The "Boryviter" Center for Advanced Experience has initiated testing of the "ODCR Assistant" neural network, designed to automate the process of passive information gathering and analysis from enemy open sources. This was reported by "Militarnyi".

The module works with unclassified data streams, particularly from Russian military social media and technical blogs. The system processes about a thousand messages daily, sorting them using lexical markers — "green" and "red". If a message contains "green" keywords and lacks "red" terms, it proceeds to further observation formation.

The next phase will involve checking the novelty of the data as well as its systematization. Meanwhile, developers note that full automation of analysis is currently unattainable; human involvement remains essential.

In addition to the "ODCR Assistant," the team is working on a language model for Ukrainian military personnel, which will operate based on neural networks and feature an interface similar to ChatGPT. The goal is to facilitate dialogue with experienced individuals and simplify situation analysis.

The development is carried out by the "Boryviter" team using powerful servers. The organization is open to collaboration but emphasizes the importance of non-commercial support focused solely on the Ukrainian army.