Projects
Each project starts with a concrete problem. These are the systems we have built and deployed for our clients.
Extensible AI hub for the construction sector. The active module estimates work item costs using LSTM + CatBoost models trained on real historical budget data.
Predictions with confidence intervals over Excel work item files. Available as both web and desktop app (Electron).
Modular AI hub organised by departments (Studies, Procurement, Production). Designed to grow: adding a new feature means editing a configuration registry.
IP-restricted web application deployed in production. Desktop app (Electron) with silent auto-update.
Automated weekly pipeline that detects, analyses, and scores private construction opportunities before they go to public tender. Uses multi-agent AI (Gemini) to evaluate each market signal, integrated with Area Hub.
Weekly opportunity newsletter with 0–100 score, certainty level, and inline commercial feedback.
Machine learning model that estimates construction work item costs from Argenia's real historical budget data, combining LSTM, CatBoost, and XGBoost.
Completed and in the feedback stage with the Argenia team: estimates already replace manual calculation as the first price reference.
Chatbot that answers questions from Area Construcción's own documentation, manuals and knowledge base. Private, no data in the cloud.
Over 12,000 documents indexed with response times under 1 second.