My first Spec-Driven Development project

Tue, 24 Feb 2026 15:50:31 +0000

“Look ma, no hands” - I wrote FrozenDB without writing lines of code. Instead, I used spec-driven development to generate all of the user stories, map them carefully to technical requirements and have AI generate the code. I’ll go into SDD more deeply later, but for this post I wanted to share some of the learnings I had over the 40 specs I wrote as part of the process.

Start small

My first few specs took a lot of development cycles. I spent a lot of time in the /speckit.plan stage refining the research and approach I wanted to take. Then, when I let the AI implement the specs, it went off and did something I didn’t want it to do. So I would have to go back to an earlier step (usually the spec.md), refine the requirements, and update every other document. This takes a lot of time and context switching. I realized my user stories were too big. For example, my first spec covered creating the database file, defining a header, and making it append-only. This took a very long time to get right, and involved a lot of tuning of every step of the spec.

Introducing FrozenDB

Thu, 19 Feb 2026 17:56:30 +0000

To make apple pie from scratch, you must first invent a database to store your recipes. - Carl Sagan

Well Carl (and avid readers), let me introduce you to FrozenDB. This is my twist on a single-file database, with the requirement that it operates on append-only files. FrozenDB is not something for production, but a learning exercise. This companion post expands on some of the things I learned about append-only structures, and database mechanics.

Frozendb on sugar, spice, &terminal? nice

My first Spec-Driven Development project

Start small

Introducing FrozenDB