Evaluating bank-core v2-openspec-claude

Wed, 27 May 2026 00:00:00 +1000

GitHub

https://github.com/prule/bank-example/tree/v2-openspec-claude

Previous episode

Introduction

Following on from the v1-basic version of my bank-example, I decided to take the generated code and use it as a basis for a new version, v2-claude. This time, I wanted to see how well I could use AI, specifically Anthropic’s Claude, to help me build out a more complete application, using a specification-driven approach with OpenSpec. This blog post documents my journey, the successes, the bumps in the road, and my overall impressions.

Evaluating bank-core v1-basic: Locking, Concurrency, and the Limits of Web-Prompted AI

Sun, 24 May 2026 00:00:00 +1000

bank-core version v1-basic successfully demonstrates deadlock-free pessimistic database locking and high-throughput $O(1)$ ledger validation, but suffers from anemic procedural layers typical of raw browser-prompted AI code. To fix these leaky boundaries, the upcoming v2 will pivot to spec-driven development utilizing Claude Code to enforce domain-driven isolation.

GitHub

https://github.com/prule/bank-example/tree/v1-basic

Next episode

Evaluating bank-core v2-openspec-claude

The Core Wins: OpenAPI, Locking, and DB Auditing

The primary goal of v1-basic was to refresh my memory with respect to java and spring boot after being in the Kotlin/Ktor ecosystem for a while.

Springboot on Pauls Blog

Evaluating bank-core v2-openspec-claude

Introduction

Evaluating bank-core v1-basic: Locking, Concurrency, and the Limits of Web-Prompted AI

The Core Wins: OpenAPI, Locking, and DB Auditing