Accelerating Java and Spring Boot Web App Development with AI Coding Agents — Repository Practices for the Claude Code and Codex Era

The biggest lever for running AI coding agents fast on Java and Spring Boot is not model selection but shaping the repository so the AI cannot misread it. Pin the boundaries with Spring Modulith and hexagonal architecture, enforce them mechanically with ArchUnit and Modulith verify in CI, reproduce databases locally with Testcontainers @ServiceConnection, and expose your running app to AI through the Spring AI 1.1 MCP Server Boot Starter. This post lays out the full setup for AI-native Java and Spring Boot development.

Pick Your Coding-Agent Model by Opportunity Cost — Why I Run Fable 5 Low and Codex 5.6 Sol Light for Speed

Lately I've deliberately defaulted to light, fast settings: Fable 5 at the Low reasoning level in Claude Code, and 5.6 Sol at the Light reasoning level and the Fast speed level in Codex. Today's high-intelligence models fail with the same shape of mistakes whether you spend a lot of reasoning tokens or a few. If the failure mode is the same, review effort doesn't change, and what matters isn't token cost but wait time, which is opportunity cost. Hard to see, but its dominance is obvious once you accept that humans are the bottleneck.