Agent harnesses orchestrate code generation. Delivery is a longer pipeline. Here's the mental model I've been using to plug team, tools, context, and models into one value stream, and where the agent harness fits inside it.
Story points, t-shirts, fruit salads, and now tokens. A messy, honest look at why estimation was already broken before AI showed up, and what it takes to keep planning sane when the tools move faster than the humans.
Anthropic's first harness article inspired ralphctl. Their second one on generator-evaluator loops pushed me to build an evaluator for v0.2.0, and the tool changed identity.
A hands-on walkthrough of RFC 8693 token exchange using Spring Cloud Gateway, Keycloak, and three frontend frameworks. Architecture, implementation, observability, and the things the docs don't tell you.
What a personal AI assistant setup actually looks like after a month of daily use. Local embeddings, memory systems, proactive cron jobs, and the quiet shift from tool to infrastructure.
I watched a trainer fight a clipboard at a youth athletics session. I'd been that trainer. Eight hours of vibecoding later, the fix was live.
I built a sprint CLI for Claude Code and GitHub Copilot. The problems I didn't see coming and what it took to make AI-assisted coding feel like a real workflow.
