Notes
Short writing on building software.
Practical notes from real engagements: what worked, what didn’t, and what I’d do differently.
-
You probably don’t need a rewrite
A practical test for deciding between rewriting a legacy system and evolving it in place.
-
Write your evals before your prompts
Why an evaluation set is the most valuable artefact in any LLM project, and how to start one in an afternoon.
-
Architecture decision records people actually read
A lightweight ADR format that survives contact with a busy team.