Long-form architectural write-ups on Snowflake, PySpark, Model Context Protocol (MCP) servers, data for AI agents, and the physics of pour-over coffee.
What I learned building fiduciary-agent, a personal open-source finance harness that runs on-device: keep arithmetic out of the LLM, ground every answer, guard against injection, and choose boring storage.
What a data engineer actually does to take AI agents from proof of concept to production: reusable MCP servers, data contracts, resilient writers and observability.
How a data engineering team built NatWest's 50+ source ESG and climate platform on Snowflake, Airflow and dbt, with contracts and data quality built in, third-party enrichment, and emissions products published to a data marketplace.
How a senior data engineer approaches the morning cup: particle size distribution, bypass ratios, why water matters, and mastering the V60 4:6 technique.
My personal map of London: strictly London-based roasteries, stamping the Beer Passport along Bermondsey's railway arches, hunting down blistered sourdough loaves, and West London Thames trails.