Selected work / Magnum

Olzhas — Magnum Knowledge Base

An AI assistant that takes the same fifty questions off managers and colleagues every day and gives new employees a faster way to find their footing.

Olzhas Telegram bot greeting an employee on /start

Client

Magnum

Audience

Internal employees

AI layer

RAG over internal docs

Magnum

Conversational assistant, RAG pipeline over internal knowledge, admin panel for the operations team, onboarding flows.

The work

Employees ask questions in natural language. The assistant searches the internal knowledge base, finds the relevant material, and answers using the company's own content.

What mattered

The knowledge already existed — it just was not usable in the moment someone needed it. The product had to make the existing library accessible, not replace it.

What shipped

A chat assistant, a RAG pipeline over Magnum content, and an admin panel that lets the operations team upload and update materials without involving engineers.

Case study

Olzhas

A large company always has more knowledge than it can serve. Magnum has internal regulations, onboarding and day-to-day work instructions, materials for every role — and a constant stream of people who ask their manager, a colleague, or whoever is nearby instead of opening the document. Olzhas is the layer that sits between the employee and the existing knowledge base. The employee asks a question. The assistant finds the right piece of content and answers from it.

Problem

Employees always asked.

The knowledge base existed and was kept up to date. It was just hard to use in the moment: too many documents, no quick way to land on the right paragraph, no time to read everything when you have a shift starting. So employees did the natural thing — they asked a manager, asked a colleague, asked the person next to them. The team ended up answering the same questions week after week, and onboarding always took longer than it should.

Solution

A single chat over everything the company has already written down.

Olzhas is a RAG assistant on top of Magnum's internal knowledge. The team uploads materials in the admin panel. The system indexes them. Employees ask questions and get answers grounded in the company's own content. The goal was not to be clever. The goal was to take the most-repeated questions off managers and colleagues and give new employees an answer in the moment, not in a meeting two days later.

Technical work

RAG built around the way the company actually keeps content.

The model is the boring part. The interesting part is how the source material is structured, indexed and refreshed when the team drops in a new policy. We built a RAG pipeline that ingests internal documents, splits them in a way that matches how Magnum writes them, and keeps the index in sync with the admin panel. The chat layer is multilingual, because the company runs in more than one language.

Related work

Sitting on a knowledge base that nobody opens?

We help companies put a chat layer over the content they already have — a RAG pipeline tuned to your documents and an admin panel your operations team can actually run.

Brief (optional)