RAG, explained: why the band still needs sheet music
Retrieval-augmented generation in one image: the model brings the technique, your data brings the sheet music, and a good system says so when the music is missing.
Case studies and notes
Work & writing
A few of our amazing clients
Microsoft Fabric F2 pricing: what a small team actually pays
What an F2 capacity costs in euros, why a one-year reservation is usually the wrong lever, and the Power BI licensing cliff at F64 that quietly lands on your invoice.
The EU AI Act deadlines moved. Here is what your company still has to do in 2026
The Digital Omnibus pushed high-risk AI Act obligations back to December 2027, but transparency labelling, AI literacy, prohibited uses and GPAI rules did not move. A plain-language calendar and a five-item to-do list.
Rebuilding dataaigency.com in the open
Why this site is a public repo, and how the rebuild works.
Does a small business need a data warehouse (or a lakehouse)?
An honest decision guide: the three signals that say yes, what these things actually are, what they cost, and when a spreadsheet is genuinely enough.
Can data tell you when to surf?
A surf forecast is a tiny data platform, so here is the whole idea explained through one question: when do I paddle out?
What a 30 minute first look at your data stack actually finds
A plain account of how I spend the free 30 minute review and the problems that keep turning up in it.
Medallion architecture: the five mistakes I keep unpicking
Bronze, silver and gold are easy to draw and easy to get wrong, so here are the five failure patterns I see most and how to avoid them.