Issei Kuzuki

Data engineer by trade. I design and build LLM-based systems, and I'm always looking for better ways to work with AI, for myself and the people around me.

Projects

All projects →

Writing

16 Sept 2026 The bottleneck moved to verification Writing code is a fifth of the job, and it's the fifth AI just optimised. The constraint moves to the other end, telling whether what you got is right, and that end scales worst exactly as you produce more.
19 Aug 2026 Directing a game I couldn't have written I don't write frontend. Tube Race is a live, polished React game. What I actually did was decide what "correct" meant and check whether it held, which turns out to be most of the job.
9 Jul 2026 The agent wants one big table LLM agents reason badly about joins. The industry denormalised for the engine for a decade; now it's denormalising for the model. Why one big table is winning again, and where ClickHouse fits.
1 Jul 2026 A year of AI coding at team scale I used to think editor integration was the load-bearing affordance of AI coding tools. A year of trying to make a team operate consistently changed my mind.
27 May 2026 Evals, after putting them off I'd read the posts, nodded at the rubrics, never quite got round to building one. Last week I did, and the things it surfaced weren't the things I expected to surface.
20 May 2026 I deleted my embedding pipeline I built a hybrid FTS5 plus LanceDB MCP server with an Ollama embedding pipeline for my personal knowledge vault. After two months I deleted all of it. This is the long version.

All writing →