How we built the MCP server behind our AI Assistant for our blog writing process: an ingestion pipeline, pgvector search, FastMCP tools and resources, and
Explore how we build the data foundations that make AI and machine learning possible. Data engineering is about collecting, cleaning, and organizing raw information so it's reliable and ready for analysis. In this category, you'll find posts on pipelines, storage strategies, and best practices for making data usable at scale. Most come out of client projects where the data turned out to be messier than the model, so they stay practical: what breaks after a pipeline has run daily for a year, and how to tell a data problem from a model problem.
