At Prijedorčanka, where daily operations involve a large number of documents, procedures and technical instructions, artificial intelligence has found its place in one of the most important resources of any business system — knowledge. Through the AI FORWARD project, the company was provided with an AI solution based on RAG (Retrieval-Augmented Generation) technology, called “Prijedorčanka AI – Mozak” (“Brain”). It enables employees to find information from internal documentation more quickly and reliably. Founded in 1972, Prijedorčanka specialises in fruit processing and the production of fruit distillates and concentrates. The company combines its traditional expertise with new technologies and working methods. Before joining AI FORWARD, employees had already received internal training on artificial intelligence, and some repetitive processes had been automated. The project was therefore a natural next step: an opportunity to develop a practical solution tailored to the company, in cooperation with a team of experts, and to introduce AI in a structured manner, with clear rules in place. “We envisioned Mozak as the company’s central knowledge base, rather than just another search tool. Quality management system documentation, procedures and technical instructions are now consolidated in one system. Every piece of information can be traced back to its original document. This means that the knowledge we have built over decades becomes an institutional asset rather than something that depends on individual employees,” representatives of the Prijedorčanka team explain.
From a large volume of documents to accessible knowledge
Before the solution was implemented, employees had to know which document contained the information they needed and search through it manually, or ask a colleague who “knew where to find things”. This was particularly evident in equipment maintenance, as each machine has its own documentation. This way of working was time-consuming and relied on individual experience, while new employees needed more time to familiarise themselves with the documentation. This challenge was identified as an area where AI could deliver tangible value. Through AI FORWARD, and in cooperation with IT specialists, a solution was developed that allows employees to search quality management system documentation by asking questions in natural language, instead of manually reviewing large numbers of documents.
Practical example
The Prijedorčanka AI – Mozak system serves as an internal knowledge base where employees can ask questions in their own words and receive answers based on the company’s internal documentation. For example, when checking the maintenance procedure for a specific machine, an employee can ask the system a question and receive an answer that references the exact document, section, and page. The system operates locally, without an internet connection, ensuring that company data remains within the company’s premises. The solution is still in the pilot phase, but initial feedback indicates that employees can retrieve information from internal documentation within seconds, instead of manually searching through multiple documents or relying on colleagues. Although actual time savings have not yet been measured, the company has already observed improvements in the speed and reliability of information retrieval.
AI as a support tool for employees
Based on a user’s question, the system retrieves relevant information from internal documentation and displays it together with the exact source — the document, section and page — allowing every answer to be verified. If the documentation does not contain a reliable answer, the system clearly states this rather than guessing. The solution operates entirely locally, without an internet connection, ensuring that company data remains within the company’s premises. A Procedure for Managing AI Systems and Risks, together with supporting forms, was also introduced as part of the implementation. The particular value of the solution lies in the fact that AI does not replace employees’ existing knowledge and expertise, but makes them more accessible and easier to use. Instead of spending time repeatedly searching through documents, employees can devote more attention to tasks that require their experience, judgement and decision-making skills. “The biggest change is speed and security. Instead of searching through documents, I get an answer with the source in a few seconds. We are still in the pilot phase and we are yet to measure the real time savings, but we can already see how much easier it is to get information. The second change is in how we think: we realized that AI can be reliable if it is set up in the right way.” Bogdana Bilbija, Marketing and HR Manager and AI Coordinator for the AI FORWARD project.
Practical implementation driven by a real need
Prijedorčanka is one of ten companies selected to implement AI solutions in practice through the AI FORWARD project. The process began with an analysis of business processes and an assessment of where artificial intelligence could deliver the greatest value. This was followed by the development, customisation and testing of the solution in line with the company’s needs, alongside employee training and technical support during its introduction. The solution is currently in the pilot phase, during which its use in day-to-day operations is being monitored. This approach demonstrates one of the key values of the AI FORWARD project: AI is not introduced as a technology for its own sake, but as a response to a specific business problem. In Prijedorčanka’s case, the focus has been on making better use of existing knowledge and reducing the time needed to find information, while maintaining full control over company data.
From traditional operations to AI-powered support
Prijedorčanka’s experience demonstrates that the application of artificial intelligence is not reserved for technology companies. On the contrary, companies with a long tradition in traditional industries can also identify specific business processes in which AI can deliver additional value. The implementation has also demonstrated how cooperation between an SME and local IT specialists can result in a solution tailored to the company’s actual needs. “For us, Mozak is a foundation, not the end goal. During the pilot phase, the system covers quality management system documentation and equipment maintenance. In the long term, we see it evolving into a central knowledge base that we will gradually connect with fruit procurement, other purchasing activities, production and sales. We are moving forward in a structured way, according to our priorities and with clear rules in place,” representatives of Prijedorčanka conclude.
AI FORWARD: From Knowledge to Practical Application
The experience of the company Prijedorčanka is part of the broader results of the AI FORWARD program, implemented by the Innovation Centre Banja Luka (ICBL) in partnership with Bloomteq/Ilirya Tech Group. The program supports small and medium-sized enterprises in Bosnia and Herzegovina in developing the knowledge and capacity needed to apply artificial intelligence in their operations—moving from awareness-raising and training to concrete solutions based on artificial intelligence and digital transformation.
This initiative is part of the EU Initiative for Private Sector Development in Bosnia and Herzegovina, co-financed by the European Union and the Government of the Federal Republic of Germany under the broader “Sustainable Economic Development and Promotion of Employment in Bosnia and Herzegovina” (SEDEP) program, implemented by GIZ.