Designing Real World Ai Agents Workshop
Hands-on workshop: Build a multi-agent AI system from scratch — Deep Research Agent + Writing Workflow served as MCP servers. Includes code, slides, and video
i
iusztinpaul
Professional software vendor delivering innovative solutions on the Softono platform. Specialized in both open-source and proprietary software development.
Total Products
2
Software by iusztinpaul
Energy Forecasting
energy-forecasting is a comprehensive 7-step MLOps framework designed to teach machine learning engineering and operations through the practical design, building, and deployment of an end-to-end ML batch system. The repository provides a free course that guides users in creating a production-ready system for forecasting hourly energy consumption in Denmark. It covers the entire lifecycle including feature engineering, model training with hyperparameter tuning, and batch prediction. The curriculum emphasizes scalable architecture using tools such as Hopsworks for feature storage, Weights & Biases for experiment tracking and model registry, Great Expectations for data validation, Docker for containerization, and Apache Airflow for orchestration. It also includes building Python packages with Poetry, deploying to Google Cloud Platform, and monitoring model performance over time. The package integrates CI/CD pipelines via GitHub Actions and demonstrates how to serve predictions through web applications using Fast