are allowed to use.
Explore this serviceMake company knowledge searchable with answers that lead back to the source.
Explore this serviceAsk questions about your documents and find the passages behind each answer.
Explore this serviceBuild a RAG system that adds relevant business information to AI answers.
Explore this serviceDesign an AI environment around your requirements for data access, storage and processing.
Explore this serviceExplore these selected explanations alongside the service guides. Each video links back to its source article, transcript and relevant project tools.
1:50Examine a fictional answer about business documents and learn to check passages, conditions, missing information and conflicting versions separately.
Source articleChat with business documents
1:51Use a fictional procedure question to trace a RAG failure to missing sources, missed passages, incorrect use of context or access controls before answering.
Source articleRAG system development
1:52Follow a fictional work instruction through its lifecycle and see how source owners, versions, access permissions and deletion keep an AI knowledge base manageable.
Source articleAI knowledge baseChoose documents and user groups, define the authoritative version and identify who maintains the content.
Test whether the right passage is retrieved, used correctly and clearly cited; include questions without an answer.
Agree how changed sources and permissions are processed and how incorrect answers are reported and investigated.
At Eleads, Ricardo combined RAG, embeddings and vector search for semantic matching of enquiries. The case describes retrieval applied to lead information in an operational workflow.
Project experience of Ricardo van der Spoel through Van der Spoel Development.
Choose one task from the services above. Describe the current process, the available information and the person who can approve the result. Then compare the requirements and acceptance checks on the relevant service page. The original documentation below helps you investigate the technical choices.
Create your project briefTechnical basis for the components of RAG.
Example of incremental updates in Microsoft Graph.
Platform example of user-scoped search filtering.
Controls for upload, storage and file processing.
