Preskočiť na obsah

AI · 22/04/2026 · 7 min read

RAG in practice: how we turned company documents into an AI assistant

Every company has the same problem: twenty years of documents, contracts and manuals nobody can find anything in. RAG — retrieval augmented generation — turns them into an assistant that answers in plain language. If it is built right.

How it works and what it costs

Documents are split into chunks, converted to vectors and stored in a database. A user's question retrieves the relevant passages and an LLM composes an answer with links to the source. Realistic budget: a pilot over one document domain €15,000–25,000; operating costs at hundreds of queries a day, €200–600 a month in inference.

Three mistakes that bury the project

First: dumping everything in, including obsolete policy versions — the assistant then confidently quotes a document from 2019. Second: no evaluation — without a test set of questions you do not know whether it answers correctly 60 % or 95 % of the time. Third: missing permissions — the assistant must not reveal the CEO's contract to the payroll clerk.

A well-built RAG saves dozens of search hours a month and always backs answers with sources. A badly built one is an expensive generator of confident nonsense. The difference is not the model — it is the data and the measurement.

Facing exactly this? Let's talk numbers.

An audit of your current solution within 48 hours — specific figures, no phrases.

← All articles