Architectural guide
Data platform architectures: what changes when AI needs your data?
Understand warehouses, lakes, lakehouses, mesh and fabric through one business example, and learn what makes a data platform ready for AI.
Maciej Kępa
Data & AI Architect
I design data platforms and AI systems for production. I write about delivery, observability and the decisions that keep those systems maintainable.
Long-form notes for engineers who have to ship
Architecture essays, delivery guides and operational lessons from the part of AI work that starts after the first promising notebook.
Architectural guide
What is an Ontology? Connecting business meaning with AI agents
Learn when an ontology helps AI connect business concepts across systems, how it complements semantic models, and where its limits remain.
Architectural guide
Semantic layers: giving AI agents business context
Learn how semantic layers give AI agents clear metrics and business context, and when a focused dashboard is a better fit than a conversational interface.
Explore the code behind the ideas
GTD MCP Server
Runnable tutorialAn MCP server that gives an agent structured tools for tasks, projects and inbox capture.
Setup, decisions and limitationsAI/ML in Practice
Workshop materialsNine learning modules connect data preparation and feature engineering to training, pipelines, MLOps and generative AI.
Setup, decisions and limitationsChoose a production AI reading path
13 posts
Production MLOps
From model packaging to deployment, ownership and operational readiness.
Explore MLOps 9 postsAI-ready data platforms
Business definitions, data history and ownership behind reliable AI inputs.
Explore data platforms 3 postsML Observability
Monitoring signals, feedback loops and operational baselines.
Explore observabilitySelected talks
Conference sessions on production AI, MLOps, observability and data platform architecture.
SQL Server and the Vector Revolution - how LLMs see your data
Embeddings, vector search and the bridge between traditional data platforms and modern AI.
Trenuj, wdrażaj, nadzoruj: techniczny przewodnik po AI w Databricks
A full-day workshop following data preparation, model training, pipelines and model operations in Databricks, with hands-on exercises.
Architecture, delivery and AI systems that have to hold up in production
I am a Data & AI Architect working on production data platforms, MLOps and cloud-native AI systems. My work focuses on the engineering decisions that make these systems operable, observable and maintainable.