01 · Foundations
Metrics people can agree on
Model shared definitions and trusted data products that work across reporting, teams, and tools.
dbt · Snowflake · data qualityAbout · Analytics engineering · B2B SaaS
I’m Piotr, an analytics engineer building dependable data foundations and exploring AI agents grounded in semantic layers—with context, accuracy, evaluation, and cost treated as first-class design concerns.
How I think about the work
Good analytics starts before the dashboard. It starts with shared definitions, well-modelled data, checks that catch meaningful failures, and a clear path from a question to a trusted answer.
That foundation is also what makes AI useful in analytics. I’m especially interested in agents that work from governed semantic layers, carry the right context, ask when a question is ambiguous, and can be evaluated against known expectations.
My writing and open-source projects explore these ideas with synthetic examples and reusable engineering patterns.
An agent can’t repair an unclear metric definition by sounding confident.
Prefer checks that protect business meaning, not just pipeline mechanics.
Keep context, tools, evaluation, and operating cost visible to the team.
What I work on
Practical work across analytics engineering and governed AI.
01 · Foundations
Model shared definitions and trusted data products that work across reporting, teams, and tools.
dbt · Snowflake · data quality02 · Applications
Explore agent patterns that use governed metrics and explicit context rather than inventing answers.
Semantic layers · context · tools03 · Reliability
Use evaluation, deterministic checks, and cost awareness to understand whether an agent is helping.
Accuracy · judges · costTools and topics
Say hello
I’m always glad to compare notes on analytics engineering, semantic layers, or building more dependable AI agents.